{"data":[{"model_id":"auto","model_name":"Auto","developer_id":12,"desc":"AIHubMix Smart Router: Fill in the model name as auto, and the gateway will automatically select the optimal model based on the request content;\n\nThe auto without a suffix uses the default strategy cost_optimized. You can explicitly specify the focus using auto:\u003cstrategy\u003e, such as auto (= auto:cost_optimized) cost priority: choose the cheapest as long as the capability meets the standard; auto:balanced balanced: considers capability / cost / latency\n\nauto:quality_first quality priority: prioritize selecting the strongest capability for complex reasoning and critical outputs\n\nauto:latency_critical low latency priority: prioritize selecting the fastest response","pricing":{"input":2,"output":2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,web,deepsearch,tools,function_calling,structured_outputs,long_context","input_modalities":"text,audio,image,video","endpoints":"","max_output":0,"context_length":1000000,"release_date":"2024-01-01","last_updated":"2024-01-01","output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-6.1-terra","model_name":"GPT 6.1 Terra","developer_id":12,"desc":"GPT-6.1 Terra is OpenAI’s multimodal reasoning model, supporting text and image inputs for tasks such as product photo matching, technical drawing interpretation, application interface interaction, and text drafting and revision. It combines speed and efficiency with visual reasoning, precise computer use, and clear, natural writing.","pricing":{"cache_read":0.05,"input":1,"output":5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":128000,"context_length":1050000,"release_date":"2026-10-26","last_updated":"2026-10-26","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"],"default":"medium"}],"vendor":"openai","schema_checked":false,"retire_stage":"active"},{"model_id":"kimi-k3.1-pro","model_name":"Kimi K3.1 Pro","developer_id":15,"desc":"Kimi K3.1 Pro is based on Moonshot AI’s Kimi K3.1, offering code generation and interactive content development capabilities for coding assistance, code analysis, and visual prototyping.","pricing":{"cache_read":0.2,"input":2,"output":10.5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image,video","endpoints":"","max_output":1048576,"context_length":1048576,"release_date":"2026-10-24","last_updated":"2026-10-24","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"],"default":"max"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"moonshot","schema_checked":false,"retire_stage":"active","pricing_status":"derived"},{"model_id":"kimi-k3.1-pro-highspeed","model_name":"Kimi K3.1 Pro Highspeed","developer_id":15,"desc":"Kimi K3.1 Pro Highspeed  is an accelerated serving option for Kimi K3.1 Pro, focused on responsive code generation for interactive coding, rapid prototyping, and latency-sensitive applications.","pricing":{"cache_read":0.2,"input":4,"output":21},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image,video","endpoints":"","max_output":1048576,"context_length":1048576,"release_date":"2026-10-24","last_updated":"2026-10-24","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"],"default":"max"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"moonshot","schema_checked":false,"retire_stage":"active","pricing_status":"derived"},{"model_id":"ideogram-vector-1","model_name":"Ideogram Vector 1","developer_id":21,"desc":"Ideogram Vector 1.0 is Ideogram’s first AI vector (SVG) generation model. It can directly generate high-quality, editable vector graphics from text prompts or existing images.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"image","cost_usd":0.353,"source":"img_price_config","variant":{"quality":"high","size":"reference"}},{"billable":"generate","unit":"image","cost_usd":0.22,"source":"img_price_config","variant":{"quality":"high","size":"standard"}},{"billable":"generate","unit":"image","cost_usd":0.143,"source":"img_price_config","variant":{"quality":"low","size":"reference"}},{"billable":"generate","unit":"image","cost_usd":0.143,"source":"img_price_config","variant":{"quality":"low","size":"standard"}},{"billable":"generate","unit":"image","cost_usd":0.176,"source":"img_price_config","variant":{"quality":"medium","size":"reference"}},{"billable":"generate","unit":"image","cost_usd":0.176,"source":"img_price_config","variant":{"quality":"medium","size":"standard"}},{"billable":"vectorize","unit":"image","cost_usd":0.11,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-10-22","last_updated":"2026-10-22","output_modalities":"image","vendor":"ideogram","schema_checked":true,"retire_stage":"active"},{"model_id":"gpt-6.1-sol","model_name":"GPT 6.1 Sol","developer_id":12,"desc":"GPT-6.1 Sol is OpenAI's latest model in the GPT-6 series, specifically designed for complex programming and agent workflows. GPT-6.1 Sol's performance in complex programming, computer operations, and professional work tasks is close to Astra, but at a lower cost. You can compare the two on your own tasks to weigh quality against cost.","pricing":{"cache_read":0.1,"cache_write":2.5,"input":2,"output":10,"tiers":[{"cache_read":0.2,"cache_write":5,"input":4,"output":15,"tier":{"size":272000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.1,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.2,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":15,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":4,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":128000,"context_length":1050000,"release_date":"2026-09-30","last_updated":"2026-09-30","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"],"default":"medium"}],"interleaved":{"openai.responses":true},"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"grok-imagine-image-2.0","model_name":"Grok Imagine Image 2.0","developer_id":9,"desc":"grok-imagine-image-2.0 is Grok's text-to-image model, supporting image generation and image editing using up to 5 reference images.","pricing":{"input":1,"output":1},"pricing_source":"billing_config","pricing_lines":[{"billable":"image_generation","unit":"image","cost_usd":0.044,"source":"billing_config","variant":{"match":{"quality":"low","size":"1K"}}},{"billable":"image_generation","unit":"image","cost_usd":0.055,"source":"billing_config","variant":{"match":{"quality":"low","size":"1.5K"}}},{"billable":"image_generation","unit":"image","cost_usd":0.066,"source":"billing_config","variant":{"match":{"quality":"low","size":"2K"}}},{"billable":"image_generation","unit":"image","cost_usd":0.066,"source":"billing_config","variant":{"match":{"quality":"medium","size":"1K"}}},{"billable":"image_generation","unit":"image","cost_usd":0.077,"source":"billing_config","variant":{"match":{"quality":"medium","size":"1.5K"}}},{"billable":"image_generation","unit":"image","cost_usd":0.088,"source":"billing_config","variant":{"match":{"quality":"medium","size":"2K"}}},{"billable":"image_generation","unit":"image","cost_usd":0.088,"source":"billing_config","variant":{"fallback":true}},{"billable":"image_input","unit":"image","cost_usd":0.011,"source":"billing_config"}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-10","last_updated":"2026-10","output_modalities":"image","schema_checked":true,"retire_stage":"active"},{"model_id":"jev-1.14","model_name":"Jev 1.14","developer_id":48,"desc":"Jev 1.14 is TypeSafe’s structured decision model for classification, scoring, and agent routing, returning typed results with calibrated probabilities. Compared with Jev 1.13, it brings improvements in multilingual support and adds experimental bounding-box outputs for images.","pricing":{"input":0.0462,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"decision","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":64000,"release_date":"2026-10-15","last_updated":"2026-10-15","vendor":"typesafe","schema_checked":false,"retire_stage":"active"},{"model_id":"minimax-m3.1-flash","model_name":"MiniMax M3.1 Flash","developer_id":18,"desc":"MiniMax-M3.1-Flash is MiniMax's latest flagship model, aimed at office automation, software engineering, visual reasoning, and professional analytics. It combines multi-step task execution with front-end and presentation-creation capabilities, supporting workflows that transform information and visual references into tangible deliverables.","pricing":{"cache_read":0.0165,"input":0.165,"output":0.66},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image,video","endpoints":"","max_output":524288,"context_length":1000000,"release_date":"2026-10-19","last_updated":"2026-10-19","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"],"default":"max"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"minimax","schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-v4.1-flash-1017","model_name":"DeepSeek V4.1 Flash 1017","developer_id":7,"desc":"The official latest version of DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. API usage and pricing remain unchanged—you can still access the latest model using deepseek-flash.","pricing":{"cache_read":0.0031,"input":0.155,"output":0.62},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":393216,"context_length":1000000,"release_date":"2026-10-17","last_updated":"2026-10-17","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high","max"],"default":"high"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"deepseek","open_weights":true,"schema_checked":false,"promotion":{"name":"deepseek-v4.1-flash-1017 limited-time special offer","off_percent":50,"time_type":"absolute","absolute":{"start":"2026-10-29T07:00:00Z","end":"2026-11-12T07:00:00Z"}},"retire_stage":"active"},{"model_id":"gemini-omni-1.1-flash","model_name":"Gemini Omni 1.1 Flash","developer_id":8,"desc":"Gemini Omni Flash (gemini-omni-1.1-flash) is a high-performance multimodal model designed for high-speed video generation, editing, and cinematic-level control.","pricing":{"cache_read":0.15,"input":1.5,"output":9},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.15,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":9,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_audio_tokens","unit":"million_tokens","cost_usd":1.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_image_tokens","unit":"million_tokens","cost_usd":1.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_video_tokens","unit":"million_tokens","cost_usd":1.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_video_tokens","unit":"million_tokens","cost_usd":17.505,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text,image,audio,video","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-08-28","last_updated":"2026-08-28","output_modalities":"video","schema_checked":false,"retire_stage":"active"},{"model_id":"glm-5.3-prime","model_name":"GLM 5.3 Prime","developer_id":5,"desc":"GLM-5.3-Prime is the high-speed version of GLM-5.3, with comprehensive advancements in programming and agent capabilities that reach open-source SOTA levels. Its internal programming benchmarks are 50% better than the previous generation, and it can deliver end-to-end production-grade results. It exhibits emergent cybersecurity capabilities, with the CyberGym vulnerability-discovery benchmark achieving the current best. It supports a 1M-token context window, 128K-token output, and three tiers of deep reasoning, making it suitable for long-range, complex tasks.","pricing":{"cache_read":0.59,"input":2.35,"output":8.23},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":131072,"context_length":1048576,"release_date":"2026-10","last_updated":"2026-10","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"],"default":"max"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","schema_checked":false,"retire_stage":"active","pricing_status":"derived"},{"model_id":"gemini-4-argon","model_name":"Gemini 4 Argon","developer_id":8,"desc":"Gemini 4 Argon is Google DeepMind’s multimodal reasoning model for complex software engineering, financial research, legal drafting, and cybersecurity defense. It supports sustained reasoning across long, multi-step workflows, combining coding capabilities with chart and long-video understanding. It can also autonomously discover, validate, and patch software vulnerabilities.","pricing":{"cache_read":0.1,"input":2,"output":10},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.1,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_audio_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_video_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.014,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image,video,audio,pdf","endpoints":"","max_output":65536,"context_length":1048576,"output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"],"default":"medium"}],"vendor":"google","schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-nano-banana-2.1","model_name":"Gemini Nano Banana 2.1","developer_id":8,"desc":"Gemini Nano Banana 2.1 (gemini-nano-banana-2.1) is Google's latest high-efficiency image generation and conversational editing model. As an upgraded version of Nano Banana 2 (Gemini 3.1 Flash Image), it significantly improves visual quality, prompt adherence, role consistency in multi-turn conversations, and text rendering while maintaining Flash-level speed and cost efficiency. It can be regarded as a more efficient counterpart to Gemini 3 Pro Image (Nano Banana Pro).","pricing":{"cache_read":0.15,"input":1.5,"output":7.5},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.15,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":7.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_image_tokens","unit":"million_tokens","cost_usd":1.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_image_tokens","unit":"million_tokens","cost_usd":30,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"image_generation,llm","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":65536,"release_date":"2026-10-07","last_updated":"2026-10-07","output_modalities":"image,text","schema_checked":true,"retire_stage":"active"},{"model_id":"muse-wonder","model_name":"Muse Wonder","developer_id":34,"desc":"Muse Wonder is Meta’s model for complex coding, long-running agents, and computer use. With a 1M-token context window, it plans multi-step tasks, delegates to sub-agents, and combines Active Memory with Active Focus to retain relevant context and sustain progress on challenging tasks.","pricing":{"cache_read":0.22,"input":4.4,"output":22},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image,video,audio,pdf","endpoints":"","max_output":0,"context_length":1048576,"release_date":"2026-09-03","last_updated":"2026-09-03","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"],"default":"medium"}],"interleaved":{"anthropic.messages":true,"openai.responses":true},"vendor":"meta","schema_checked":false,"retire_stage":"active"},{"model_id":"cohere-rerank-v5-fast","model_name":"Cohere Rerank V5 Fast","developer_id":6,"desc":"cohere-rerank-v5-fast is Cohere's enterprise search and retrieval-augmented generation (RAG) reranking model. It can reorder retrieval results based on query relevance, supports multiple languages, and provides stable relevance scoring to help filter out irrelevant content. Its Context Focus feature can also extract the most relevant passages from documents, reducing the language model's token consumption and response latency.","pricing":{"input":0.02,"output":0.02},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"rerank","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-10","last_updated":"2026-10","schema_checked":false,"retire_stage":"active"},{"model_id":"cohere-rerank-v5-pro","model_name":"Cohere Rerank V5 Pro","developer_id":6,"desc":"cohere-rerank-v5-pro is Cohere's enterprise search and retrieval-augmented generation (RAG) reranking model. It can reorder retrieval results based on query relevance, supports multiple languages, and provides stable relevance scoring to help filter out irrelevant content. Its Context Focus feature can also extract the most relevant passages from documents, reducing the language model's token consumption and response latency.","pricing":{"input":0.05,"output":0.05},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"rerank","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-10","last_updated":"2026-10","schema_checked":false,"retire_stage":"active"},{"model_id":"claude-haiku-5-5","model_name":"Claude Haiku 5.5","developer_id":2,"desc":"Claude Haiku 5.5 is Anthropic’s next-generation product, designed for high-throughput, cost-sensitive tasks. It can reliably handle fast and repetitive workloads such as summarization, context compression, database queries, and classification requests. It is also well suited to be used as a sub-agent model in programming workflows alongside Opus 5.5 and Sonnet 5.5.","pricing":{"cache_read":0.01,"cache_write":0.125,"input":0.1,"output":0.5,"tiers":[{"cache_read":0.05,"cache_write":0.625,"input":0.5,"output":2.5,"tier":{"size":100000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":0.2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":100000}},{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":1,"source":"billing_config","tier":{"name":"tier2","min_tokens":100001,"max_tokens":-1}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":0.125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":100000}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":0.625,"source":"billing_config","tier":{"name":"tier2","min_tokens":100001,"max_tokens":-1}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":100000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.625,"source":"billing_config","tier":{"name":"tier2","min_tokens":100001,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.01,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":100000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.05,"source":"billing_config","tier":{"name":"tier2","min_tokens":100001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":100000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier2","min_tokens":100001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.1,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":100000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier2","min_tokens":100001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":128000,"context_length":1000000,"release_date":"2026-10-08","last_updated":"2026-10-08","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"],"default":"medium"}],"interleaved":{"anthropic.messages":true},"vendor":"anthropic","schema_checked":false,"retire_stage":"active"},{"model_id":"elephant-1-free","model_name":"Elephant 1 (free)","developer_id":53,"desc":"Elephant 1 is a 9B decision model developed by Base Labs, Baseten's research team, and built on the Qwen3.5-9B architecture. Featuring a context length of 16,384 tokens, this model is designed to analyze a given state in text or JSON format alongside typed questions like yes/no, multiple choice, or ordinal queries. It offers a specialized and efficient solution for automated decision-making workflows.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"decision","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-image-2.1-pro","model_name":"Qwen Image 2.1 Pro","developer_id":13,"desc":"Qwen-Image-2.1-Pro is a unified text-to-image generation and image-editing model in the Tongyi Qianwen (Qwen) series. Its visual generation component contains only 7 billion parameters (a 32-layer single-stream DiT), achieving a good balance between generation quality, inference efficiency, and versatility. This release includes four key improvements:\n- Compact and efficient: adopts a lightweight architecture that combines hybrid-granularity attention and prefix KV cache reuse to deliver high-quality image generation with low computational cost.\n- Native transparency support, unified generation and editing: can generate regular or transparent (RGBA) images from text, edit transparent layers, and extract subjects from photos—all handled by a single model.\n- Versatile editing: supports up to 10 reference images, allows specifying local edit regions via circular or freehand annotations or separate masks, and preserves identity features of people and products.\n- Photorealistic textures and refined aesthetics: improved typography, portrait lighting, and detail rendering for more visually appealing results.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"image","cost_usd":0.0352,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-10-10","last_updated":"2026-10-10","output_modalities":"image","vendor":"alibaba","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-image-2.1-turbo","model_name":"Qwen Image 2.1 Turbo","developer_id":13,"desc":"Qwen-Image-2.1-Turbo is currently the best-balanced and most cost-effective open-source image generation model in the Qwen-Image series, offering four core advantages: a lightweight model with strong performance and excellent value; native transparency support with integrated generation and editing; flexible editing—supporting multiple reference images, local control, high-fidelity restoration, and comprehensive editing capabilities; and realistic textures, elegant typography, and refined portrait quality.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"image","cost_usd":0.0141,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-10-10","last_updated":"2026-10-10","output_modalities":"image","vendor":"alibaba","schema_checked":false,"retire_stage":"active"},{"model_id":"span-01-lite-free","model_name":"Span 01 Lite (free)","developer_id":54,"desc":"Span-01 Lite is a free, lightweight behavior scoring model developed by Respan. This model analyzes text based on plain-language behaviors that you define and returns the probability of each behavior being present. It offers an efficient and accessible way to evaluate and score content according to your custom criteria.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"decision","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"mammoth-1-free","model_name":"Mammoth 1 (free)","developer_id":53,"desc":"Mammoth 1 is a 27B decision model developed by Base Labs, Baseten's research team, and built on Qwen3.5-27B. Featuring a context length of 16,384 tokens, the model is designed to analyze a given state in text or JSON format and answer typed questions such as yes/no, multiple choice, or ordinal queries. It offers a robust and specialized solution for structured decision-making tasks.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"decision","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"nemotron-3.5-super-vl-free","model_name":"Nemotron 3.5 Super VL (free)","developer_id":17,"desc":"NVIDIA Nemotron 3.5 Super VL is an open, multimodal mixture-of-experts model developed by NVIDIA that features 12 billion active parameters out of 120 billion total. It supports a wide range of inputs including text, images, documents, GUI screenshots, and video. With an extensive context length of 1,000,000 tokens, this model is highly capable of handling complex, long-context multimodal tasks.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-6-luna","model_name":"GPT 6 Luna","developer_id":12,"desc":"GPT-6 Luna is OpenAI's latest and most efficient model, designed for focused, high-throughput tasks.","pricing":{"cache_read":0.01,"cache_write":0.125,"input":0.1,"output":0.5,"tiers":[{"cache_read":0.02,"cache_write":0.25,"input":0.2,"output":0.75,"tier":{"size":272000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.25,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.01,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.02,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.75,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.1,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.2,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm,decision","features":"","input_modalities":"text,image","endpoints":"","max_output":128000,"context_length":1050000,"release_date":"2026-09-23","last_updated":"2026-09-23","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"],"default":"medium"}],"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-6-sol","model_name":"GPT 6 Sol","developer_id":12,"desc":"GPT-6 Sol is OpenAI's latest model in the GPT-6 series, specifically designed for complex programming and agent workflows.","pricing":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":10,"tiers":[{"cache_read":0.4,"cache_write":5,"input":4,"output":15,"tier":{"size":272000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.4,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":15,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":4,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":128000,"context_length":1050000,"release_date":"2026-09-23","last_updated":"2026-09-23","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"],"default":"medium"}],"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"claude-opus-5-5","model_name":"Claude Opus 5.5","developer_id":2,"desc":"Claude Opus 5.5 is Anthropic’s latest flagship model. In Anthropic’s comprehensive alignment testing, Opus 5.5 is the strongest-performing model tested to date. It also includes the safety safeguards Anthropic has developed for its most capable models.","pricing":{"cache_read":0.2,"cache_write":5,"input":4,"output":20},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":8,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":20,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":4,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image,pdf","endpoints":"","max_output":128000,"context_length":1000000,"release_date":"2026-09-23","last_updated":"2026-09-23","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"],"default":"medium"}],"interleaved":{"anthropic.messages":true},"vendor":"anthropic","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"claude-sonnet-5-5","model_name":"Claude Sonnet 5.5","developer_id":2,"desc":"Claude Sonnet 5.5 is the next-generation product in Anthropic’s Sonnet model series; Claude Sonnet 5.5 offers the best balance between speed and intelligence. The following five major changes will affect code currently running on Claude Sonnet 5:\n1. Using \"between_tools\" can disable up-front thinking.\n2. Forcing the use of tools will result in an error.\n3. Thinking content blocks are bound to the model and the conversation.\n4. On the Claude API and Google Cloud, the older \"computer_20251124\" computer tool usage is no longer accepted.\n5. The advisor tool will refuse to accept Claude Opus 4.8, Claude Opus 4.7, and Claude Sonnet 5 as advisor models.\n\nUse between_tools to disable up-front thinking.\nForcing tool use will return an error.\nThinking blocks are bound to the model and the conversation.\nOn the Claude API and Google Cloud, early computer_20251124 computer tool usage is no longer accepted.\nThe advisor tool no longer accepts Claude Opus 4.8, Claude Opus 4.7, and Claude Sonnet 5 as advisors.","pricing":{"cache_read":0.1,"cache_write":2.5,"input":2,"output":10},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":4,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.1,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image,pdf","endpoints":"","max_output":128000,"context_length":1000000,"release_date":"2026-09-29","last_updated":"2026-09-29","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"],"default":"high"}],"interleaved":{"anthropic.messages":true},"vendor":"anthropic","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"mistral-large-4-0","model_name":"Mistral Large 4.0","developer_id":10,"desc":"Mistral Large 4 is Mistral AI’s frontier multimodal model with text and image input, designed for complex reasoning, coding, and agentic workflows. It supports tool calling and structured outputs, with a 512K-token context window and up to 256K output tokens, making it well suited for long-context and multi-step tasks. Compared with earlier Mistral large models, Mistral Large 4 places greater emphasis on multimodal understanding, extended context, and agentic execution.","pricing":{"cache_read":0.139944,"input":1.36,"output":4.17996},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":1000000,"release_date":"2026-10-06","last_updated":"2026-10-06","output_modalities":"text","vendor":"mistral","schema_checked":false,"retire_stage":"active"},{"model_id":"grok-4.7","model_name":"Grok 4.7","developer_id":9,"desc":"Grok 4.7 is xAI’s flagship model for coding, agentic tasks, and professional knowledge work. Compared with Grok 4.6, it uses a larger base model and longer reinforcement-learning training, improving long-horizon task execution, self-verification, context management, and document and presentation creation.","pricing":{"cache_read":0.5,"input":2,"output":6,"tiers":[{"cache_read":1,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":1,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":6,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":12,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":4,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":500000,"release_date":"2026-09-22","last_updated":"2026-09-22","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"],"default":"medium"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"xai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"mimo-v2.6-flash","model_name":"MiMo V2.6 Flash","developer_id":31,"desc":"mimo-v2.6-flash is Xiaomi's latest model series. A fully multimodal, highly intelligent, low-cost efficient inference model, it is the best-balanced choice for high-frequency invocations and large-scale tasks in professional office settings.","pricing":{"cache_read":0.0031,"input":0.155,"output":0.31},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0031,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.31,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.155,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.005,"source":"billing_config"}],"has_zdr_provider":true,"types":"llm","features":"","input_modalities":"text,image,video,audio","endpoints":"","max_output":131072,"context_length":1048576,"release_date":"2026-09-22","last_updated":"2026-09-22","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"xiaomi","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"mimo-v2.6-pro","model_name":"MiMo V2.6 Pro","developer_id":31,"desc":"MiMo-V2.6-Pro is Xiaomi’s trillion-parameter, natively omni-modal flagship reasoning model for complex projects, long-horizon agentic tasks, coding, research, and professional knowledge work. It supports a 1M-token context window and up to 128K output tokens. Compared with V2.5, it delivers stronger reasoning and long-task performance while retaining the same API pricing.","pricing":{"cache_read":0.00384,"input":0.48,"output":0.96},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.00384,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.96,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.48,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.005,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image,video,audio","endpoints":"","max_output":131072,"context_length":1048576,"release_date":"2026-09-22","last_updated":"2026-09-22","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"xiaomi","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"mimo-v2.6-pro-ultraspeed","model_name":"MiMo V2.6 Pro Ultraspeed","developer_id":31,"desc":"MiMo-V2.6-Pro-UltraSpeed combines the flagship performance of MiMo-V2.6-Pro and offers up to 20× output speed to serve highly real-time interactive and latency-sensitive production scenarios.","pricing":{"cache_read":0.0384,"input":4.8,"output":9.6},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0384,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":9.6,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":4.8,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.005,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image,video,audio","endpoints":"","max_output":131072,"context_length":1048576,"release_date":"2026-09-22","last_updated":"2026-09-22","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"xiaomi","variant_of":"mimo-v2.6-pro","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-3.8-flash-lite-tts","model_name":"Gemini 3.8 Flash Lite Tts","developer_id":8,"desc":"Gemini 3.8 Flash-Lite TTS (gemini-3.8-flash-lite-tts) is Google's fast, cost-efficient workhorse text-to-speech model, built to replace gemini-3.1-flash-tts-preview for high-throughput production workloads.","pricing":{"cache_read":0.125,"input":0.5,"output":6},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":0.5,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":6,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"tts","features":"","input_modalities":"text","endpoints":"","max_output":16384,"context_length":8192,"release_date":"2026-09-24","last_updated":"2026-09-24","output_modalities":"audio","vendor":"google","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-3.8-flash-tts","model_name":"Gemini 3.8 Flash Tts","developer_id":8,"desc":"Gemini 3.8 Flash TTS (gemini-3.8-flash-tts) is Google's 3.8 Flash text-to-speech audio model, designed to deliver studio-grade sound fidelity, expressive performance, and long-form stability.","pricing":{"cache_read":0.125,"input":0.5,"output":9},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":0.5,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":9,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"tts","features":"","input_modalities":"text","endpoints":"","max_output":16384,"context_length":8192,"release_date":"2026-09-24","last_updated":"2026-09-24","output_modalities":"audio","vendor":"google","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3.8-omni-flash","model_name":"Qwen3.8 Omni Flash","developer_id":13,"desc":"Qwen3.8 Omni Flash is Alibaba Cloud Qwen's next-generation native multimodal model, supporting 1M-length sequences and able to directly accept text, images, audio, and video as input. It is based on the Qwen3.8-Flash-Next architecture. The model is designed for agent capabilities in real productivity scenarios: while offering agentic abilities such as programming, text knowledge work, and GUI operation, it also achieves significant results in audio/video-centered agentic applications—such as video editing, music video creation, film production and narration, audio/video-to-text-and-image summarization, and audio/video dialogue—that require integrated processing of text, images, audio, and video. It supports 2-channel and 4-channel spatial audio parsing, is compatible with DashScope and OpenAI protocols, and it is recommended to install the accompanying Qwen-MM-Plugins to facilitate agent frameworks' access to native multimodal capabilities.","pricing":{"cache_read":0.014075,"cache_write":0.175937,"input":0.1126,"output":0.380025},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.1759375,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.014075,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.380025,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.1126,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.000548,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image,audio,video","endpoints":"","max_output":131072,"context_length":1000000,"release_date":"2026-08-26","last_updated":"2026-08-26","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"],"default":"xhigh"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"alibaba","schema_checked":false,"retire_stage":"active"},{"model_id":"jev-1.13","model_name":"Jev 1.13","developer_id":48,"desc":"Jev is a structured decision model launched by TypeSafe and is also their first \"System One\" model.\n\nSystem One models can make structured decisions for software quickly, returning typed selection results rather than freely generated text. They are suitable for routing, classification, and other decision nodes in applications—where fast, predictable answers are more important than generating natural language content.","pricing":{"input":0.0462,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"decision","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":64000,"release_date":"2026-09-17","last_updated":"2026-09-17","vendor":"typesafe","schema_checked":false,"retire_stage":"active"},{"model_id":"jev-latest","model_name":"Jev","developer_id":48,"desc":"Jev is a structured decision model launched by TypeSafe and is also their first \"System One\" model.\n\nSystem One models can make structured decisions for software quickly, returning typed selection results rather than freely generated text. They are suitable for routing, classification, and other decision nodes in applications—where fast, predictable answers are more important than generating natural language content.","pricing":{"input":0.0462,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"decision","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":64000,"release_date":"2026-09-17","last_updated":"2026-09-17","vendor":"typesafe","variant_of":"jev-1.13","variant_kind":"rolling-alias","schema_checked":false,"retire_stage":"active"},{"model_id":"decision-model-preview","model_name":"Decision Model Preview","developer_id":13,"desc":"Alibaba Cloud has launched the decision model decision-model-preview. This structured decision model is designed for high-frequency business judgments; it can concurrently perform classification, binary decisions, and scoring based on text or business state, and returns probability distributions and confidence levels. It is suitable for scenarios such as ticket routing, content moderation, agent routing, and result verification. Free for a limited time.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"decision","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":64000,"release_date":"2026-09-24","last_updated":"2026-09-24","schema_checked":false,"retire_stage":"active"},{"model_id":"step-5-preview","model_name":"Step 5 Preview","developer_id":16,"desc":"Step 5 Preview is StepFun's next-generation flagship base model designed for real-world tasks, with a focus on programming and professional expertise.","pricing":{"cache_read":0.054,"input":1.08,"output":3.0888},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image,video","endpoints":"","max_output":64000,"context_length":1000000,"release_date":"2026-09-20","last_updated":"2026-09-20","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"],"default":"medium"}],"vendor":"stepfun","schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seedream-5-0-flash","model_name":"Doubao Seedream 5.0 Flash","developer_id":4,"desc":"Doubao-Seedream-5.0-flash is a fast image-creation model released by ByteDance that balances speed and cost efficiency; it supports precise editing, layer separation, and transparent-background output, making it suitable for high-frequency, large-scale image production and rapid interactive scenarios.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"image","cost_usd":0.0186,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"image","vendor":"bytedance","schema_checked":false,"retire_stage":"active"},{"model_id":"glm-5.3-flashx","model_name":"GLM 5.3 Flashx","developer_id":5,"desc":"GLM-5.3-FlashX is Z.AI’s high-speed inference model, designed for coding agents, real-time interactions, long-running agentic workflows, and applications that require fast token generation. It is heavily optimized at the inference infrastructure level for lower latency and higher execution efficiency, reaching generation speeds of up to 200 tokens per second. Compared with GLM-5.3-Flash, GLM-5.3-FlashX delivers up to 5× faster inference, with a stronger focus on low-latency and high-throughput workloads.","pricing":{"cache_read":0.08037,"input":0.282,"output":0.987},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"","input_modalities":"text,image,video","endpoints":"","max_output":0,"context_length":1000000,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-6-astra","model_name":"GPT 6 Astra","developer_id":12,"desc":"GPT-6 Astra is OpenAI's newest and most intelligent model, with industry-leading performance in computer operations, web browsing, software engineering, scientific research, and professional work. It excels at executing multi-step workflows across code, browsers, and various professional software. Astra can achieve better results with significantly fewer output tokens, making its estimated API cost per task lower.","pricing":{"cache_read":1,"cache_write":12.5,"input":10,"output":50,"tiers":[{"cache_read":2,"cache_write":25,"input":20,"output":75,"tier":{"size":272000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":12.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":25,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":1,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":50,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":75,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":20,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,thinking,structured_outputs","input_modalities":"text,image","endpoints":"chat_completions,responses","max_output":128000,"context_length":1050000,"release_date":"2026-09-05","last_updated":"2026-09-05","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"],"default":"medium"}],"interleaved":{"openai.responses":true},"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"jina-ocr-v1","model_name":"Jina Ocr V1","developer_id":22,"desc":"jina-ocr-v1 is Jina AI's latest page-to-Markdown document parsing model, with 570 million active parameters. Its architecture inherits the DeepEncoder from DeepSeek-OCR; jina-ocr-v1 retains that encoder and decoder, and thus supports document parsing for approximately 100 languages.(This model is free for a limited time.)","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"ocr","features":"","input_modalities":"image","endpoints":"","max_output":0,"context_length":32000,"release_date":"2026-09-14","last_updated":"2026-09-14","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-3.8-flash","model_name":"Gemini 3.8 Flash","developer_id":8,"desc":"Gemini 3.8 Flash is Google's most intelligent Flash-series model, designed for long-running software engineering tasks, autonomous agents, and complex enterprise workflows, while retaining the Flash series' fast responsiveness and cost-effectiveness.","pricing":{"cache_read":0.075,"input":0.75,"output":3.75},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":0.5,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.075,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_audio_tokens","unit":"million_tokens","cost_usd":0.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_video_tokens","unit":"million_tokens","cost_usd":0.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.014,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs,web,long_context","input_modalities":"text,image,video,audio,pdf","endpoints":"chat_completions,gemini_api,claude_api","max_output":65536,"context_length":1048576,"release_date":"2026-09-02","last_updated":"2026-09-02","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"],"default":"medium"}],"vendor":"google","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-v4.1-flash","model_name":"DeepSeek V4.1 Flash","developer_id":7,"desc":"DeepSeek-V4.1-Flash model official release. This is the smallest model in DeepSeek’s new model-architecture series, featuring native multimodal visual understanding capabilities. The new architecture is designed to deliver a higher capability ceiling, faster inference speeds, greater throughput, and scalability to larger-parameter models.","pricing":{"cache_read":0.002816,"input":0.1408,"output":0.5632},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0031,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.006196,"source":"billing_config","tier":{"name":"peak","min_tokens":0,"max_tokens":-1,"time_condition":{"timezone":"UTC","ranges":["01:00-04:00","06:00-10:00"]}}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.62,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.2392,"source":"billing_config","tier":{"name":"peak","min_tokens":0,"max_tokens":-1,"time_condition":{"timezone":"UTC","ranges":["01:00-04:00","06:00-10:00"]}}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.155,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.3098,"source":"billing_config","tier":{"name":"peak","min_tokens":0,"max_tokens":-1,"time_condition":{"timezone":"UTC","ranges":["01:00-04:00","06:00-10:00"]}}}],"has_zdr_provider":true,"types":"llm","features":"tools,function_calling,structured_outputs,thinking","input_modalities":"text,image","endpoints":"chat_completions,claude_api","max_output":384000,"context_length":1000000,"release_date":"2026-09-08","last_updated":"2026-09-08","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"],"default":"high"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"deepseek","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"glm-5.3-flash","model_name":"GLM 5.3 Flash","developer_id":5,"desc":"GLM-5.3-Flash is a high-efficiency multimodal model from Z.AI. It supports a context window of roughly 1 million tokens, along with text, image, and video inputs, and includes tool-calling capabilities. It is primarily designed for coding agents, complex reasoning, and long-horizon software engineering tasks. Built on the existing GLM technology stack, the model has been further post-trained and optimized to deliver strong performance while placing greater emphasis on inference efficiency, responsiveness, and cost.The model is offered at a limited-time 50% discount; users are welcome to try it.","pricing":{"cache_read":0.032396,"input":0.11268,"output":0.39438},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,video","endpoints":"","max_output":131072,"context_length":1048576,"release_date":"2026-08-26","last_updated":"2026-08-26","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"],"default":"max"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"zhipu","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"xiaomi-mimo-v2.6-pro-free","model_name":"Xiaomi Mimo V2.6 Pro (free)","developer_id":31,"desc":"xiaomi-mimo-v2.6-pro-free is the open free version of xiaomi-mimo-v2.6-pro.  To maintain reliable service, each account is limited to 5 requests per minute, 100 requests per day, and 1 million tokens per day.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image,video,audio","endpoints":"","max_output":131072,"context_length":1048576,"release_date":"2026-09-22","last_updated":"2026-09-22","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"xiaomi","variant_of":"mimo-v2.6-pro","variant_kind":"pricing-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"claude-fable-5-1","model_name":"Claude Fable 5.1","developer_id":2,"desc":"Claude-fable-5-1 is Anthropic's most capable newly released model, suitable for the most demanding reasoning and long-running agent work. Claude Fable 5.1, while keeping input and output prices the same as Claude Fable 5, reduces cache read prices to one quarter of the original and is more capable for long-running agent programming, multi-step research, and document, spreadsheet, and slide processing. (The model is extremely expensive and not recommended for casual use.)","pricing":{"cache_read":0.275,"cache_write":13.75,"input":11,"output":55},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":22,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":13.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":13.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.275,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":55,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":11,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,pdf","endpoints":"chat_completions,claude_api","max_output":128000,"context_length":1000000,"release_date":"2026-09-02","last_updated":"2026-09-02","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"],"default":"medium"}],"interleaved":{"anthropic.messages":true},"vendor":"anthropic","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-live-transcribe","model_name":"GPT Live Transcribe","developer_id":12,"desc":"OpenAI's latest realtime speech-to-text model, built for low-latency use — it streams incremental transcripts as audio arrives, ideal for live captions, dictation, and voice interfaces. Supports automatic transcription across 57 languages, with keyword/context hints and a tunable latency-vs-accuracy tradeoff.","pricing":{"input":0,"output":0},"pricing_source":"billing_config","pricing_lines":[{"billable":"audio_input_seconds","unit":"minute","cost_usd":0.017,"source":"billing_config"}],"has_zdr_provider":false,"types":"stt","features":"","input_modalities":"audio,text","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-07-28","last_updated":"2026-07-28","output_modalities":"text","vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-realtime-2.1","model_name":"GPT Realtime 2.1","developer_id":12,"desc":"GPT-Realtime-2.1 is a reasoning speech-to-speech model for the Realtime API, with tool use and configurable reasoning effort, improving on GPT-Realtime-2 in alphanumeric recognition, silence and noise handling, and interruption behavior.","pricing":{"cache_read":0.4,"input":4,"output":24},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_audio_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"t1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_image_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"t1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_text_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"t1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_audio_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"t1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_image_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"t1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_text_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"t1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_audio_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"t1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_text_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"t1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"tts,stt","features":"","input_modalities":"text,audio,image","endpoints":"","max_output":32000,"context_length":128000,"release_date":"2026-07-06","last_updated":"2026-07-06","output_modalities":"audio,text","reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"],"default":"low"}],"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-3.8-27b","model_name":"Qwen 3.8 27B","developer_id":13,"desc":"Qwen3.8-27b is an Alibaba-released dense vision-language model with open-source weights. Qwen3.8 was developed based on the architecture of Qwen3.5, achieving significant improvements in encoding capability, handling professional tasks, research tasks, and tasks that require long-term completion. Qwen3.8-27B integrates these advantages into a compact, easy-to-deploy dense model — a native vision-language model capable of understanding image and video information and featuring flexible cognitive control capabilities. This model can more reliably accomplish complex, multi-step tasks.","pricing":{"input":1.1,"output":1.65},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"","input_modalities":"text,image,video","endpoints":"","max_output":0,"context_length":131072,"release_date":"2026-08-12","last_updated":"2026-08-12","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"glm-5.3","model_name":"GLM 5.3","developer_id":5,"desc":"GLM-5.3 is Z.AI’s coding and agentic reasoning model, built for complex software engineering, long-running agent tasks, vulnerability analysis, and other demanding workloads. Building on GLM-5.2, it incorporates further post-training improvements to deliver stronger coding performance, better task execution, and greater token efficiency.\n\nWe currently offer the production-ready GLM-5.3 API with unlimited concurrency, making it well suited for high-throughput workloads, coding agents, and large-scale automation. For a limited time, GLM-5.3 is available at 10% off.","pricing":{"cache_read":0.2817,"input":1.1268,"output":3.9438},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":131072,"context_length":1048576,"release_date":"2026-08-14","last_updated":"2026-08-14","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"],"default":"max"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-kimi-k3.1-pro","model_name":"Coding Kimi K3.1 Pro","developer_id":15,"desc":"coding-kimi-k3.1-pro is a coding preview of Kimi K3.1 Pro, available for evaluation only. The service is highly unstable and is not recommended for production use. AIHubMix will make the stable API available once it is officially released.","pricing":{"cache_read":0.132,"input":0.88,"output":3.23},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-10-24","last_updated":"2026-10-24","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"coding-kimi-k3.1-pro-highspeed","model_name":"Coding Kimi K3.1 Pro Highspeed","developer_id":15,"desc":"coding-kimi-k3.1-pro-highspeed is a coding preview of Kimi K3.1 Pro highspeed, available for evaluation only. The service is highly unstable and is not recommended for production use. AIHubMix will make the stable API available once it is officially released.","pricing":{"cache_read":0.264,"input":1.76,"output":6.46},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-10-24","last_updated":"2026-10-24","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3.8-max-2026-09-02","model_name":"Qwen3.8 Max 2026 09-02","developer_id":13,"desc":"Qwen3.8-Max-0902 (also known as qwen3.8-max-2026-09-02) is a snapshot version of Alibaba Cloud Tongyi Qianwen's qwen3.8-max. It pushes encoding depth further, enabling it to handle more complex engineering-level projects and long-term autonomous development; collaborative agent capabilities are significantly enhanced, performing more confidently in multi-tool orchestration and end-to-end delivery; visual understanding is comprehensively improved, with more sensitive and accurate chart reasoning, document parsing, and multimodal perception. Continuing the 1-million-context window, reasoning modes, and a complete tool ecosystem, it continues to evolve at a higher level of intelligence.","pricing":{"cache_read":0.169,"cache_write":2.1125,"input":1.69,"output":5.07},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":2.1125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.169,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":5.07,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.69,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.000548,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,web,long_context,thinking","input_modalities":"text,image,video","endpoints":"","max_output":131072,"context_length":1000000,"release_date":"2026-09-02","last_updated":"2026-09-02","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"],"default":"xhigh"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"alibaba","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-image-2.5-flare","model_name":"GPT Image 2.5 Flare","developer_id":12,"desc":"GPT-Image-2.5 Flare is OpenAI's latest image model, the fastest and suited for everyday high-quality image generation. It accepts text and image inputs and produces image outputs. The model supports quality settings: low, medium, high, xhigh, max, and auto.","pricing":{"cache_read":1.25,"input":5,"output":30},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":1.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_image_tokens","unit":"million_tokens","cost_usd":8,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_image_tokens","unit":"million_tokens","cost_usd":30,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"generate","unit":"image","cost_usd":0.211,"source":"img_price_config","variant":{"quality":"auto","size":"1024x1024"}},{"billable":"generate","unit":"image","cost_usd":0.165,"source":"img_price_config","variant":{"quality":"auto","size":"1024x1536"}},{"billable":"generate","unit":"image","cost_usd":0.165,"source":"img_price_config","variant":{"quality":"auto","size":"1536x1024"}},{"billable":"generate","unit":"image","cost_usd":0.211,"source":"img_price_config","variant":{"quality":"high","size":"1024x1024"}},{"billable":"generate","unit":"image","cost_usd":0.165,"source":"img_price_config","variant":{"quality":"high","size":"1024x1536"}},{"billable":"generate","unit":"image","cost_usd":0.165,"source":"img_price_config","variant":{"quality":"high","size":"1536x1024"}},{"billable":"generate","unit":"image","cost_usd":0.006,"source":"img_price_config","variant":{"quality":"low","size":"1024x1024"}},{"billable":"generate","unit":"image","cost_usd":0.005,"source":"img_price_config","variant":{"quality":"low","size":"1024x1536"}},{"billable":"generate","unit":"image","cost_usd":0.005,"source":"img_price_config","variant":{"quality":"low","size":"1536x1024"}},{"billable":"generate","unit":"image","cost_usd":0.053,"source":"img_price_config","variant":{"quality":"medium","size":"1024x1024"}},{"billable":"generate","unit":"image","cost_usd":0.041,"source":"img_price_config","variant":{"quality":"medium","size":"1024x1536"}},{"billable":"generate","unit":"image","cost_usd":0.041,"source":"img_price_config","variant":{"quality":"medium","size":"1536x1024"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-09-08","last_updated":"2026-09-08","output_modalities":"image","vendor":"openai","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"gpt-image-2.5-sunburst","model_name":"GPT Image 2.5 Sunburst","developer_id":12,"desc":"GPT Image 2.5 Sunburst is OpenAI's latest image model, capable of generating and editing images from text and image inputs. It is suitable for workflows that require extremely high editing precision. The model supports quality settings: low, medium, high, xhigh, max, and auto.","pricing":{"cache_read":1.25,"input":5,"output":30},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":1.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_image_tokens","unit":"million_tokens","cost_usd":8,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_image_tokens","unit":"million_tokens","cost_usd":30,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"generate","unit":"image","cost_usd":0.211,"source":"img_price_config","variant":{"quality":"auto","size":"1024x1024"}},{"billable":"generate","unit":"image","cost_usd":0.165,"source":"img_price_config","variant":{"quality":"auto","size":"1024x1536"}},{"billable":"generate","unit":"image","cost_usd":0.165,"source":"img_price_config","variant":{"quality":"auto","size":"1536x1024"}},{"billable":"generate","unit":"image","cost_usd":0.211,"source":"img_price_config","variant":{"quality":"high","size":"1024x1024"}},{"billable":"generate","unit":"image","cost_usd":0.165,"source":"img_price_config","variant":{"quality":"high","size":"1024x1536"}},{"billable":"generate","unit":"image","cost_usd":0.165,"source":"img_price_config","variant":{"quality":"high","size":"1536x1024"}},{"billable":"generate","unit":"image","cost_usd":0.006,"source":"img_price_config","variant":{"quality":"low","size":"1024x1024"}},{"billable":"generate","unit":"image","cost_usd":0.005,"source":"img_price_config","variant":{"quality":"low","size":"1024x1536"}},{"billable":"generate","unit":"image","cost_usd":0.005,"source":"img_price_config","variant":{"quality":"low","size":"1536x1024"}},{"billable":"generate","unit":"image","cost_usd":0.053,"source":"img_price_config","variant":{"quality":"medium","size":"1024x1024"}},{"billable":"generate","unit":"image","cost_usd":0.041,"source":"img_price_config","variant":{"quality":"medium","size":"1024x1536"}},{"billable":"generate","unit":"image","cost_usd":0.041,"source":"img_price_config","variant":{"quality":"medium","size":"1536x1024"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-09-08","last_updated":"2026-09-08","output_modalities":"image","vendor":"openai","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"mercury-2.5-preview","model_name":"Mercury 2.5 Preview","developer_id":43,"desc":"Mercury 2.5 is the latest diffusion-based large language model (dLLM) released by Inception. It is the fastest inference LLM; unlike the sequential token-by-token generation approach, Mercury 2.5 can generate and optimize multiple tokens in parallel, achieving a generation speed of 1,107 tokens per second on standard GPUs. Compared to Mercury 2, its intelligence has increased by more than 10 percentage points, and its quality rivals leading cost-optimized frontier models such as GPT-5.6 Luna (Low), Gemini 3.5 Flash-Lite, and Claude Haiku 4.5.","pricing":{"cache_read":0.02,"input":0.2,"output":0.75},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"thinking,tools","input_modalities":"text","endpoints":"","max_output":65536,"context_length":260000,"release_date":"2026-09-02","last_updated":"2026-09-02","output_modalities":"text","reasoning":true,"tool_call":true,"vendor":"inception","open_weights":false,"schema_checked":false,"promotion":{"name":"mercury-2.5-preview limited-time special offer","off_percent":80,"time_type":"daily","daily":{"ranges":["00:00-23:59"]}},"retire_stage":"active"},{"model_id":"hy4-preview","model_name":"Hy4 Preview","developer_id":24,"desc":"Hy4 Preview is Tencent Hunyuan’s large language model for agents, coding, office automation, and complex tool use.Hy4 preview has a total of 770B parameters and 49B active parameters, and is primarily optimized for agent, coding, and productivity scenarios. It strengthens understanding, planning, tool invocation, and sustained execution capabilities for complex tasks. Compared with the previous generation, Hy4 preview further improves multi-step agents, code development, and productivity tasks, offering better task decomposition, context continuity, instruction following, and long-horizon execution. In coding scenarios, it further enhances code understanding, generation, modification, and the handling of complex engineering tasks; in productivity scenarios, it focuses on improving document processing, information analysis, office automation, game development, webpage generation, and cross-tool collaboration. Hy4 preview is suitable for coding agents, complex tool invocation, and various agent workflows that require multi-step planning and sustained execution, providing more reliable task completion for complex real-world business scenarios.","pricing":{"cache_read":0.04225,"input":0.845,"output":2.535},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,web,long_context,thinking","input_modalities":"text","endpoints":"","max_output":64000,"context_length":1048576,"release_date":"2026-08-28","last_updated":"2026-08-28","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high"],"default":"high"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"tencent","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-glm-5.3","model_name":"Coding GLM 5.3","developer_id":5,"desc":"GLM-5.3 is Z.ai’s reasoning model for coding and agentic workflows, designed for complex software engineering, long-running agents, and vulnerability analysis. It uses the same base model as GLM-5.2, with scaled post-training improving coding, task execution, and token efficiency.\n\nThis model is a limited-time preview version of GLM-5.3, intended for testing and evaluation only. Service stability is not guaranteed, and we do not recommend using it in production environments. We’re waiting for the official commercial API release and will integrate it as soon as official support becomes available.","pricing":{"cache_read":0.015,"input":0.06,"output":0.22},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"chat_completions,claude_api","max_output":131072,"context_length":1048576,"release_date":"2026-08-14","last_updated":"2026-08-14","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"],"default":"max"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-glm-5.3-flash-free","model_name":"Coding GLM 5.3 Flash (free)","developer_id":5,"desc":"coding-glm-5.3-flash-free is the open and free version of coding-glm-5.3-flash. To ensure stable service performance, usage limits are in place: up to 5 requests per minute, 100 requests per day, and a daily token allowance of 1 million.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,video","endpoints":"","max_output":131072,"context_length":1000000,"release_date":"2026-08-26","last_updated":"2026-08-26","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"],"default":"max"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"zhipu","variant_of":"coding-glm-5.3-flash","variant_kind":"pricing-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-glm-5.3-flash","model_name":"Coding GLM 5.3 Flash","developer_id":5,"desc":"Coding GLM 5.3 Flash is a dedicated version of GLM 5.3 Flash built for AI coding and Coding Agent workflows. It is designed for code understanding, generation, editing, repository-level development, and automated software engineering tasks. With support for context windows of up to approximately 1 million tokens, it can handle large codebases and extended development sessions. The model also supports text, image, and video inputs, along with tool use, making it well suited for AI coding tools such as Claude Code, OpenCode, Cline, and other agentic development environments.","pricing":{"cache_read":0.007043,"input":0.02817,"output":0.098595},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,video","endpoints":"","max_output":131072,"context_length":1000000,"release_date":"2026-08-26","last_updated":"2026-08-26","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"],"default":"max"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"zhipu","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-glm-5.3-free","model_name":"Coding GLM 5.3 (free)","developer_id":5,"desc":"coding-glm-5.3-free is the open and free version of coding-glm-5.3. To ensure stable service performance, usage limits are in place: up to 5 requests per minute, 100 requests per day, and a daily token allowance of 1 million.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":131072,"context_length":1048576,"release_date":"2026-08-14","last_updated":"2026-08-14","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"],"default":"max"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","variant_of":"coding-glm-5.3","variant_kind":"pricing-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"muse-spark-1.3","model_name":"Muse Spark 1.3","developer_id":34,"desc":"Muse Spark 1.3 is Meta’s multimodal reasoning model, designed for long-running agentic, multi-agent, and complex coding workflows. It can maintain context and task constraints across extended workflows, reconcile conflicting information, and request clarification or confirmation when needed. Compared with Muse Spark 1.2, Muse Spark 1.3 improves efficiency across long-horizon agentic and coding tasks, with fewer unnecessary turns, tool calls, and tokens, while producing more concise outputs.\n","pricing":{"cache_read":0.165,"input":1.375,"output":4.675},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools","input_modalities":"text,image,video,audio,pdf","endpoints":"","max_output":1000000,"context_length":1048576,"release_date":"2026-09-03","last_updated":"2026-09-03","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"],"default":"medium"}],"interleaved":{"anthropic.messages":true,"openai.responses":true},"vendor":"meta","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3.8-flash","model_name":"Qwen3.8 Flash","developer_id":13,"desc":"Qwen3.8 Flash is Alibaba Cloud Qwen’s flagship native vision-language model for coding, office tasks, long-context reasoning, and agent workflows. It supports a 1M-token context, 128K output, web access, and tool calling. Compared with Qwen3.7-Plus, Qwen3.8-Flash significantly reduces training and inference costs—the training overhead is only about one-ninth of the former—while offering stronger capabilities on coding and office tasks.","pricing":{"cache_read":0.014075,"cache_write":0.175937,"input":0.1126,"output":0.380025},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.1759375,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.014075,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.380025,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.1126,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.000548,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,web,long_context,thinking","input_modalities":"text,image,video","endpoints":"","max_output":131072,"context_length":1000000,"release_date":"2026-08-26","last_updated":"2026-08-26","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"],"default":"xhigh"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"alibaba","schema_checked":false,"retire_stage":"active"},{"model_id":"xiaomi-mimo-v2.6-flash-free","model_name":"Xiaomi Mimo V2.6 Flash (free)","developer_id":31,"desc":"xiaomi-mimo-v2.6-flash-free is the open free version of xiaomi-mimo-v2.6-flash.  To maintain reliable service, each account is limited to 5 requests per minute, 100 requests per day, and 1 million tokens per day.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image,video,audio","endpoints":"","max_output":131072,"context_length":1048576,"release_date":"2026-09-22","last_updated":"2026-09-22","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"xiaomi","variant_of":"mimo-v2.6-flash","variant_kind":"pricing-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"mai-image-2.6","model_name":"Mai Image 2.6","developer_id":3,"desc":"MAI-Image-2.6 is Microsoft's latest image-generation and editing model. It can generate images from text prompts and supports image-guided editing in multiple aspect ratios.","pricing":{"input":5,"output":5},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_image_tokens","unit":"million_tokens","cost_usd":8,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_image_tokens","unit":"million_tokens","cost_usd":38,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":4096,"context_length":32000,"release_date":"2026-09-05","last_updated":"2026-09-05","output_modalities":"image","vendor":"microsoft","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"mai-image-2.6-flash","model_name":"Mai Image 2.6 Flash","developer_id":3,"desc":"MAI-Image-2.6 Flash is Microsoft’s low-latency version of the latest image model MAI-Image-2.6. It supports image generation in multiple aspect ratios and image-guided editing.","pricing":{"input":1.75,"output":1.75},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_image_tokens","unit":"million_tokens","cost_usd":2.50005,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_image_tokens","unit":"million_tokens","cost_usd":18.99975,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":4096,"context_length":32000,"release_date":"2026-09-05","last_updated":"2026-09-05","output_modalities":"image","vendor":"microsoft","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"gemini-3.7-flash","model_name":"Gemini 3.7 Flash","developer_id":8,"desc":"(This model has been officially taken offline; requests to gemini-3.5-flash will now be automatically routed to gemini-3.8-flash.)Gemini 3.7 Flash is Google’s natively multimodal reasoning model for coding, agents, web development, and knowledge work. It supports a 1M-token context window and adjustable thinking levels. Compared with Gemini 3.6 Flash, it improves coding, tool use, multi-step planning, and instruction following.","pricing":{"cache_read":0.075,"input":0.75,"output":3.75},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":1,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.075,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_audio_tokens","unit":"million_tokens","cost_usd":0.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_video_tokens","unit":"million_tokens","cost_usd":0.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.014,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs,web,long_context","input_modalities":"text,image,video,audio,pdf","endpoints":"chat_completions,gemini_api,claude_api","max_output":65536,"context_length":1048576,"release_date":"2026-08-13","last_updated":"2026-08-13","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"],"default":"medium"}],"vendor":"google","variant_of":"gemini-3.8-flash","variant_kind":"deprecated-alias","open_weights":false,"schema_checked":false,"retire_stage":"deprecated","deprecated_at":"2026-10-12T10:34:28Z"},{"model_id":"agnes-3.0-flash","model_name":"Agnes 3.0 Flash","developer_id":36,"desc":"Agnes 3.0 Flash is designed for real-world agent tasks and development workflows, covering the full execution chain from task understanding and planning to tool invocation and final delivery. The model focuses on improving stability, instruction-following, factual grounding, and output completeness in complex tasks, helping developers build more reliable agent applications.","pricing":{"input":0.03,"output":0.15},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking","input_modalities":"text,image","endpoints":"chat_completions,responses","max_output":65500,"context_length":512000,"release_date":"2026-09-09","last_updated":"2026-09-09","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"vendor":"agnes","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"minimax-h3-max","model_name":"MiniMax H3 Max","developer_id":18,"desc":"MiniMax H3 (minimax-h3) is a general-purpose omni-modal generation model developed by the Chinese AI company MiniMax. It can jointly understand text, images, video, and audio while generating videos of up to 15 seconds in 2K resolution with native stereo sound. It is designed for advertising, branding, e-commerce, product design, UI/UX, and gaming. Compared with Hailuo 01 and Hailuo 02, H3 evolves from specialized video generation into a unified model for multimodal creation, reference-based editing, text rendering, and motion transfer.","pricing":{"input":2,"output":2},"pricing_source":"billing_config","pricing_lines":[{"billable":"image_input","unit":"image","cost_usd":0.0704,"source":"billing_config"},{"billable":"input_video_seconds","unit":"second","cost_usd":0.15028,"source":"billing_config","variant":{"match":{"quality":"768P"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.05732,"source":"billing_config","variant":{"match":{"quality":"480P"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.15028,"source":"billing_config","variant":{"fallback":true}},{"billable":"video_generation","unit":"second","cost_usd":0.0704,"source":"billing_config","variant":{"match":{"quality":"768P"}}},{"billable":"video_generation","unit":"second","cost_usd":0.05113,"source":"billing_config","variant":{"match":{"quality":"480P"}}},{"billable":"video_generation","unit":"second","cost_usd":0.0704,"source":"billing_config","variant":{"fallback":true}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-09-02","last_updated":"2026-09-02","output_modalities":"video","vendor":"minimax","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"intern-s2-free","model_name":"Intern S2 (free)","developer_id":47,"desc":"Intern-S2-Preview is InternLM’s 35B scientific multimodal foundation model, designed for professional scientific reasoning, research agents, multimodal understanding, and complex scientific workflows. It scales the difficulty, diversity, and coverage of scientific tasks across the full training pipeline, while strengthening scientific agent capabilities, time-series modeling, molecular and material structure understanding, and efficient reasoning. Compared with the trillion-parameter Intern-S1-Pro, Intern-S2-Preview achieves comparable performance on multiple core scientific tasks with only 35B parameters, while retaining strong general reasoning and multimodal capabilities.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":262144,"release_date":"2026-05-14","last_updated":"2026-05-14","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"glm-5.2","model_name":"GLM 5.2","developer_id":5,"desc":"GLM-5.2 is Z.ai’s flagship model for the era of long-horizon tasks. With a truly usable 1M-token context window, it can handle project-level engineering context, execute long-running tasks more reliably, follow engineering standards more consistently, and complete the full development workflow from requirements to multi-platform deployment in a single task.","pricing":{"cache_read":0.2817,"input":1.1268,"output":3.9438},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"chat_completions,claude_api","max_output":131072,"context_length":1000000,"release_date":"2026-06-16","last_updated":"2026-06-16","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high","max"],"default":"max"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"agents-a1-free","model_name":"Agents A1 (free)","developer_id":47,"desc":"Agents-A1 is a 35B Mixture-of-Experts (MoE) agentic model developed by InternScience for complex, long-horizon tasks across search, engineering, scientific research, instruction following, and tool use. The model is trained to scale both long-horizon agent trajectories and heterogeneous agent capabilities through a multi-stage training framework that combines full-domain supervised fine-tuning, domain-specialized teacher models, and multi-teacher on-policy distillation. Agents-A1 supports both text and image inputs and is designed for general-purpose agent workflows that require multi-step reasoning, planning, tool interaction, and sustained task execution.\n","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":262144,"release_date":"2026-06-26","last_updated":"2026-06-26","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-v4-flash-0731","model_name":"DeepSeek V4 Flash 0731","developer_id":7,"desc":"DeepSeek-V4-Flash-0731(deepseek-v4-flash-0731) is an open-source MoE large language model developed by the Chinese AI company DeepSeek, with support for a million-token context window. It is designed for coding, complex reasoning, tool use, agentic workflows, and long-document processing. Its advantages include strong performance with fewer active parameters and improved efficiency through DSpark speculative decoding. Compared with DeepSeek V4-Flash Preview, it offers significantly stronger coding and agent capabilities, while outperforming DeepSeek V4-Pro Preview on several benchmarks with fewer active parameters.","pricing":{"cache_read":0.0284,"input":0.142,"output":0.284},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0284,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.284,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.142,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.00056,"source":"billing_config"}],"has_zdr_provider":true,"types":"llm","features":"tools,function_calling,structured_outputs,thinking","input_modalities":"text","endpoints":"chat_completions,claude_api","max_output":384000,"context_length":1000000,"release_date":"2026-07-31","last_updated":"2026-07-31","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"],"default":"high"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"deepseek","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-v4-flash-vision-exp","model_name":"DeepSeek V4 Flash Vision Exp","developer_id":7,"desc":"DeepSeek’s officially released new multimodal visual-understanding model, DeepSeek‑V4‑Flash‑Vision‑Exp, is experimental in nature and supports multimodal inputs. In pure-text capabilities (agents, reasoning, world knowledge, etc.), DeepSeek‑V4‑Flash‑Vision‑Exp is on par with the official DeepSeek‑V4‑Flash release.(The model name deepseek-v4-flash-vision-exp remains callable, but the official corresponding model has been taken offline; requests will be served by the DeepSeek-V4.1-Flash model and billed at Flash pricing.)","pricing":{"cache_read":0.0031,"input":0.155,"output":0.62},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0031,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.006196,"source":"billing_config","tier":{"name":"peak","min_tokens":0,"max_tokens":-1,"time_condition":{"timezone":"UTC","ranges":["01:00-04:00","06:00-10:00"]}}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.62,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.2392,"source":"billing_config","tier":{"name":"peak","min_tokens":0,"max_tokens":-1,"time_condition":{"timezone":"UTC","ranges":["01:00-04:00","06:00-10:00"]}}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.155,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.3098,"source":"billing_config","tier":{"name":"peak","min_tokens":0,"max_tokens":-1,"time_condition":{"timezone":"UTC","ranges":["01:00-04:00","06:00-10:00"]}}}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,thinking","input_modalities":"text,image","endpoints":"chat_completions,claude_api","max_output":393216,"context_length":1000000,"release_date":"2026-07-31","last_updated":"2026-07-31","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high","max"],"default":"high"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"deepseek","variant_of":"deepseek-v4.1-flash-1017","variant_kind":"deprecated-alias","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-v4-pro-0813","model_name":"DeepSeek V4 Pro 0813","developer_id":7,"desc":"DeepSeek V4 Pro 0813 is DeepSeek’s high-performance general-purpose reasoning and agent model, designed for complex reasoning, coding, long-document analysis, and agentic workflows. It supports thinking and non-thinking modes, a 1M-token context window, up to 384K output, tool calling, and the Responses API. Compared with V4 Flash 0731, Pro prioritizes capability on complex tasks, while Flash focuses on speed, cost efficiency, and high concurrency.","pricing":{"cache_read":0.023058,"input":0.6918,"output":2.0754},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.023057694,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.046475352,"source":"billing_config","tier":{"name":"peak","min_tokens":0,"max_tokens":-1,"time_condition":{"timezone":"UTC","ranges":["01:00-04:00","06:00-10:00"]}}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.0754,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":4.1832,"source":"billing_config","tier":{"name":"peak","min_tokens":0,"max_tokens":-1,"time_condition":{"timezone":"UTC","ranges":["01:00-04:00","06:00-10:00"]}}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.6918,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.3944,"source":"billing_config","tier":{"name":"peak","min_tokens":0,"max_tokens":-1,"time_condition":{"timezone":"UTC","ranges":["01:00-04:00","06:00-10:00"]}}}],"has_zdr_provider":true,"types":"llm","features":"tools,function_calling,structured_outputs,thinking","input_modalities":"text","endpoints":"","max_output":384000,"context_length":1000000,"release_date":"2026-08-13","last_updated":"2026-08-13","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"],"default":"high"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"deepseek","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"dots-3-note-preview-free","model_name":"Dots 3 Note Preview (free)","developer_id":39,"desc":"Dots3-Note Preview is an open-weight mixture-of-experts model developed by Dots Studio, featuring 16B active parameters out of 280B total. As the lightest model in the Dots 3 family, it is designed for efficient performance while supporting an expansive context length of 512,000 tokens. This preview version provides an accessible way to experience the capabilities of the Dots 3 architecture.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"reasoning,tool_calling,long_context","input_modalities":"text,image,video,audio","endpoints":"chat_completions","max_output":0,"context_length":524288,"output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"dots-studio","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"grok-4.6","model_name":"Grok 4.6","developer_id":9,"desc":"Grok 4.6 is xAI’s (SpaceXAI) flagship multimodal reasoning model for coding, long-running agents, knowledge work, and interactive application development. It supports image understanding, a 500K context window, tool calling, and structured outputs. Compared with Grok 4.5, it offers stronger multi-step execution, self-verification, coding, and visual project generation. ","pricing":{"cache_read":0.5,"input":2,"output":6,"tiers":[{"cache_read":1,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":1,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":6,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":12,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":4,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs,long_context","input_modalities":"text,image","endpoints":"","max_output":500000,"context_length":500000,"release_date":"2026-08","last_updated":"2026-08","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"],"default":"medium"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"xai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"wan3.0-video","model_name":"Wan3.0 Video","developer_id":13,"desc":"Wan 3.0 (Tongyi Wanxiang 3.0) is an integrated video generation and editing model launched by Alibaba’s Tongyi Lab. It is suitable for scenarios such as advertising, e-commerce, short films, character animation, video editing, and document-to-video. Its advantages include native support for videos up to 30 seconds long and the unified handling of reference content such as text, images, audio, video, documents, spreadsheets, presentations, and web pages, delivering more realistic visuals and audio, stable character consistency, and capabilities for referencing, editing, replication, and driving. Compared with Wan 2.7, which split text-to-video, image-to-video, reference generation, and editing across multiple models, Wan 3.0 integrates these capabilities into a single model, making the creative workflow more unified and flexible.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.169,"source":"img_price_config","variant":{"quality":"standard","size":"1080p"}},{"billable":"generate","unit":"second","cost_usd":0.04225,"source":"img_price_config","variant":{"quality":"standard","size":"480p"}},{"billable":"generate","unit":"second","cost_usd":0.0845,"source":"img_price_config","variant":{"quality":"standard","size":"720p"}},{"billable":"generate","unit":"second","cost_usd":0.169,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text,image,video,audio,document,link","endpoints":"","max_output":0,"context_length":0,"output_modalities":"video","vendor":"alibaba","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"wan3.0-video-prime","model_name":"Wan3.0 Video Prime","developer_id":13,"desc":"Wan3.0 Video Prime is Alibaba Cloud’s preview high-speed edition of its All-in-One video model, positioned for faster-turnaround ads, ecommerce, short films, and editing. Aligned with Wan3.0 Video’s capabilities, it supports text-to-video, image-to-video, reference-based generation, document/webpage-to-video, up to 30 seconds at 30fps, 1080P output, adaptive aspect ratios, and native audio. It unifies modes that Wan 2.7 handled through separate task-specific models.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.2535,"source":"img_price_config","variant":{"quality":"standard","size":"1080p"}},{"billable":"generate","unit":"second","cost_usd":0.06338,"source":"img_price_config","variant":{"quality":"standard","size":"480p"}},{"billable":"generate","unit":"second","cost_usd":0.1268,"source":"img_price_config","variant":{"quality":"standard","size":"720p"}},{"billable":"generate","unit":"second","cost_usd":0.2535,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text,image,video,audio,document,link","endpoints":"","max_output":0,"context_length":0,"output_modalities":"video","vendor":"alibaba","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"mai-thinking-1","model_name":"Mai Thinking 1","developer_id":3,"desc":"MAI-Thinking-1 is Microsoft’s first inference model in the MAI series, built for enterprise-scale workloads. With excellent reasoning, mathematical, and general intelligence capabilities, combined with superior cost-effectiveness, it makes high-throughput, 24/7 AI workloads economically viable.","pricing":{"input":2,"output":8},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,structured_outputs","input_modalities":"text","endpoints":"chat_completions","max_output":64000,"context_length":256000,"release_date":"2026-08-12","last_updated":"2026-08-12","output_modalities":"text","reasoning":true,"vendor":"microsoft","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-xiaomi-mimo-v2.6-flash","model_name":"Coding Xiaomi Mimo V2.6 Flash","developer_id":31,"desc":"Only supports OpenAI-compatible formats.","pricing":{"cache_read":0.0016,"input":0.08,"output":0.16},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0016,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.16,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.08,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":256000}},{"billable":"web_search_requests","unit":"request","cost_usd":0.005,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image,video,audio","endpoints":"","max_output":131072,"context_length":1048576,"release_date":"2026-09-22","last_updated":"2026-09-22","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"xiaomi","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-v4-flash-0731-fast","model_name":"DeepSeek V4 Flash 0731 Fast","developer_id":7,"desc":"DeepSeek V4 Flash 0731 Fast is a high-speed deployment of DeepSeek’s agentic model provided by Wafer, designed for coding, tool use, and high-volume agent workloads. It preserves the capabilities of V4 Flash 0731 while delivering much faster inference. Compared with V4 Pro, it prioritizes latency and execution efficiency.","pricing":{"cache_read":0.07,"input":0.28,"output":1.4},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,thinking","input_modalities":"text","endpoints":"chat_completions,claude_api","max_output":384000,"context_length":1000000,"release_date":"2026-07-31","last_updated":"2026-07-31","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"],"default":"high"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"deepseek","variant_of":"deepseek-v4-flash-0731","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.6-sol-disc","model_name":"GPT 5.6 Sol Disc","developer_id":12,"desc":"GPT-5.6 Sol (limited-time 50% off) is OpenAI’s frontier reasoning model for complex coding, professional knowledge work, deep research, and long-running agents. It supports a roughly 1.05M-token context window, image understanding, and extensive tool use. Compared with Terra and Luna, Sol prioritizes capability and reliability on demanding tasks.","pricing":{"cache_read":0.4,"cache_write":5,"input":4,"output":20,"tiers":[{"cache_read":0.8,"cache_write":10,"input":8,"output":30,"tier":{"size":272000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.4,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.8,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":20,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":30,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":4,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":8,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,thinking,structured_outputs","input_modalities":"text,image","endpoints":"chat_completions,responses","max_output":128000,"context_length":1050000,"release_date":"2026-08-18","last_updated":"2026-08-18","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"],"default":"medium"}],"vendor":"openai","open_weights":false,"schema_checked":false,"promotion":{"name":"gpt-5.6-sol-discount limited-time special offer","off_percent":50,"time_type":"daily","daily":{"ranges":["00:00-23:59"]}},"retire_stage":"active"},{"model_id":"doubao-seedance-2-5-260628","model_name":"Doubao Seedance 2.5 260628","developer_id":4,"desc":"Seedance 2.5 is ByteDance Seed’s next-generation unified multimodal audio-video generation model, designed for filmmaking, advertising, education, simulation, and long-form content creation. It generates up to 30 seconds of synchronized audio and video in one pass and supports multi-round extensions. Compared with Seedance 2.0, it offers stronger storytelling, smoother transitions, richer reference support, improved realism, and more precise editing.","pricing":{"input":2,"output":0},"pricing_source":"billing_config","pricing_lines":[{"billable":"video_generation","unit":"token","cost_usd":7.7,"source":"billing_config","variant":{"match":{"ability":"video_reference","size":"1080p"}}},{"billable":"video_generation","unit":"token","cost_usd":12.87,"source":"billing_config","variant":{"match":{"ability":"generate","size":"1080p"}}},{"billable":"video_generation","unit":"token","cost_usd":7.04,"source":"billing_config","variant":{"match":{"ability":"video_reference"}}},{"billable":"video_generation","unit":"token","cost_usd":11.77,"source":"billing_config","variant":{"fallback":true}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text,image,video,audio","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-06-28","last_updated":"2026-06-28","output_modalities":"video","vendor":"bytedance","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"gpt-5.6-luna","model_name":"GPT 5.6 Luna","developer_id":12,"desc":"GPT-5.6 Luna is designed for cost-sensitive, high-volume workloads. It roughly corresponds to the nano model tier used in earlier GPT-5 families.","pricing":{"cache_read":0.02,"cache_write":0.25,"input":0.2,"output":1.2,"tiers":[{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8,"tier":{"size":272000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.02,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.04,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.8,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.4,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,thinking,structured_outputs","input_modalities":"text,image","endpoints":"chat_completions,responses","max_output":128000,"context_length":1050000,"release_date":"2026-07-09","last_updated":"2026-07-09","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"],"default":"medium"}],"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.6-sol","model_name":"GPT 5.6 Sol","developer_id":12,"desc":"GPT‑5.6 Sol sets a new standard for both intelligence and efficiency, achieving state-of-the-art results across coding, knowledge work, cybersecurity, and science while outperforming previous and competing frontier models with fewer tokens and at lower estimated cost.","pricing":{"cache_read":0.4,"cache_write":5,"input":4,"output":20,"tiers":[{"cache_read":0.8,"cache_write":10,"input":8,"output":30,"tier":{"size":272000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.4,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.8,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":20,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":30,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":4,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":8,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,thinking,structured_outputs","input_modalities":"text,image","endpoints":"chat_completions,responses","max_output":128000,"context_length":1050000,"release_date":"2026-07-09","last_updated":"2026-07-09","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"],"default":"medium"}],"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.6-terra","model_name":"GPT 5.6 Terra","developer_id":12,"desc":"GPT-5.6 Terra is designed for workloads that balance intelligence and cost. It roughly corresponds to the mini model tier used in earlier GPT-5 families.","pricing":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":12,"tiers":[{"cache_read":0.4,"cache_write":5,"input":4,"output":18,"tier":{"size":272000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.4,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":12,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":18,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":4,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,thinking,structured_outputs","input_modalities":"text,image","endpoints":"chat_completions,responses","max_output":128000,"context_length":1050000,"release_date":"2026-07-09","last_updated":"2026-07-09","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"],"default":"medium"}],"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3.8-max","model_name":"Qwen3.8 Max","developer_id":13,"desc":"Qwen3.8-Max is Alibaba Cloud Tongyi Qianwen's next-generation flagship large language model, featuring a mixture-of-experts (MoE) architecture with 2.4 trillion parameters. It achieves another breakthrough in encoding depth, enabling it to handle more complex engineering-grade projects and long-term autonomous development; collaborative agent capabilities are significantly enhanced, performing more confidently in multi-tool orchestration and end-to-end delivery; visual understanding is comprehensively improved, with more sensitive and accurate chart reasoning, document parsing, and multimodal perception. Continuing the 1-million-context window, reasoning modes, and a complete tool ecosystem, it continues to evolve at a higher level of intelligence.","pricing":{"cache_read":0.169,"cache_write":2.1125,"input":1.69,"output":5.07},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":2.1125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.169,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":5.07,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.69,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.000548,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,web,long_context,thinking","input_modalities":"text,image,video","endpoints":"","max_output":131072,"context_length":1000000,"release_date":"2026-08-03","last_updated":"2026-08-03","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"],"default":"xhigh"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"alibaba","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3.8-2.4t-a95b","model_name":"Qwen3.8 2.4t A95B","developer_id":13,"desc":"Qwen3.8-2.4T-A95B is Alibaba’s most powerful Qwen model to date. It is a 2.4‑trillion‑parameter sparse Mixture-of-Experts (MoE) model with approximately 95 billion active parameters. It is built for autonomous, long‑duration tasks: multi‑day code runs, reproducing research papers, and self‑improvement.","pricing":{"cache_read":0.5,"input":2,"output":6},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"tools,function_calling,structured_outputs,web,long_context,thinking","input_modalities":"text","endpoints":"","max_output":131072,"context_length":1000000,"release_date":"2026-08-12","last_updated":"2026-08-12","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"alibaba","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"grok-4.5","model_name":"Grok 4.5","developer_id":9,"desc":"Grok 4.5 was trained on datasets spanning knowledge in coding, science, engineering, and math. With both intelligent and efficient reasoning, Grok 4.5 excels at real engineering tasks and exceeds comparable leading models at these tasks.","pricing":{"cache_read":0.5,"input":2,"output":6,"tiers":[{"cache_read":1.1,"input":4.4,"output":13.2,"tier":{"size":200000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.55,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":1.1,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":6.6,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":13.2,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2.2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":4.4,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs,long_context","input_modalities":"text,image","endpoints":"","max_output":500000,"context_length":500000,"release_date":"2026-07","last_updated":"2026-07","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"],"default":"medium"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"xai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"lfm-2.5-2.6b-free","model_name":"Lfm 2.5 2.6b (free)","developer_id":37,"desc":"LFM-2.5-2.6B is a compact reasoning model developed by Liquid, featuring a generous 128,000 token context length. It is highly suited for agent workflows, data extraction, retrieval-augmented generation (RAG), and long-context processing. However, the developer advises against using this model for agentic coding tasks.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"reasoning,long_context","input_modalities":"text","endpoints":"chat_completions","max_output":0,"context_length":131072,"release_date":"2026-08-12","last_updated":"2026-08-12","output_modalities":"text","reasoning":true,"vendor":"liquid","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"minimax-h3","model_name":"MiniMax H3","developer_id":18,"desc":"MiniMax H3 (minimax-h3) is a general-purpose omni-modal generation model developed by the Chinese AI company MiniMax. It can jointly understand text, images, video, and audio while generating videos of up to 15 seconds in 2K resolution with native stereo sound. It is designed for advertising, branding, e-commerce, product design, UI/UX, and gaming. Compared with Hailuo 01 and Hailuo 02, H3 evolves from specialized video generation into a unified model for multimodal creation, reference-based editing, text rendering, and motion transfer.","pricing":{"input":2,"output":2},"pricing_source":"billing_config","pricing_lines":[{"billable":"image_input","unit":"image","cost_usd":0.0282,"source":"billing_config"},{"billable":"input_video_seconds","unit":"second","cost_usd":0.12397,"source":"billing_config","variant":{"match":{"quality":"2K"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.07744,"source":"billing_config","variant":{"match":{"quality":"768P"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.12397,"source":"billing_config","variant":{"fallback":true}},{"billable":"video_generation","unit":"second","cost_usd":0.12397,"source":"billing_config","variant":{"match":{"quality":"2K"}}},{"billable":"video_generation","unit":"second","cost_usd":0.07744,"source":"billing_config","variant":{"match":{"quality":"768P"}}},{"billable":"video_generation","unit":"second","cost_usd":0.12397,"source":"billing_config","variant":{"fallback":true}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text,image,video,audio","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-07-30","last_updated":"2026-07-30","output_modalities":"video","vendor":"minimax","open_weights":true,"schema_checked":true,"retire_stage":"active"},{"model_id":"agnes-2.5-flash","model_name":"Agnes 2.5 Flash","developer_id":36,"desc":"Agnes 2.5 Flash is Agnes AI’s fast and efficient language model, an upgraded, fully available model based on Agnes 2.0 Flash. It continues to use an OpenAI-compatible Chat Completions interface and has been optimized for coding tasks, agent workflows, tool calls, multi-turn dialogue, reasoning, and image understanding.","pricing":{"input":0.03,"output":0.15},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking","input_modalities":"text,image","endpoints":"chat_completions,responses","max_output":65500,"context_length":512000,"release_date":"2026-07","last_updated":"2026-07","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"vendor":"agnes","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"agnes-2.5-pro","model_name":"Agnes 2.5 Pro","developer_id":36,"desc":"Agnes 2.5 Pro is Agnes AI’s paid inference model and the commercially stable version of the Agnes 2.5 Pro Alpha ranking model, suitable for advanced coding, scientific reasoning, long-context analysis, agent workflows, and multimodal understanding. The model is accessed via an OpenAI-compatible Chat Completions API.","pricing":{"cache_read":0.00378,"input":0.45,"output":0.9},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking","input_modalities":"text,image","endpoints":"chat_completions,responses","max_output":65536,"context_length":1000000,"release_date":"2026-08-01","last_updated":"2026-08-01","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"}],"vendor":"agnes","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"agnes-2.5-pro-alpha","model_name":"Agnes 2.5 Pro Alpha","developer_id":36,"desc":"Agnes 2.5 Pro Alpha is Agnes AI’s paid inference model, suitable for advanced coding, scientific reasoning, long-context analysis, agent workflows, and multimodal understanding. The model is accessed via an OpenAI-compatible Chat Completions API.","pricing":{"cache_read":0.00378,"input":0.45,"output":0.9},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking","input_modalities":"text,image","endpoints":"chat_completions,responses","max_output":65536,"context_length":1000000,"release_date":"2026-07-24","last_updated":"2026-07-24","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"}],"vendor":"agnes","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"agnes-image-2.1-flash","model_name":"Agnes Image 2.1 Flash","developer_id":36,"desc":"Agnes Image 2.1 Flash is Agnes AI’s high-performance image generation and image editing model, supporting text-to-image, image-to-image, and multi-image composition. It is suitable for creative design, marketing visuals, e-commerce product images, and social content production.","pricing":{"input":2,"output":2},"pricing_source":"billing_config","pricing_lines":[{"billable":"image_generation","unit":"image","cost_usd":0.01,"source":"billing_config","variant":{"match":{"size":"1K"}}},{"billable":"image_generation","unit":"image","cost_usd":0.01,"source":"billing_config","variant":{"match":{"size":"1024x1024"}}},{"billable":"image_generation","unit":"image","cost_usd":0.01,"source":"billing_config","variant":{"match":{"size":"864x1152"}}},{"billable":"image_generation","unit":"image","cost_usd":0.01,"source":"billing_config","variant":{"match":{"size":"1152x864"}}},{"billable":"image_generation","unit":"image","cost_usd":0.01,"source":"billing_config","variant":{"match":{"size":"1312x736"}}},{"billable":"image_generation","unit":"image","cost_usd":0.01,"source":"billing_config","variant":{"match":{"size":"736x1312"}}},{"billable":"image_generation","unit":"image","cost_usd":0.01,"source":"billing_config","variant":{"match":{"size":"832x1248"}}},{"billable":"image_generation","unit":"image","cost_usd":0.01,"source":"billing_config","variant":{"match":{"size":"1248x832"}}},{"billable":"image_generation","unit":"image","cost_usd":0.01,"source":"billing_config","variant":{"match":{"size":"1568x672"}}},{"billable":"image_generation","unit":"image","cost_usd":0.01,"source":"billing_config","variant":{"match":{"size":"1024x768"}}},{"billable":"image_generation","unit":"image","cost_usd":0.018,"source":"billing_config","variant":{"match":{"size":"2K"}}},{"billable":"image_generation","unit":"image","cost_usd":0.018,"source":"billing_config","variant":{"match":{"size":"2048x2048"}}},{"billable":"image_generation","unit":"image","cost_usd":0.018,"source":"billing_config","variant":{"match":{"size":"1728x2304"}}},{"billable":"image_generation","unit":"image","cost_usd":0.018,"source":"billing_config","variant":{"match":{"size":"2304x1728"}}},{"billable":"image_generation","unit":"image","cost_usd":0.018,"source":"billing_config","variant":{"match":{"size":"2624x1472"}}},{"billable":"image_generation","unit":"image","cost_usd":0.018,"source":"billing_config","variant":{"match":{"size":"1472x2624"}}},{"billable":"image_generation","unit":"image","cost_usd":0.018,"source":"billing_config","variant":{"match":{"size":"1664x2496"}}},{"billable":"image_generation","unit":"image","cost_usd":0.018,"source":"billing_config","variant":{"match":{"size":"2496x1664"}}},{"billable":"image_generation","unit":"image","cost_usd":0.018,"source":"billing_config","variant":{"match":{"size":"3136x1344"}}},{"billable":"image_generation","unit":"image","cost_usd":0.021,"source":"billing_config","variant":{"match":{"size":"3K"}}},{"billable":"image_generation","unit":"image","cost_usd":0.021,"source":"billing_config","variant":{"match":{"size":"3072x3072"}}},{"billable":"image_generation","unit":"image","cost_usd":0.021,"source":"billing_config","variant":{"match":{"size":"2592x3456"}}},{"billable":"image_generation","unit":"image","cost_usd":0.021,"source":"billing_config","variant":{"match":{"size":"3456x2592"}}},{"billable":"image_generation","unit":"image","cost_usd":0.021,"source":"billing_config","variant":{"match":{"size":"3936x2208"}}},{"billable":"image_generation","unit":"image","cost_usd":0.021,"source":"billing_config","variant":{"match":{"size":"2208x3936"}}},{"billable":"image_generation","unit":"image","cost_usd":0.021,"source":"billing_config","variant":{"match":{"size":"2496x3744"}}},{"billable":"image_generation","unit":"image","cost_usd":0.021,"source":"billing_config","variant":{"match":{"size":"3744x2496"}}},{"billable":"image_generation","unit":"image","cost_usd":0.021,"source":"billing_config","variant":{"match":{"size":"4704x2016"}}},{"billable":"image_generation","unit":"image","cost_usd":0.024,"source":"billing_config","variant":{"match":{"size":"4K"}}},{"billable":"image_generation","unit":"image","cost_usd":0.024,"source":"billing_config","variant":{"match":{"size":"4096x4096"}}},{"billable":"image_generation","unit":"image","cost_usd":0.024,"source":"billing_config","variant":{"match":{"size":"3456x4608"}}},{"billable":"image_generation","unit":"image","cost_usd":0.024,"source":"billing_config","variant":{"match":{"size":"4608x3456"}}},{"billable":"image_generation","unit":"image","cost_usd":0.024,"source":"billing_config","variant":{"match":{"size":"5248x2944"}}},{"billable":"image_generation","unit":"image","cost_usd":0.024,"source":"billing_config","variant":{"match":{"size":"2944x5248"}}},{"billable":"image_generation","unit":"image","cost_usd":0.024,"source":"billing_config","variant":{"match":{"size":"3328x4992"}}},{"billable":"image_generation","unit":"image","cost_usd":0.024,"source":"billing_config","variant":{"match":{"size":"4992x3328"}}},{"billable":"image_generation","unit":"image","cost_usd":0.024,"source":"billing_config","variant":{"match":{"size":"6272x2688"}}},{"billable":"image_generation","unit":"image","cost_usd":0.01,"source":"billing_config","variant":{"fallback":true}},{"billable":"image_input","unit":"image","cost_usd":0.003,"source":"billing_config","variant":{"free_quantity":3}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"image","vendor":"agnes","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"claude-opus-5","model_name":"Claude Opus 5","developer_id":2,"desc":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.\n\nThe model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.","pricing":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":6.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":6.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,structured_outputs,long_context,web","input_modalities":"text,image,pdf","endpoints":"chat_completions,claude_api,responses","max_output":128000,"context_length":1000000,"release_date":"2026-07-24","last_updated":"2026-07-24","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"],"default":"high"}],"interleaved":{"anthropic.messages":true},"vendor":"anthropic","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-image-3.0","model_name":"Qwen Image 3.0","developer_id":13,"desc":"Qwen Image 3.0(qwen-image-3.0) is an image generation and editing model developed by Alibaba Cloud’s Qwen team. It supports text-to-image generation, reference-based creation, and image editing. It is well suited for social media, e-commerce, creative design, and everyday content production, offering a strong balance of image quality and speed. Compared with the Pro version, it is better suited for frequent and large-scale daily creation.","pricing":{"input":2,"output":0},"pricing_source":"billing_config","pricing_lines":[{"billable":"image_generation","unit":"image","cost_usd":0.02535,"source":"billing_config","variant":{"match":{"long_edge_px":{"lte":1024}}}},{"billable":"image_generation","unit":"image","cost_usd":0.02535,"source":"billing_config","variant":{"match":{"long_edge_px":{"gt":1024,"lte":2048}}}},{"billable":"image_generation","unit":"image","cost_usd":0.02535,"source":"billing_config","variant":{"fallback":true}},{"billable":"image_input","unit":"image","cost_usd":0.00286,"source":"billing_config"}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"image","vendor":"alibaba","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"qwen-image-3.0-pro","model_name":"Qwen Image 3.0 Pro","developer_id":13,"desc":"Qwen Image 3.0 Pro (qwen-image-3.0-pro) is Alibaba Cloud Qwen’s flagship image generation and editing model. It is designed for advertising, brand visuals, UI, presentations, product imagery, and professional design. Its strengths include complex layouts, accurate Chinese and English text rendering, realistic materials, and reference-based editing. Compared with the standard version, it delivers stronger detail, composition, and commercial-grade visual quality.","pricing":{"input":2,"output":0},"pricing_source":"billing_config","pricing_lines":[{"billable":"image_generation","unit":"image","cost_usd":0.03572,"source":"billing_config","variant":{"match":{"long_edge_px":{"lte":1024}}}},{"billable":"image_generation","unit":"image","cost_usd":0.07143,"source":"billing_config","variant":{"match":{"long_edge_px":{"gt":1024,"lte":2048}}}},{"billable":"image_generation","unit":"image","cost_usd":0.07143,"source":"billing_config","variant":{"fallback":true}},{"billable":"image_input","unit":"image","cost_usd":0.00286,"source":"billing_config"}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"image","vendor":"alibaba","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"gemini-3.6-flash","model_name":"Gemini 3.6 Flash","developer_id":8,"desc":"Gemini 3.6 Flash provides sustained frontier-level intelligence optimized for real-world tasks at a higher speed and lower cost. Designed for the agentic era, it excels at code generation, agentic execution, and spatial reasoning. This model is particularly effective for rapid agentic loops involving complex coding cycles and iterations.","pricing":{"cache_read":0.075,"input":0.75,"output":3.75},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":1,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.075,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_audio_tokens","unit":"million_tokens","cost_usd":0.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_video_tokens","unit":"million_tokens","cost_usd":0.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.014,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs,web,long_context","input_modalities":"text,image,video,audio,pdf","endpoints":"chat_completions,gemini_api,claude_api","max_output":65536,"context_length":1048576,"release_date":"2026-07-21","last_updated":"2026-07-21","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"],"default":"medium"}],"vendor":"google","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"nemotron-3.5-lightning-free","model_name":"Nemotron 3.5 Lightning (free)","developer_id":17,"desc":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, featuring 3 billion active parameters out of 30 billion total. It supports an extensive context window of up to 1,000,000 tokens. This model is designed to deliver efficient performance for high-throughput agentic workloads and specialized tasks.\nCompared with Nemotron 3 Super and Ultra, Lightning is smaller and optimized for fast, high-volume execution, while the larger models focus on complex planning and advanced reasoning.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"reasoning,tool_calling,long_context","input_modalities":"text","endpoints":"chat_completions","max_output":0,"context_length":1048576,"release_date":"2026-08-11","last_updated":"2026-08-11","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"vendor":"nvidia","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"kimi-k3","model_name":"Kimi K3","developer_id":15,"desc":"Kimi K3 is Kimi’s flagship model for long-horizon coding and end-to-end knowledge work, with a 1M-token context window and industry-leading intelligence.","pricing":{"cache_read":0.284,"input":2.84,"output":14.2},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"thinking,function_calling,structured_outputs","input_modalities":"text,image,video","endpoints":"","max_output":1048576,"context_length":1048576,"release_date":"2026-07-16","last_updated":"2026-07-16","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","high","max"],"default":"max"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"moonshot","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"muse-spark-1.2","model_name":"Muse Spark 1.2","developer_id":34,"desc":"Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context window.","pricing":{"input":1.375,"output":4.675},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools","input_modalities":"text,image,video,audio,pdf","endpoints":"","max_output":0,"context_length":1048576,"release_date":"2026-08-05","last_updated":"2026-08-05","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"],"default":"medium"}],"interleaved":{"anthropic.messages":true,"openai.responses":true},"vendor":"meta","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"claude-sonnet-5","model_name":"Claude Sonnet 5","developer_id":2,"desc":"Claude Sonnet 5 is the next generation of Anthropic's Sonnet model family. It is a drop-in upgrade for Claude Sonnet 4.6 with three behavior changes: adaptive thinking is on by default, manual extended thinking now returns a 400 error (it was deprecated on Claude Sonnet 4.6), and setting sampling parameters (temperature, top_p, top_k) to non-default values returns a 400 error","pricing":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":10},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":4,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,pdf","endpoints":"chat_completions,gemini_api,claude_api","max_output":128000,"context_length":1000000,"release_date":"2026-06-30","last_updated":"2026-06-30","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"],"default":"high"}],"interleaved":{"anthropic.messages":true},"vendor":"anthropic","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-audio-3.0-tts-flash","model_name":"Qwen Audio 3.0 Tts Flash","developer_id":13,"desc":"qwen-audio-3.0-tts-flash is a high-performance speech synthesis large model optimized for real-time interactive scenarios. Compared with the previous version, the model supports more low-resource languages and Chinese dialects, improves the authenticity of dialect pronunciation, and enhances free-style instruction following and fine-grained label control, enabling more flexible control of expression such as emotion, tone, character, speaking rate, and volume. At the same time, the model exhibits stronger robustness under complex acoustic conditions like noise and reverberation, improving sound quality, clarity, and overall expressiveness. The Flash version focuses on optimizing the real-time synthesis experience, keeping first-packet latency under 200 ms, making it suitable for low-latency interactive scenarios such as voice assistants, real-time dialogue, and intelligent customer service.","pricing_source":"model_ratio","pricing_lines":[{"billable":"input_characters","unit":"character","cost_usd":0.0000142,"source":"model_ratio"}],"has_zdr_provider":false,"types":"tts","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"audio","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-audio-3.0-tts-plus","model_name":"Qwen Audio 3.0 Tts Plus","developer_id":13,"desc":"qwen-audio-3.0-tts-plus is a high-performance speech synthesis large model designed for high-quality speech generation scenarios. Compared with the previous version, the model supports more low-resource languages and Chinese dialects, significantly improving the authenticity of dialect pronunciation, and enhancing free-style instruction following and fine-grained label control capabilities, allowing more accurate control of emotion, tone, character, speaking rate, volume, and synthesis style. Meanwhile, the model exhibits stronger robustness under complex acoustic conditions such as noise and reverberation, further improving sound quality, clarity, resolution, and overall expressiveness. The Plus version places greater emphasis on synthesis quality and detail, making it suitable for professional scenarios that require higher sound quality, naturalness, and expressiveness, such as content creation, audiobooks, film and TV dubbing, brand voice design, and high-quality voice services.","pricing_source":"model_ratio","pricing_lines":[{"billable":"input_characters","unit":"character","cost_usd":0.0000197,"source":"model_ratio"}],"has_zdr_provider":false,"types":"tts","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"audio","schema_checked":false,"retire_stage":"active"},{"model_id":"muse-spark-1.1","model_name":"Muse Spark 1.1","developer_id":34,"desc":"Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context window.","pricing":{"input":1.375,"output":4.675},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools","input_modalities":"text,image,video,audio,pdf","endpoints":"","max_output":0,"context_length":1048576,"release_date":"2026-04-08","last_updated":"2026-04-08","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"],"default":"medium"}],"interleaved":{"anthropic.messages":true,"openai.responses":true},"vendor":"meta","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-3.1-flash-lite-image","model_name":"Gemini 3.1 Flash Lite Image","developer_id":8,"desc":"Google's newest, most compact, and most cost-effective image generation and editing model, designed for large-scale use.","pricing":{"cache_read":0.025,"input":0.25,"output":1.5},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.025,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_image_tokens","unit":"million_tokens","cost_usd":0.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_image_tokens","unit":"million_tokens","cost_usd":30,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"image_generation,llm","features":"thinking","input_modalities":"text,image","endpoints":"","max_output":4096,"context_length":65536,"release_date":"2026-06-30","last_updated":"2026-06-30","output_modalities":"image,text","reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","high"],"default":"minimal"}],"interleaved":{"google.gemini":true},"vendor":"google","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"gemini-3.5-flash-lite","model_name":"Gemini 3.5 Flash Lite","developer_id":8,"desc":"Gemini 3.5 Flash-Lite is a low-latency, cost-effective multimodal model optimized for high-throughput, low-cost execution for subagent tasks and document parsing. The model supports text, image, video, audio, and PDF inputs, and is designed for high-volume agentic workflows, simple data extraction, and applications where latency and API cost are the primary constraints.","pricing":{"cache_read":0.03,"input":0.3,"output":2.499999},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":1,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.03,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.499999,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_audio_tokens","unit":"million_tokens","cost_usd":0.3,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_video_tokens","unit":"million_tokens","cost_usd":0.3,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.3,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.014,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs,web,long_context","input_modalities":"text,image,video,audio,pdf","endpoints":"chat_completions,gemini_api,claude_api","max_output":65536,"context_length":1048576,"release_date":"2026-07-21","last_updated":"2026-07-21","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"],"default":"medium"}],"vendor":"google","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"glm-5.2-fast-preview","model_name":"GLM 5.2 Fast Preview","developer_id":5,"desc":"GLM-5.2-Fast-Preview is the high-speed version of Zhipu AI’s flagship model GLM-5.2, supporting a 1M ultra-long context. The model’s capabilities are aligned with the GLM-5.2 standard version, offering logical reasoning, long-text understanding, and code generation. Through inference acceleration optimizations, output TPS can reach 1.5–2× that of the GLM-5.2 standard version, significantly improving output speed. It is suitable for scenarios sensitive to output speed, such as real-time dialogue, multi-turn Agent calls, and streaming code generation.","pricing":{"cache_read":0.5635,"input":2.254,"output":7.889},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"chat_completions,claude_api","max_output":131072,"context_length":1000000,"release_date":"2026-06-16","last_updated":"2026-06-16","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high","max"],"default":"max"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"claude-fable-5","model_name":"Claude Fable 5","developer_id":2,"desc":"Anthropic's most capable widely released model, for the most demanding reasoning and long-horizon agentic work（This model is extremely expensive and is not recommended for casual use.）","pricing":{"cache_read":1.1,"cache_write":13.75,"input":11,"output":55},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":22,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":13.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":13.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":1.1,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":55,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":11,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,pdf","endpoints":"chat_completions,claude_api","max_output":128000,"context_length":1000000,"release_date":"2026-06-09","last_updated":"2026-06-09","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"],"default":"medium"}],"interleaved":{"anthropic.messages":true},"vendor":"anthropic","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"jina-reranker-v3.5","model_name":"Jina Reranker V3.5","developer_id":22,"desc":"jina-reranker-v3.5 is a 0.6B-parameter multilingual listwise document reranker and a drop-in upgrade to jina-reranker-v3. It keeps the same last-but-not-late (LBNL) listwise interface — ranking a query against many candidates in one forward pass — while improving domain robustness, structured-data ranking, multilingual retrieval, and inference efficiency.","pricing":{"input":0.05,"output":0.05},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"rerank","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":131072,"vendor":"jina","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"hy3","model_name":"Hy3","developer_id":24,"desc":"The Hy3 official version is honed for real-world business scenarios, using a Mixture-of-Experts (MoE) architecture with 295B total parameters and 21B activated parameters. It natively supports a 256K context window and offers multiple thinking modes: no_think (ultra-fast response), think_low (quick thinking), and think_high (deep reasoning), balancing ultra-fast responses, complex reasoning, and invocation cost. Compared with the Preview version, Hy3—based on real business feedback from Tencent Yuanbao, WorkBuddy, ima, Marvis, and others—focuses on improving the Coding Agent, long-form understanding, multi-turn context continuity, search QA, and complex task execution, performing more stably in reducing hallucinations, improving task completion, and engineering usability. It is better suited to practical scenarios such as frontend tasks, cross-file code development, long-document analysis, office automation, and multi-step Agent workflows.","pricing":{"cache_read":0.03905,"input":0.1562,"output":0.6248},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.03905,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.6248,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.1562,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,web,long_context,thinking","input_modalities":"text","endpoints":"","max_output":128000,"context_length":256000,"release_date":"2026-07-06","last_updated":"2026-07-06","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["no_think","low","high"]}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"tencent","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"claude-opus-4-8","model_name":"Claude Opus 4.8","developer_id":2,"desc":"Claude Opus 4.8 is Anthropic’s newest and most powerful publicly available model. It is suitable for the most complex tasks. It is Anthropic’s strongest model for complex reasoning, long-horizon agent programming, and highly autonomous work.claude-opus-4-8 does not display thought content by default; you need to set the additional parameter \"display\": \"summarized\" to enable it","pricing":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":6.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":6.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,pdf","endpoints":"chat_completions,claude_api","max_output":128000,"context_length":1000000,"release_date":"2026-05-28","last_updated":"2026-05-28","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"],"default":"medium"}],"interleaved":{"anthropic.messages":true},"vendor":"anthropic","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seed-2-1-pro","model_name":"Doubao Seed 2.1 Pro","developer_id":4,"desc":"A new generation of large models moving toward production-grade intelligence, comprehensively upgrading coding, agent, and multimodal capabilities with stronger autonomous planning, long-horizon execution, and dynamic recovery abilities to handle real, complex enterprise tasks.","pricing":{"cache_read":0.1859,"input":0.9295,"output":4.6475},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.1859,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":4.6475,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.9295,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"llm","features":"thinking,web,tools,function_calling,structured_outputs","input_modalities":"text,image,video,document","endpoints":"","max_output":256000,"context_length":256000,"output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"],"default":"medium"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"bytedance","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seed-2-1-turbo","model_name":"Doubao Seed 2.1 Turbo","developer_id":4,"desc":"Balancing performance and cost, comprehensively upgrading coding, agent, and multimodal capabilities, with stronger autonomous planning, long-horizon execution, and dynamic recovery abilities to handle real, complex enterprise tasks.","pricing":{"cache_read":0.09295,"input":0.46475,"output":2.32375},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.09295,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.32375,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.46475,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"llm","features":"thinking,web,tools,function_calling,structured_outputs","input_modalities":"text,image,video,document","endpoints":"","max_output":256000,"context_length":256000,"output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"],"default":"medium"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"bytedance","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"mai-image-2.5-pro","model_name":"Mai Image 2.5 Pro","developer_id":3,"desc":"MAI-Image-2.5 is Microsoft's flagship AI image generation and editing model. With top-tier realism, precise text rendering, and powerful image editing capabilities, it debuted among the top three in AI image generation rankings. It is primarily targeted at commercial design, product photography, and professional creative work.","pricing":{"input":5,"output":5},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_image_tokens","unit":"million_tokens","cost_usd":8,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_image_tokens","unit":"million_tokens","cost_usd":29.375,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"image","vendor":"microsoft","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"grok-build-0.1","model_name":"Grok Build 0.1","developer_id":9,"desc":"Fast coding model trained specifically for agentic coding workflows.","pricing":{"cache_read":0.2,"input":1,"output":2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs,long_context","input_modalities":"text,image","endpoints":"","max_output":256000,"context_length":256000,"release_date":"2026-04-16","last_updated":"2026-04-16","output_modalities":"text","reasoning":true,"tool_call":true,"vendor":"xai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"mai-image-2.5","model_name":"Mai Image 2.5","developer_id":3,"desc":"MAI-Image-2.5 is Microsoft's flagship AI image generation and editing model. With top-tier realism, precise text rendering, and powerful image editing capabilities, it debuted among the top three in AI image generation rankings. It is primarily targeted at commercial design, product photography, and professional creative work.","pricing":{"input":5,"output":5},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_image_tokens","unit":"million_tokens","cost_usd":8,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_image_tokens","unit":"million_tokens","cost_usd":47,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"image","vendor":"microsoft","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"mai-image-2.5-flash","model_name":"Mai Image 2.5 Flash","developer_id":3,"desc":"MAI-Image-2.5 is Microsoft's flagship AI image generation and editing model. With top-tier realism, precise text rendering, and powerful image editing capabilities, it debuted among the top three in AI image generation rankings. It is primarily targeted at commercial design, product photography, and professional creative work.","pricing":{"input":1.75,"output":1.75},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_image_tokens","unit":"million_tokens","cost_usd":1.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_image_tokens","unit":"million_tokens","cost_usd":32.99975,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"image","vendor":"microsoft","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-3.5-flash","model_name":"Gemini 3.5 Flash","developer_id":8,"desc":"(This model has been officially taken offline; requests to gemini-3.5-flash will now be automatically routed to gemini-3.6-flash.)Gemini 3.5 Flash provides sustained frontier-level intelligence optimized for real-world tasks at a higher speed and lower cost. Designed for the agentic era, it excels at sub-agent deployment, multi-step workflows, and long-horizon tasks at scale. This model is particularly effective for rapid agentic loops involving complex coding cycles and iterations.","pricing":{"cache_read":0.075,"input":0.75,"output":3.75},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":1,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.075,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_audio_tokens","unit":"million_tokens","cost_usd":0.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_video_tokens","unit":"million_tokens","cost_usd":0.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.014,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs,web,deepsearch,long_context","input_modalities":"text,image,video,audio,pdf","endpoints":"chat_completions,gemini_api,claude_api","max_output":65536,"context_length":1048576,"release_date":"2026-05-19","last_updated":"2026-05-19","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"],"default":"medium"}],"vendor":"google","variant_of":"gemini-3.6-flash","variant_kind":"deprecated-alias","open_weights":false,"schema_checked":false,"retire_stage":"deprecated","deprecated_at":"2026-10-12T10:34:05Z"},{"model_id":"coding-kimi-k3","model_name":"Coding Kimi K3","developer_id":15,"desc":"","pricing":{"cache_read":0.066,"input":0.44,"output":1.61333},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,function_calling,structured_outputs","input_modalities":"text,image,video","endpoints":"","max_output":1048576,"context_length":1048576,"release_date":"2026-07-16","last_updated":"2026-07-16","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","high","max"],"default":"max"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"moonshot","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"happyhorse-1.1-i2v","model_name":"Happyhorse 1.1 I2v","developer_id":13,"desc":"HappyHorse-1.1-I2V supports image-to-video generation, further enhancing visual texture, dynamic performance, and cross-segment consistency. The model can more accurately understand input images and carry forward the creative intent, delivering significant improvements in character skin texture, ID consistency across segments, motion smoothness, text rendering stability, and audio–visual synchronization, producing higher-quality videos that are more realistic and natural, rich in detail, and more consistent.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.1691,"source":"img_price_config","variant":{"quality":"standard","size":"1080x1920"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"1088x832"}},{"billable":"generate","unit":"second","cost_usd":0.1691,"source":"img_price_config","variant":{"quality":"standard","size":"1248x1632"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"1280x720"}},{"billable":"generate","unit":"second","cost_usd":0.1691,"source":"img_price_config","variant":{"quality":"standard","size":"1440x1440"}},{"billable":"generate","unit":"second","cost_usd":0.1691,"source":"img_price_config","variant":{"quality":"standard","size":"1632x1248"}},{"billable":"generate","unit":"second","cost_usd":0.1691,"source":"img_price_config","variant":{"quality":"standard","size":"1920x1080"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"720x1280"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"832x1088"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"960x960"}},{"billable":"generate","unit":"second","cost_usd":0.1691,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-07-17","last_updated":"2026-07-17","output_modalities":"video","vendor":"alibaba","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"happyhorse-1.1-r2v","model_name":"Happyhorse 1.1 R2v","developer_id":13,"desc":"HappyHorse-1.1-R2V supports reference-based video generation, further improving the stable preservation of subject, scene style, and visual consistency. The model supports up to nine reference images as input, and can more accurately understand and carry forward creative intent, offering stronger controllability and expressiveness in characters, scenes, style, and camera/shot performance.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.1691,"source":"img_price_config","variant":{"quality":"standard","size":"1080x1920"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"1088x832"}},{"billable":"generate","unit":"second","cost_usd":0.1691,"source":"img_price_config","variant":{"quality":"standard","size":"1248x1632"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"1280x720"}},{"billable":"generate","unit":"second","cost_usd":0.1691,"source":"img_price_config","variant":{"quality":"standard","size":"1440x1440"}},{"billable":"generate","unit":"second","cost_usd":0.1691,"source":"img_price_config","variant":{"quality":"standard","size":"1632x1248"}},{"billable":"generate","unit":"second","cost_usd":0.1691,"source":"img_price_config","variant":{"quality":"standard","size":"1920x1080"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"720x1280"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"832x1088"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"960x960"}},{"billable":"generate","unit":"second","cost_usd":0.1691,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-07-17","last_updated":"2026-07-17","output_modalities":"video","vendor":"alibaba","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"happyhorse-1.1-t2v","model_name":"Happyhorse 1.1 T2v","developer_id":13,"desc":"HappyHorse-1.1-T2V supports text-to-video generation, further enhancing text semantic understanding, camera/shot orchestration, and dynamic generation performance. The model can more accurately realize creative intent, producing higher-quality videos with smoother, more natural movements, richer detail, and greater consistency in character actions, scene atmosphere, visual aesthetics, and physical motion.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.1691,"source":"img_price_config","variant":{"quality":"standard","size":"1080x1920"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"1088x832"}},{"billable":"generate","unit":"second","cost_usd":0.1691,"source":"img_price_config","variant":{"quality":"standard","size":"1248x1632"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"1280x720"}},{"billable":"generate","unit":"second","cost_usd":0.1691,"source":"img_price_config","variant":{"quality":"standard","size":"1440x1440"}},{"billable":"generate","unit":"second","cost_usd":0.1691,"source":"img_price_config","variant":{"quality":"standard","size":"1632x1248"}},{"billable":"generate","unit":"second","cost_usd":0.1691,"source":"img_price_config","variant":{"quality":"standard","size":"1920x1080"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"720x1280"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"832x1088"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"960x960"}},{"billable":"generate","unit":"second","cost_usd":0.1691,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-07-17","last_updated":"2026-07-17","output_modalities":"video","vendor":"alibaba","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-glm-5.2-free","model_name":"Coding GLM 5.2 (free)","developer_id":5,"desc":"coding glm 5.2 free (coding-glm-5.2-free)  is a free coding-focused API route offered by AIHubMix, powered by Z.ai’s open-source flagship GLM-5.2 model. It is suitable for code generation, debugging, project-level development, tool use, and long-running agent tasks, with support for reasoning, function calling, and structured outputs. Compared with GLM-5.1, it offers stronger coding capabilities and a 1-million-token context window. Each account is limited to 5 requests per minute, 100 requests per day, and 1 million free tokens per day.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":131072,"context_length":1000000,"release_date":"2026-06-16","last_updated":"2026-06-16","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high","max"],"default":"max"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","variant_of":"coding-glm-5.2","variant_kind":"pricing-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-kimi-k3-free","model_name":"Coding Kimi K3 (free)","developer_id":15,"desc":"coding-kimi-k3-free is the open and free version of coding-kimi-k3. To maintain reliable service, each account is limited to 5 requests per minute, 100 requests per day, and 1 million tokens per day.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,function_calling,structured_outputs","input_modalities":"text,image,video","endpoints":"","max_output":1048576,"context_length":1048576,"release_date":"2026-07-16","last_updated":"2026-07-16","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","high","max"],"default":"max"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"moonshot","variant_of":"coding-kimi-k3","variant_kind":"pricing-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-3.1-flash-image","model_name":"Gemini 3.1 Flash Image","developer_id":8,"desc":"gemini-3.1-flash-image (Nano Banana 2) features professional-grade visual intelligence, lightning-fast efficiency, and realistic, grounded generative capabilities. This model serves as the high-efficiency counterpart to Gemini 3 Pro Image, optimized for speed and high-volume developer use cases.","pricing":{"cache_read":0.05,"input":0.5,"output":3},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.05,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_image_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_image_tokens","unit":"million_tokens","cost_usd":60,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"image_generation,llm","features":"thinking","input_modalities":"text,image,pdf,video","endpoints":"","max_output":32768,"context_length":131072,"release_date":"2026-05-28","last_updated":"2026-05-28","output_modalities":"image,text","reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","high"],"default":"minimal"}],"interleaved":{"google.gemini":true},"vendor":"google","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"kimi-k2.7-code","model_name":"Kimi K2.7 Code","developer_id":15,"desc":"Kimi K2.7 Code is Kimi’s most intelligent Coding model, capable of completing programming tasks with higher success rates in long context. It features a native multimodal architecture that supports text, image, video input, and thinking modes, and dialogue and agent tasks.","pricing":{"cache_read":0.160835,"input":0.95,"output":3.9995},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"thinking,function_calling,structured_outputs","input_modalities":"text,image,video","endpoints":"","max_output":32768,"context_length":262144,"release_date":"2026-06-12","last_updated":"2026-06-12","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"moonshot","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"kimi-k2.7-code-highspeed","model_name":"Kimi K2.7 Code Highspeed","developer_id":15,"desc":"High-Speed version of Kimi K2.7 Code model, with output speed of approximately 180 Tokens/s and up to 260 Tokens/s in short context scenarios, delivering a more extreme coding experience.","pricing":{"cache_read":0.32167,"input":1.9,"output":7.999},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,function_calling,structured_outputs","input_modalities":"text,image,video","endpoints":"","max_output":32768,"context_length":262144,"release_date":"2026-06-12","last_updated":"2026-06-12","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"moonshot","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-audio-1.5","model_name":"GPT Audio 1.5","developer_id":12,"desc":"The gpt-audio model is OpenAI's first officially released (generally available) audio model. It supports audio input and output and can be used in Chat Completions.","pricing":{"input":2.5,"output":10},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_audio_tokens","unit":"million_tokens","cost_usd":32,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_audio_tokens","unit":"million_tokens","cost_usd":64,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"tts,stt","features":"thinking,function_calling,structured_outputs","input_modalities":"text,audio","endpoints":"","max_output":16384,"context_length":128000,"output_modalities":"audio,text","reasoning":true,"tool_call":true,"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"hy-3d-3.1","model_name":"Hy 3d 3.1","developer_id":24,"desc":"Using the Hunyuan Sheng 3D 3.1 model, it can generate higher-precision and higher-quality 3D models, supporting text-to-3D, image-to-3D, eight-view-to-3D, single-geometry generation (untextured model), sketch-to-3D, and intelligent topology-to-3D features.","pricing_source":"img_price_config","pricing_lines":[{"billable":"geometry","unit":"request","cost_usd":0.25,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"geometry-fc","unit":"request","cost_usd":0.4167,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"geometry-fc-fmt","unit":"request","cost_usd":0.5,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"geometry-fmt","unit":"request","cost_usd":0.3333,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"geometry-pbr","unit":"request","cost_usd":0.4167,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"geometry-pbr-fc","unit":"request","cost_usd":0.5833,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"geometry-pbr-fc-fmt","unit":"request","cost_usd":0.6667,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"geometry-pbr-fmt","unit":"request","cost_usd":0.5,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"normal","unit":"request","cost_usd":0.3333,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"normal-fc","unit":"request","cost_usd":0.5,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"normal-fc-fmt","unit":"request","cost_usd":0.5833,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"normal-fmt","unit":"request","cost_usd":0.4167,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"normal-pbr","unit":"request","cost_usd":0.5,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"normal-pbr-fc","unit":"request","cost_usd":0.6667,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"normal-pbr-fc-fmt","unit":"request","cost_usd":0.75,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"normal-pbr-fmt","unit":"request","cost_usd":0.5833,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"sketch","unit":"request","cost_usd":0.4167,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"sketch-fc","unit":"request","cost_usd":0.5833,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"sketch-fc-fmt","unit":"request","cost_usd":0.6667,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"sketch-fmt","unit":"request","cost_usd":0.5,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"sketch-pbr","unit":"request","cost_usd":0.5833,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"sketch-pbr-fc","unit":"request","cost_usd":0.75,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"sketch-pbr-fc-fmt","unit":"request","cost_usd":0.8333,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"sketch-pbr-fmt","unit":"request","cost_usd":0.6667,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"3d","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"vendor":"tencent","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"kling-v3-omni","model_name":"Kling V3 Omni","developer_id":33,"desc":"VIDEO 3.0 Omni: All-in-One Multimodal Input, Voice-Driven Characters, Direct Audio-Visual Output, and Storyboarding Building on the Kling VIDEO O1 and Kling VIDEO 2.6, the Kling 3.0 Model Series leverage a deeply integrated unified model training framework, achieving more native multimodal input and output. It combines Native Audio with Element Consistency Control, and breaks through duration limits.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.4225,"source":"img_price_config","variant":{"quality":"4k","size":"standard"}},{"billable":"generate","unit":"second","cost_usd":0.1127,"source":"img_price_config","variant":{"quality":"pro","size":"standard"}},{"billable":"generate","unit":"second","cost_usd":0.0845,"source":"img_price_config","variant":{"quality":"std","size":"standard"}},{"billable":"ref","unit":"second","cost_usd":0.169,"source":"img_price_config","variant":{"quality":"pro","size":"standard"}},{"billable":"ref","unit":"second","cost_usd":0.1268,"source":"img_price_config","variant":{"quality":"std","size":"standard"}},{"billable":"ref-sound","unit":"second","cost_usd":0.169,"source":"img_price_config","variant":{"quality":"pro","size":"standard"}},{"billable":"ref-sound","unit":"second","cost_usd":0.1268,"source":"img_price_config","variant":{"quality":"std","size":"standard"}},{"billable":"sound","unit":"second","cost_usd":0.4225,"source":"img_price_config","variant":{"quality":"4k","size":"standard"}},{"billable":"sound","unit":"second","cost_usd":0.1408,"source":"img_price_config","variant":{"quality":"pro","size":"standard"}},{"billable":"sound","unit":"second","cost_usd":0.1127,"source":"img_price_config","variant":{"quality":"std","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text,image,video","endpoints":"","max_output":0,"context_length":0,"output_modalities":"video","vendor":"kuaishou","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"kling-video-o1","model_name":"Kling Video O1","developer_id":33,"desc":"Kling Video O1 is a major unified multimodal video model launched by Kuaishou. It integrates text, images, video, and subject inputs into a single engine, focusing on addressing the \"consistency\" pain point in AI video, and is very suitable for professional teams in e-commerce, advertising, and continuity-driven creation that need to maintain the appearance of characters and objects unchanged across scenes.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.4225,"source":"img_price_config","variant":{"quality":"4k","size":"standard"}},{"billable":"generate","unit":"second","cost_usd":0.1127,"source":"img_price_config","variant":{"quality":"pro","size":"standard"}},{"billable":"generate","unit":"second","cost_usd":0.0845,"source":"img_price_config","variant":{"quality":"std","size":"standard"}},{"billable":"ref","unit":"second","cost_usd":0.169,"source":"img_price_config","variant":{"quality":"pro","size":"standard"}},{"billable":"ref","unit":"second","cost_usd":0.1268,"source":"img_price_config","variant":{"quality":"std","size":"standard"}},{"billable":"ref-sound","unit":"second","cost_usd":0.169,"source":"img_price_config","variant":{"quality":"pro","size":"standard"}},{"billable":"ref-sound","unit":"second","cost_usd":0.1268,"source":"img_price_config","variant":{"quality":"std","size":"standard"}},{"billable":"sound","unit":"second","cost_usd":0.4225,"source":"img_price_config","variant":{"quality":"4k","size":"standard"}},{"billable":"sound","unit":"second","cost_usd":0.1408,"source":"img_price_config","variant":{"quality":"pro","size":"standard"}},{"billable":"sound","unit":"second","cost_usd":0.1127,"source":"img_price_config","variant":{"quality":"std","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text,image,video","endpoints":"","max_output":0,"context_length":0,"output_modalities":"video","vendor":"kuaishou","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"longcat-2.0","model_name":"Longcat 2.0","developer_id":28,"desc":"Designed for agent development scenarios, it natively supports tool invocation, multi-step reasoning, and long-context tasks; it excels at code generation, automated workflows, and executing complex instructions; and it is deeply adapted to productivity tools such as Claude Code, OpenClaw, OpenCode, and Kilo Code.","pricing":{"cache_read":0.015492,"input":0.7746,"output":3.0984},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools","input_modalities":"text","endpoints":"","max_output":131072,"context_length":1000000,"release_date":"2026-06-30","last_updated":"2026-06-30","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"meituan-longcat","open_weights":true,"schema_checked":false,"promotion":{"name":"OpenRouter discount","off_percent":45,"time_type":"daily","daily":{"ranges":["00:00-23:59"]}},"retire_stage":"active"},{"model_id":"gemini-3-pro-image","model_name":"Gemini 3 Pro Image","developer_id":8,"desc":"Gemini-3-Pro-Image (Nano Banana Pro) is a high-performance image generation and editing model built on Gemini 3 Pro. It delivers enhanced multimodal understanding and real-world semantic reasoning, enabling fast creation of well-structured visual content such as infographics, product sketches, and multi-subject scenes. It can also leverage real-time knowledge through Search grounding. The model excels in text rendering, consistent multi-image blending, and identity preservation, while offering fine-grained creative controls like localized edits, lighting and focus adjustments, camera transformations, and flexible aspect ratios. It’s ideal for rapid design, concept previews, product visualization, and everyday image generation workflows.","pricing":{"input":2,"output":12},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":12,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_image_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_image_tokens","unit":"million_tokens","cost_usd":120,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"image_generation,llm","features":"thinking","input_modalities":"text,image","endpoints":"","max_output":32768,"context_length":65536,"release_date":"2026-05-28","last_updated":"2026-05-28","output_modalities":"image,text","reasoning":true,"interleaved":{"google.gemini":true},"vendor":"google","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"gpt-4o-transcribe-diarize","model_name":"GPT 4o Transcribe Diarize","developer_id":12,"desc":"GPT-4o Transcribe Diarize is an automatic speech recognition (ASR) model with built-in speaker diarization, meaning it can associate audio segments in a conversation with different speakers.","pricing":{"input":2.5,"output":10},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_audio_tokens","unit":"million_tokens","cost_usd":6,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"stt","features":"thinking,function_calling,structured_outputs","input_modalities":"text,audio","endpoints":"","max_output":2000,"context_length":16000,"output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3.7-flash","model_name":"Qwen3.7 Flash","developer_id":13,"desc":"The Qwen 3.7 series' mid-to-high cost-performance \"Plus\" model builds on strong text capabilities with a comprehensive upgrade to vision-language abilities, while retaining full agent capabilities in coding, tool use, and productivity workflows. Its core features are multimodal interactive hybrid agent capabilities, able to perceive real-world scenes, read screens and operate GUIs, generate code based on visual references, and provide end-to-end navigation of mobile applications.","pricing":{"cache_read":0.00564,"cache_write":0.03525,"input":0.0282,"output":0.1128,"tiers":[{"cache_read":0.0169,"cache_write":0.105625,"input":0.0845,"output":0.338,"tier":{"size":32000,"type":"context"}},{"cache_read":0.0338,"cache_write":0.21125,"input":0.169,"output":0.676,"tier":{"size":256000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.03525,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":32000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.105625,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":256000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.21125,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":1000000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.00564,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0169,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":256000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0338,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":1000000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.1128,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.338,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.676,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":1000000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.0282,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.0845,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.169,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":1000000}},{"billable":"web_search_requests","unit":"request","cost_usd":0.000548,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,web,long_context,thinking","input_modalities":"text,image,video","endpoints":"","max_output":131072,"context_length":1000000,"release_date":"2026-07-15","last_updated":"2026-07-15","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"alibaba","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3.7-plus","model_name":"Qwen3.7 Plus","developer_id":13,"desc":"The Qwen 3.7 series' mid-to-high cost-performance \"Plus\" model builds on strong text capabilities with a comprehensive upgrade to vision-language abilities, while retaining full agent capabilities in coding, tool use, and productivity workflows. Its core features are multimodal interactive hybrid agent capabilities, able to perceive real-world scenes, read screens and operate GUIs, generate code based on visual references, and provide end-to-end navigation of mobile applications.","pricing":{"cache_read":0.0564,"cache_write":0.3525,"input":0.282,"output":1.128,"tiers":[{"cache_read":0.169,"cache_write":1.05625,"input":0.845,"output":3.38,"tier":{"size":256000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.3525,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":256000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":1.05625,"source":"billing_config","tier":{"name":"tier2","min_tokens":256001,"max_tokens":1000000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0564,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":256000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.169,"source":"billing_config","tier":{"name":"tier2","min_tokens":256001,"max_tokens":1000000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.128,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.38,"source":"billing_config","tier":{"name":"tier2","min_tokens":256001,"max_tokens":1000000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.282,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.845,"source":"billing_config","tier":{"name":"tier2","min_tokens":256001,"max_tokens":1000000}},{"billable":"web_search_requests","unit":"request","cost_usd":0.000548,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,web,long_context,thinking","input_modalities":"text,image,video","endpoints":"chat_completions,claude_api","max_output":131072,"context_length":1000000,"release_date":"2026-05-26","last_updated":"2026-05-26","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"alibaba","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"step-3.7-flash","model_name":"Step 3.7 Flash","developer_id":16,"desc":"step-3.7-flash is stepfun's flagship inference model, designed for high-complexity tasks that require deep reasoning and fast execution. It excels at decomposing multi-step problems, performing tool calls, and maintaining consistency across massive datasets. It is the preferred choice for complex workloads such as long-context agents, advanced software engineering, and end-to-end research automation.","pricing":{"cache_read":0.044,"input":0.22,"output":1.32},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"","input_modalities":"text,image,video","endpoints":"","max_output":0,"context_length":256000,"release_date":"2026-05-29","last_updated":"2026-05-29","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"],"default":"medium"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"stepfun","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"minimax-m3","model_name":"MiniMax M3","developer_id":18,"desc":"The MiniMax M3 is a flagship programming model built for real-world productivity. As a production-grade model natively designed for Agent scenarios, it has achieved state-of-the-art (SOTA) performance in coding, agentic tool use, search, and office work.","pricing":{"input":0.288,"output":1.152},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,video","endpoints":"","max_output":524288,"context_length":1000000,"release_date":"2026-06-01","last_updated":"2026-06-01","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"minimax","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"claude-opus-4-8-think","model_name":"Claude Opus 4.8 Thinking","developer_id":2,"desc":"The claude-opus-4-8-think model has adaptive thinking mode pre-enabled; the default thinking intensity is \"medium\", and it can be invoked directly via the OpenAI unified API. The claude-opus-4-8 model does not display thinking content by default; you need to set the extra parameter \"display\": \"summarized\" to enable it.","pricing":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":6.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":6.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,pdf","endpoints":"","max_output":128000,"context_length":1000000,"release_date":"2026-05-28","last_updated":"2026-05-28","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"],"default":"medium"}],"interleaved":{"anthropic.messages":true},"vendor":"anthropic","variant_of":"claude-opus-4-8","variant_kind":"mode-preset","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"nemotron-3-nano-omni-30b-a3b-reasoning-free","model_name":"Nemotron 3 Nano Omni 30B A3B (reasoning) (free)","developer_id":17,"desc":"Developed by Nvidia, NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. Supporting a massive context length of 256,000 tokens, it accepts and processes inputs across text, images, and video. This model provides powerful multimodal comprehension tailored for complex enterprise workflows.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"reasoning,tool_calling,long_context","input_modalities":"text,image,video,audio","endpoints":"chat_completions","max_output":0,"context_length":262144,"release_date":"2026-04-28","last_updated":"2026-04-28","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved":{"openai.chat_completions":true},"vendor":"nvidia","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"nemotron-3-ultra-550b-a55b-free","model_name":"Nemotron 3 Ultra 550B A55B (free)","developer_id":17,"desc":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model featuring an extensive 1,000,000-token context length. Built on a hybrid Transformer-Mamba mixture-of-experts (MoE) architecture, it operates with 55B active parameters out of a total of 550B parameters. This advanced structure is designed to support sophisticated reasoning and complex task orchestration.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"reasoning,tool_calling,long_context","input_modalities":"text","endpoints":"chat_completions","max_output":0,"context_length":1048576,"release_date":"2026-06-04","last_updated":"2026-06-04","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"nvidia","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3.7-max","model_name":"Qwen3.7 Max","developer_id":13,"desc":"The Max model, the largest and most capable in the Qwen3.7 series, is currently offering its pure-text model capabilities for trial. Qwen3.7 is a new-generation flagship model designed for the agent era; its core strengths lie in the breadth and depth of its agent capabilities: it performs excellently in programming, office and productivity tasks, and long-term autonomous execution.","pricing":{"cache_read":0.169,"cache_write":2.1125,"input":1.69,"output":5.07},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":2.1125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.169,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":5.07,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.69,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.000548,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,web,long_context,thinking","input_modalities":"text","endpoints":"","max_output":131072,"context_length":1000000,"release_date":"2026-05-20","last_updated":"2026-05-20","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"alibaba","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-image-2","model_name":"GPT Image 2","developer_id":12,"desc":"GPT-image-2 is OpenAI's latest cutting-edge image generation model. Key value adds include better performance, quality, editing controls, and face preservation.\n(Currently the model's image generation time may be \u003e5 minutes; it is recommended to set the client timeout to ≥10 minutes.)\nThe model supports high input_fidelity and adding/removing one aspect of the image while retaining others. This model includes improvements in aspect ratio, resolution, and editing capabilities.","pricing":{"cache_read":1.25,"input":5,"output":30},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":1.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_image_tokens","unit":"million_tokens","cost_usd":8,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_image_tokens","unit":"million_tokens","cost_usd":30,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-04-21","last_updated":"2026-04-21","output_modalities":"image","vendor":"openai","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"nemotron-3.5-content-safety-free","model_name":"Nemotron 3.5 Content Safety (free)","developer_id":17,"desc":"Developed by NVIDIA, Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model fine-tuned from Google Gemma-3-4B. Supporting an expansive context length of 128,000 tokens, this model moderates both user inputs and generated responses for LLMs and VLMs. It provides robust safety filtering to ensure aligned and secure interactions across multiple modalities.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"reasoning,long_context","input_modalities":"text,image","endpoints":"chat_completions","max_output":0,"context_length":131072,"release_date":"2026-06-04","last_updated":"2026-06-04","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"}],"vendor":"nvidia","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"grok-4.3","model_name":"Grok 4.3","developer_id":9,"desc":"Grok 4.3 is amongst the leading models in intelligence and well priced when comparing to other models of similar price. It's also notably fast, however very verbose. The model supports text and image input, outputs text, and has a 1m tokens context window.","pricing":{"input":1.25,"output":2.5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs,long_context","input_modalities":"text,image","endpoints":"","max_output":30000,"context_length":1000000,"release_date":"2026-04-17","last_updated":"2026-04-17","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"],"default":"low"}],"interleaved":{"anthropic.messages":true,"openai.responses":true},"vendor":"xai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"happyhorse-1.0-i2v","model_name":"Happyhorse 1.0 I2v","developer_id":13,"desc":"HappyHorse-1.0-I2V supports image-to-video generation, featuring highly faithful dynamic visual generation capabilities, accurately understanding textual semantics and producing smooth, natural, and detail-rich high-quality videos.\n\n","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.2479,"source":"img_price_config","variant":{"quality":"standard","size":"1080x1920"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"1088x832"}},{"billable":"generate","unit":"second","cost_usd":0.2479,"source":"img_price_config","variant":{"quality":"standard","size":"1248x1632"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"1280x720"}},{"billable":"generate","unit":"second","cost_usd":0.2479,"source":"img_price_config","variant":{"quality":"standard","size":"1440x1440"}},{"billable":"generate","unit":"second","cost_usd":0.2479,"source":"img_price_config","variant":{"quality":"standard","size":"1632x1248"}},{"billable":"generate","unit":"second","cost_usd":0.2479,"source":"img_price_config","variant":{"quality":"standard","size":"1920x1080"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"720x1280"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"832x1088"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"960x960"}},{"billable":"generate","unit":"second","cost_usd":0.2479,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"video","vendor":"alibaba","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"happyhorse-1.0-r2v","model_name":"Happyhorse 1.0 R2v","developer_id":13,"desc":"HappyHorse-1.0-R2V supports reference-guided video generation, offering more stable subject and scene referencing, supports up to 9 reference images, and can accurately maintain creative intent to achieve stronger expressive capabilities.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.2479,"source":"img_price_config","variant":{"quality":"standard","size":"1080x1920"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"1088x832"}},{"billable":"generate","unit":"second","cost_usd":0.2479,"source":"img_price_config","variant":{"quality":"standard","size":"1248x1632"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"1280x720"}},{"billable":"generate","unit":"second","cost_usd":0.2479,"source":"img_price_config","variant":{"quality":"standard","size":"1440x1440"}},{"billable":"generate","unit":"second","cost_usd":0.2479,"source":"img_price_config","variant":{"quality":"standard","size":"1632x1248"}},{"billable":"generate","unit":"second","cost_usd":0.2479,"source":"img_price_config","variant":{"quality":"standard","size":"1920x1080"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"720x1280"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"832x1088"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"960x960"}},{"billable":"generate","unit":"second","cost_usd":0.2479,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"video","vendor":"alibaba","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"happyhorse-1.0-t2v","model_name":"Happyhorse 1.0 T2v","developer_id":13,"desc":"HappyHorse-1.0-T2V supports text-to-video generation, featuring highly faithful dynamic visual generation capabilities, accurately understanding textual semantics and producing smooth, natural, and detail-rich high-quality videos.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.2479,"source":"img_price_config","variant":{"quality":"standard","size":"1080x1920"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"1088x832"}},{"billable":"generate","unit":"second","cost_usd":0.2479,"source":"img_price_config","variant":{"quality":"standard","size":"1248x1632"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"1280x720"}},{"billable":"generate","unit":"second","cost_usd":0.2479,"source":"img_price_config","variant":{"quality":"standard","size":"1440x1440"}},{"billable":"generate","unit":"second","cost_usd":0.2479,"source":"img_price_config","variant":{"quality":"standard","size":"1632x1248"}},{"billable":"generate","unit":"second","cost_usd":0.2479,"source":"img_price_config","variant":{"quality":"standard","size":"1920x1080"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"720x1280"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"832x1088"}},{"billable":"generate","unit":"second","cost_usd":0.1395,"source":"img_price_config","variant":{"quality":"standard","size":"960x960"}},{"billable":"generate","unit":"second","cost_usd":0.2479,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"video","vendor":"alibaba","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"happyhorse-1.0-video-edit","model_name":"Happyhorse 1.0 Video Edit","developer_id":13,"desc":"HappyHorse-1.0-Video-Edit supports video editing, allows editing videos via natural language commands, can reference up to 5 images to edit video elements locally or globally, and can accurately replicate video dynamics to achieve stronger expressive capabilities.","pricing":{"input":2,"output":0},"pricing_source":"billing_config","pricing_lines":[{"billable":"input_video_seconds","unit":"second","cost_usd":0.1395,"source":"billing_config","variant":{"match":{"size":"720x1280"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.1395,"source":"billing_config","variant":{"match":{"size":"1280x720"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.1395,"source":"billing_config","variant":{"match":{"size":"960x960"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.1395,"source":"billing_config","variant":{"match":{"size":"832x1088"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.1395,"source":"billing_config","variant":{"match":{"size":"1088x832"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.2479,"source":"billing_config","variant":{"match":{"size":"1920x1080"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.2479,"source":"billing_config","variant":{"match":{"size":"1080x1920"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.2479,"source":"billing_config","variant":{"match":{"size":"1440x1440"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.2479,"source":"billing_config","variant":{"match":{"size":"1632x1248"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.2479,"source":"billing_config","variant":{"match":{"size":"1248x1632"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.2479,"source":"billing_config","variant":{"fallback":true}},{"billable":"video_generation","unit":"second","cost_usd":0.1395,"source":"billing_config","variant":{"match":{"size":"720x1280"}}},{"billable":"video_generation","unit":"second","cost_usd":0.1395,"source":"billing_config","variant":{"match":{"size":"1280x720"}}},{"billable":"video_generation","unit":"second","cost_usd":0.1395,"source":"billing_config","variant":{"match":{"size":"960x960"}}},{"billable":"video_generation","unit":"second","cost_usd":0.1395,"source":"billing_config","variant":{"match":{"size":"832x1088"}}},{"billable":"video_generation","unit":"second","cost_usd":0.1395,"source":"billing_config","variant":{"match":{"size":"1088x832"}}},{"billable":"video_generation","unit":"second","cost_usd":0.2479,"source":"billing_config","variant":{"match":{"size":"1920x1080"}}},{"billable":"video_generation","unit":"second","cost_usd":0.2479,"source":"billing_config","variant":{"match":{"size":"1080x1920"}}},{"billable":"video_generation","unit":"second","cost_usd":0.2479,"source":"billing_config","variant":{"match":{"size":"1440x1440"}}},{"billable":"video_generation","unit":"second","cost_usd":0.2479,"source":"billing_config","variant":{"match":{"size":"1632x1248"}}},{"billable":"video_generation","unit":"second","cost_usd":0.2479,"source":"billing_config","variant":{"match":{"size":"1248x1632"}}},{"billable":"video_generation","unit":"second","cost_usd":0.2479,"source":"billing_config","variant":{"fallback":true}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text,video,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"video","vendor":"alibaba","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"north-mini-code-free","model_name":"North Mini Code (free)","developer_id":6,"desc":"Developed by Cohere, north-mini-code-free is the debut model of the North family and Cohere's first agentic coding model. This sparse mixture-of-experts model features 30B total parameters and 3B active parameters, designed and optimized for high performance. With an expansive context length of 256,000 tokens, it is well-suited for handling complex developer workflows and large codebases.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"reasoning,tool_calling,long_context","input_modalities":"text","endpoints":"chat_completions","max_output":64000,"context_length":256000,"release_date":"2026-06-09","last_updated":"2026-06-09","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high"]}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"cohere","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-glm-5.2","model_name":"Coding GLM 5.2","developer_id":5,"desc":"Currently, the special resources for this model are limited, but due to its popularity, the usage is too high, which may result in a large number of 429 errors. Resources have been coordinated, and improvements are expected in the coming weeks, so please stay tuned. In the meantime, it is recommended to use the regular-priced API model, which can ensure absolute stability. The model ID is glm-5.2.","pricing":{"input":0.06,"output":0.22},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":131072,"context_length":1000000,"release_date":"2026-06-16","last_updated":"2026-06-16","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high","max"],"default":"max"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"ernie-5.1","model_name":"ERNIE 5.1","developer_id":25,"desc":"ERNIE 5.1 is the latest model in the Wenxin series, with comprehensive upgrades to its foundational capabilities and significant improvements in agents, knowledge, reasoning, and deep search. This upgrade uses a decoupled fully-asynchronous reinforcement learning technique to specifically address challenges encountered as large models evolve toward agent-based autonomous decision-making, such as training–inference numerical bias, low utilization of heterogeneous resources, and global issues caused by long-tail effects. It is paired with scaled agent post-training techniques to enhance model capabilities and generalization, enabling a three-step collaboration of environment, expert, and fusion that both ensures training efficiency and significantly improves the model’s stability and performance on complex tasks.","pricing":{"cache_read":0.5634,"input":0.5634,"output":2.5353,"tiers":[{"cache_read":0.845,"input":0.845,"output":3.098361,"tier":{"size":32000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.5634,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.845,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.5353,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.0983615,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.5634,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.845,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}}],"has_zdr_provider":false,"types":"llm","features":"thinking","input_modalities":"text","endpoints":"","max_output":65536,"context_length":119000,"release_date":"2026-05-10","last_updated":"2026-05-10","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"baidu","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-3.1-flash-lite","model_name":"Gemini 3.1 Flash Lite","developer_id":8,"desc":"gemini-3.1-flash-lite is currently Google's latest and most cost-effective model, optimized for large-scale agent-based tasks, translation, and simple data processing.","pricing":{"cache_read":0.025,"input":0.25,"output":1.5},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":1,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.025,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_audio_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_video_tokens","unit":"million_tokens","cost_usd":0.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.014,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs,web,deepsearch,long_context","input_modalities":"text,image,video,audio,pdf","endpoints":"chat_completions,gemini_api,claude_api","max_output":65536,"context_length":1048576,"release_date":"2026-05-07","last_updated":"2026-05-07","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"],"default":"medium"}],"vendor":"google","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-3.1-flash-lite-nothink","model_name":"Gemini 3.1 Flash Lite (no think)","developer_id":8,"desc":"gemini-3.1-flash-lite is currently Google's latest and most cost-effective model, optimized for large-scale agent-based tasks, translation, and simple data processing.","pricing":{"cache_read":0.025,"input":0.25,"output":1.5},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":1,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.025,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_audio_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_video_tokens","unit":"million_tokens","cost_usd":0.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.014,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs,web,deepsearch,long_context","input_modalities":"text,image,video,audio,pdf","endpoints":"chat_completions,gemini_api,claude_api","max_output":65536,"context_length":1048576,"output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"],"default":"medium"}],"vendor":"google","variant_of":"gemini-3.1-flash-lite","variant_kind":"mode-preset","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.5","model_name":"GPT 5.5","developer_id":12,"desc":"GPT-5.5 raises the baseline for complex production workflows. It’s a strong fit for coding use cases, tool-heavy agents, grounded assistants, long-context retrieval, product-spec-to-plan workflows, and customer-facing workflows where execution quality and response polish are critical.","pricing":{"cache_read":0.5,"input":5,"output":30,"tiers":[{"cache_read":1,"input":10,"output":45,"tier":{"size":272000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":1,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":30,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":45,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,function_calling,structured_outputs,web,tools","input_modalities":"text,image,pdf","endpoints":"chat_completions,claude_api,responses","max_output":128000,"context_length":1050000,"release_date":"2026-04-24","last_updated":"2026-04-24","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"],"default":"medium"}],"interleaved":{"openai.responses":true},"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.5-pro","model_name":"GPT 5.5 Pro","developer_id":12,"desc":"Please note: this model is extremely expensive and very slow. If a request fails due to network issues, you may still be charged heavily; we cannot refund charges incurred by requests to this model.\nGPT-5.5 pro is available in the Responses API only to enable support for multi-turn model interactions before responding to API requests, and other advanced API features in the future. Since GPT-5.5 pro is designed to tackle tough problems, some requests may take several minutes to finish. To avoid timeout, please set a longer timeout duration. It is recommended to use this under good network conditions.","pricing":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"size":272000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":180,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":270,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":30,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":60,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,web,tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":128000,"context_length":1050000,"release_date":"2026-04-23","last_updated":"2026-04-23","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"],"default":"medium"}],"interleaved":{"openai.responses":true},"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-v4-flash","model_name":"DeepSeek V4 Flash","developer_id":7,"desc":"(This model currently points to the older 0423 version; if you need to request the latest version, you can choose the model deepseek-v4-flash-0731)DeepSeek-V4 features an ultra-long context of one million characters and achieves leading performance domestically and in the open-source domain in agent capabilities, world knowledge, and reasoning.","pricing":{"cache_read":0.0284,"input":0.142,"output":0.284},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,thinking","input_modalities":"text,image","endpoints":"chat_completions,claude_api","max_output":393216,"context_length":1000000,"release_date":"2026-04-24","last_updated":"2026-04-24","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high","max"],"default":"high"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"deepseek","variant_of":"deepseek-v4.1-flash-1017","variant_kind":"deprecated-alias","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-v4-pro","model_name":"DeepSeek V4 Pro","developer_id":7,"desc":"(This model currently points to the older 0423 version; if you need to request the latest version, you can choose the model deepseek-v4-pro-0813)DeepSeek-V4 features an ultra-long context of one million characters and achieves leading performance domestically and in the open-source domain in agent capabilities, world knowledge, and reasoning.","pricing":{"cache_read":0.14027,"input":1.69,"output":3.38},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,thinking","input_modalities":"text","endpoints":"","max_output":384000,"context_length":1000000,"release_date":"2026-04-24","last_updated":"2026-04-24","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"],"default":"high"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"deepseek","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemma-4-31b-it-free","model_name":"Gemma 4 31B It (free)","developer_id":8,"desc":"Gemma 4 31B Instruct is a 30.7B dense multimodal model developed by Google DeepMind that supports both text and image inputs with text outputs. It features an expansive 256K token context window alongside a configurable thinking and reasoning mode. The model also includes native function support to streamline complex tasks.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"reasoning,tool_calling,long_context","input_modalities":"text,image,video","endpoints":"chat_completions","max_output":0,"context_length":262144,"release_date":"2026-04-02","last_updated":"2026-04-02","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","high"]}],"vendor":"google","variant_of":"gemma-4-31b-it","variant_kind":"pricing-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seedream-5.0-pro","model_name":"Doubao Seedream 5.0 Pro","developer_id":4,"desc":"Seedream-5.0-pro is the latest image-creation model released by ByteDance. The model advances image creation to a new stage of controllable production. The main highlights of this update are more controllable editing, more production-ready generation, and more natural results.","pricing":{"input":2,"output":0},"pricing_source":"billing_config","pricing_lines":[{"billable":"image_generation","unit":"image","cost_usd":0.0471,"source":"billing_config","variant":{"match":{"megapixels":{"lte":2.36}}}},{"billable":"image_generation","unit":"image","cost_usd":0.0942,"source":"billing_config","variant":{"match":{"megapixels":{"gt":2.36}}}},{"billable":"image_generation","unit":"image","cost_usd":0.0471,"source":"billing_config","variant":{"fallback":true}},{"billable":"image_input","unit":"image","cost_usd":0.00286,"source":"billing_config"}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"image","vendor":"bytedance","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"ernie-5.0","model_name":"ERNIE 5.0","developer_id":25,"desc":"ERNIE 5.0 is the next-generation natively multimodal foundation model in the ERNIE family. Built on a unified multimodal architecture, it jointly learns from text, images, audio, and video to deliver broad multimodal capabilities.\n\nERNIE 5.0 features significantly upgraded core capabilities and shows strong performance across benchmarks, with notable gains in multimodal understanding, instruction following, creative writing, factual accuracy, and agent planning with tool use.","pricing":{"cache_read":0.82192,"input":0.82192,"output":3.28768,"tiers":[{"cache_read":1.36986,"input":1.36986,"output":5.47944,"tier":{"size":32000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.82192,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":1.36986,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.28768,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":5.47944,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.82192,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.36986,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}}],"has_zdr_provider":false,"types":"llm","features":"thinking","input_modalities":"text,image","endpoints":"","max_output":65536,"context_length":119000,"output_modalities":"text","reasoning":true,"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"baidu","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"kimi-k2.6","model_name":"Kimi K2.6","developer_id":15,"desc":"Kimi K2.6 is Kimi's latest and most intelligent model, with stronger and more stable long-range code-writing capabilities, significantly improved instruction-following and self-correction abilities, and support for text, image, and video inputs, thinking and non-thinking modes, as well as dialogue and Agent tasks.The model has a context length of 256k, supports long-form thinking, and excels at deep reasoning.","pricing":{"cache_read":0.160835,"input":0.95,"output":3.9995},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,function_calling,structured_outputs","input_modalities":"text,image,video","endpoints":"","max_output":32768,"context_length":262144,"release_date":"2026-04-21","last_updated":"2026-04-21","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"moonshot","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"command-a-plus-05-2026","model_name":"Command A Plus 05 2026","developer_id":6,"desc":"Cohere's stronger command model for multilingual agents and enterprise workflows","pricing":{"input":2.5,"output":10},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,structured_outputs","input_modalities":"text,image","endpoints":"chat_completions,responses","max_output":64000,"context_length":128000,"release_date":"2026-05-20","last_updated":"2026-05-20","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"vendor":"cohere","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3.6-27b","model_name":"Qwen3.6 27B","developer_id":13,"desc":"The Qwen3.6 series 27B native vision-language Dense model. Compared with the 3.5-27B, the model notably improves Agentic coding capability and further enhances STEM and reasoning abilities; on the visual modality side, spatial intelligence, object localization and detection capabilities are significantly strengthened, and video understanding, document OCR, and visual agent capabilities have steadily improved.","pricing":{"input":0.422,"output":2.532},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,web,long_context,thinking","input_modalities":"text,image,video","endpoints":"","max_output":65536,"context_length":262144,"release_date":"2026-04-22","last_updated":"2026-04-22","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"vendor":"alibaba","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3.6-35b-a3b","model_name":"Qwen3.6 35B A3B","developer_id":13,"desc":"Qwen 3.6, the native vision-language Plus series model, demonstrates outstanding performance comparable to the current top cutting-edge models, with a significant improvement over the 3.5 series. The model's capabilities have been markedly enhanced in Agentic coding, front-end programming, Vibe coding and other coding abilities, universal multimodal recognition, OCR, object localization, and more.","pricing":{"input":0.254,"output":1.524},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.524,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.254,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":256000}},{"billable":"web_search_requests","unit":"request","cost_usd":0.000548,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,web,long_context,thinking","input_modalities":"text,image,video","endpoints":"","max_output":65536,"context_length":262144,"release_date":"2026-04-16","last_updated":"2026-04-16","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"alibaba","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3.6-flash","model_name":"Qwen3.6 Flash","developer_id":13,"desc":"Qwen 3.6, the native vision-language Plus series model, demonstrates outstanding performance comparable to the current top cutting-edge models, with a significant improvement over the 3.5 series. The model's capabilities have been markedly enhanced in Agentic coding, front-end programming, Vibe coding and other coding abilities, universal multimodal recognition, OCR, object localization, and more.","pricing":{"cache_read":0.0169,"cache_write":0.21125,"input":0.169,"output":1.014,"tiers":[{"cache_read":0.0676,"cache_write":0.845,"input":0.676,"output":4.056,"tier":{"size":256000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.21125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":256000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.845,"source":"billing_config","tier":{"name":"tier2","min_tokens":256001,"max_tokens":1000000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0169,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":256000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0676,"source":"billing_config","tier":{"name":"tier2","min_tokens":256001,"max_tokens":1000000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.014,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":4.056,"source":"billing_config","tier":{"name":"tier2","min_tokens":256001,"max_tokens":1000000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.169,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.676,"source":"billing_config","tier":{"name":"tier2","min_tokens":256001,"max_tokens":1000000}},{"billable":"web_search_requests","unit":"request","cost_usd":0.000548,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,web,long_context,thinking","input_modalities":"text,image,video","endpoints":"","max_output":65536,"context_length":1000000,"release_date":"2026-04-27","last_updated":"2026-04-27","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"alibaba","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-chat-latest","model_name":"GPT Chat","developer_id":12,"desc":"GPT Chat Latest points to OpenAI's stable API alias chat-latest that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates in the future, they are routed behind this slug automatically.","pricing":{"cache_read":0.5,"input":5,"output":30,"tiers":[{"cache_read":1,"input":10,"output":45,"tier":{"size":272000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":1,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":30,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":45,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,function_calling,structured_outputs,web,tools","input_modalities":"text,image","endpoints":"","max_output":128000,"context_length":400000,"release_date":"2026-05-05","last_updated":"2026-05-05","output_modalities":"text","reasoning":true,"tool_call":true,"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"claude-opus-4-7","model_name":"Claude Opus 4.7","developer_id":2,"desc":"Claude Opus 4.7 is Anthropic’s latest and most powerful publicly available model. It has high autonomy and performs exceptionally well on long-horizon agent tasks, knowledge work, vision tasks, and memory tasks.  The claude-opus-4-7 model does not display thinking content by default; you need to set the extra parameter \"display\": \"summarized\" to enable it.This page summarizes all the new features at release.","pricing":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":6.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":6.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,pdf","endpoints":"","max_output":128000,"context_length":1000000,"release_date":"2026-04-16","last_updated":"2026-04-16","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"],"default":"medium"}],"interleaved":{"anthropic.messages":true},"vendor":"anthropic","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"claude-opus-4-7-think","model_name":"Claude Opus 4.7 Thinking","developer_id":2,"desc":"The claude-opus-4-7-think model has adaptive thinking mode pre-enabled; the default thinking intensity is \"medium\", and it can be invoked directly via the OpenAI unified API. The claude-opus-4-7 model does not display thinking content by default; you need to set the extra parameter \"display\": \"summarized\" to enable it.","pricing":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":6.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":6.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,pdf","endpoints":"","max_output":128000,"context_length":1000000,"release_date":"2026-04-16","last_updated":"2026-04-16","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"],"default":"medium"}],"interleaved":{"anthropic.messages":true},"vendor":"anthropic","variant_of":"claude-opus-4-7","variant_kind":"mode-preset","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"cohere-rerank-v4.0-fast","model_name":"Cohere Rerank V4.0 Fast","developer_id":6,"desc":"Rerank 4 is the most advanced set of reranker models available today, purpose-built to meet the realities and challenges of enterprise AI search. It delivers best-in-class retrieval, outperforming the likes of MongoDB’s Voyage models and ElasticSearch’s Jina rerankers in overall search relevance, as well as improved latency, flexible deployment options, deep customizability and robust multilingual performance. Designed for business-critical applications across key industries and domains, Rerank 4 sets a new standard for accuracy and adaptability in enterprise search.","pricing":{"input":0.068,"output":0},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"search_units","unit":"search_unit","cost_usd":0.002,"source":"billing_config"}],"has_zdr_provider":false,"types":"rerank","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":32768,"vendor":"cohere","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"cohere-rerank-v4.0-pro","model_name":"Cohere Rerank V4.0 Pro","developer_id":6,"desc":"Rerank 4 is the most advanced set of reranker models available today, purpose-built to meet the realities and challenges of enterprise AI search. It delivers best-in-class retrieval, outperforming the likes of MongoDB’s Voyage models and ElasticSearch’s Jina rerankers in overall search relevance, as well as improved latency, flexible deployment options, deep customizability and robust multilingual performance. Designed for business-critical applications across key industries and domains, Rerank 4 sets a new standard for accuracy and adaptability in enterprise search.","pricing":{"input":0.068,"output":0},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"search_units","unit":"search_unit","cost_usd":0.0025,"source":"billing_config"}],"has_zdr_provider":false,"types":"rerank","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":32768,"vendor":"cohere","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-image-2.0","model_name":"Qwen Image 2.0","developer_id":13,"desc":"The Qwen-Image-2.0 series accelerated models integrate image generation and image editing; they offer more professional text rendering with support for 1k-token instructions, finer realistic textures and delicate portrayal of photorealistic scenes, and stronger semantic adherence. The accelerated version effectively achieves an optimal balance between model quality and performance.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"image","cost_usd":0.0282,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-03-03","last_updated":"2026-03-03","output_modalities":"image","vendor":"alibaba","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"qwen-image-2.0-pro","model_name":"Qwen Image 2.0 Pro","developer_id":13,"desc":"The Qwen-Image-2.0 full-powered models achieve the integration of image generation and image editing; they offer more professional text rendering with support for 1k-token instructions, more refined photorealistic textures and delicate depiction of realistic scenes, and stronger semantic adherence. The full-powered version delivers the strongest text rendering capability and realism in the 2.0 series.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"image","cost_usd":0.0704,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-03-03","last_updated":"2026-03-03","output_modalities":"image","vendor":"alibaba","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"gemma-4-26b-a4b-it-free","model_name":"Gemma 4 26B A4B It (free)","developer_id":8,"desc":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model developed by Google DeepMind. Featuring an expansive context length of 262,144 tokens, it delivers near-31B quality with highly efficient inference. Despite its 25.2B total parameters, only 3.8B are activated per token, making it an incredibly fast and cost-effective solution.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"reasoning,tool_calling,long_context","input_modalities":"text,image,video","endpoints":"chat_completions","max_output":0,"context_length":262144,"release_date":"2026-04-02","last_updated":"2026-04-02","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","high"]}],"vendor":"google","variant_of":"gemma-4-26b-a4b-it","variant_kind":"pricing-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"grok-4-20-non-reasoning","model_name":"Grok 4 20","developer_id":9,"desc":"Grok 4.2 is xAI’s latest large language model, built for strong reasoning, multimodal understanding, and enterprise use. It improves instruction following, honesty, and calibration over earlier Grok versions, while supporting both single‑agent and multi‑agent workflows. Designed as a general‑purpose, truth‑seeking assistant, Grok 4.2 is well suited for research, analysis, coding, and complex professional tasks when deployed with appropriate guardrails.","pricing":{"cache_read":1,"input":2,"output":6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":1000000,"release_date":"2026-03-09","last_updated":"2026-03-09","output_modalities":"text","reasoning":true,"tool_call":true,"vendor":"xai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"grok-4-20-reasoning","model_name":"Grok 4 20 (reasoning)","developer_id":9,"desc":"Grok 4.2 is xAI’s latest large language model, built for strong reasoning, multimodal understanding, and enterprise use. It improves instruction following, honesty, and calibration over earlier Grok versions, while supporting both single‑agent and multi‑agent workflows. Designed as a general‑purpose, truth‑seeking assistant, Grok 4.2 is well suited for research, analysis, coding, and complex professional tasks when deployed with appropriate guardrails.","pricing":{"input":2,"output":6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":1000000,"release_date":"2026-03-09","last_updated":"2026-03-09","output_modalities":"text","reasoning":true,"tool_call":true,"interleaved":{"anthropic.messages":true,"openai.responses":true},"vendor":"xai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3.6-plus","model_name":"Qwen3.6 Plus","developer_id":13,"desc":"Qwen 3.6, the native vision-language Plus series model, demonstrates outstanding performance comparable to the current top cutting-edge models, with a significant improvement over the 3.5 series. The model's capabilities have been markedly enhanced in Agentic coding, front-end programming, Vibe coding and other coding abilities, universal multimodal recognition, OCR, object localization, and more.","pricing":{"cache_read":0.0282,"cache_write":0.3525,"input":0.282,"output":1.692,"tiers":[{"cache_read":0.1128,"cache_write":1.41,"input":1.128,"output":6.768,"tier":{"size":256000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.3525,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":256000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":1.41,"source":"billing_config","tier":{"name":"tier2","min_tokens":256001,"max_tokens":1000000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0282,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":256000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.1128,"source":"billing_config","tier":{"name":"tier2","min_tokens":256001,"max_tokens":1000000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.692,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":6.768,"source":"billing_config","tier":{"name":"tier2","min_tokens":256001,"max_tokens":1000000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.282,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.128,"source":"billing_config","tier":{"name":"tier2","min_tokens":256001,"max_tokens":1000000}},{"billable":"web_search_requests","unit":"request","cost_usd":0.000548,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,web,long_context,thinking","input_modalities":"text,image,video","endpoints":"","max_output":65536,"context_length":1000000,"release_date":"2026-04-02","last_updated":"2026-04-02","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"alibaba","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"wan2.7-i2v","model_name":"Wan2.7 I2v","developer_id":13,"desc":"Wanxiang 2.7 — image-to-video: performance capabilities comprehensively upgraded. Dramatic/dialogue scenes convey delicate, natural emotions; action scenes are fierce, with every punch landing hard. Combined with more dramatic, rhythmically paced camera cuts, it achieves stronger overall performance.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.141,"source":"img_price_config","variant":{"quality":"standard","size":"1080x1920"}},{"billable":"generate","unit":"second","cost_usd":0.0846,"source":"img_price_config","variant":{"quality":"standard","size":"1088x832"}},{"billable":"generate","unit":"second","cost_usd":0.141,"source":"img_price_config","variant":{"quality":"standard","size":"1248x1632"}},{"billable":"generate","unit":"second","cost_usd":0.0846,"source":"img_price_config","variant":{"quality":"standard","size":"1280x720"}},{"billable":"generate","unit":"second","cost_usd":0.141,"source":"img_price_config","variant":{"quality":"standard","size":"1440x1440"}},{"billable":"generate","unit":"second","cost_usd":0.141,"source":"img_price_config","variant":{"quality":"standard","size":"1632x1248"}},{"billable":"generate","unit":"second","cost_usd":0.141,"source":"img_price_config","variant":{"quality":"standard","size":"1920x1080"}},{"billable":"generate","unit":"second","cost_usd":0.0846,"source":"img_price_config","variant":{"quality":"standard","size":"720x1280"}},{"billable":"generate","unit":"second","cost_usd":0.0846,"source":"img_price_config","variant":{"quality":"standard","size":"832x1088"}},{"billable":"generate","unit":"second","cost_usd":0.0846,"source":"img_price_config","variant":{"quality":"standard","size":"960x960"}},{"billable":"generate","unit":"second","cost_usd":0.0846,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text,image,audio","endpoints":"","max_output":0,"context_length":0,"output_modalities":"video","vendor":"alibaba","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"wan2.7-r2v","model_name":"Wan2.7 R2v","developer_id":13,"desc":"Wanxiang 2.7 — reference-driven video generation: more stable references for characters, props, and scenes; supports up to five mixed image/video references; supports audio/timbre references; combined with foundational capability upgrades to deliver stronger performance.","pricing":{"input":2,"output":0},"pricing_source":"billing_config","pricing_lines":[{"billable":"input_video_seconds","unit":"second","cost_usd":0.0846,"source":"billing_config","variant":{"match":{"size":"720x1280"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.0846,"source":"billing_config","variant":{"match":{"size":"1280x720"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.0846,"source":"billing_config","variant":{"match":{"size":"960x960"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.0846,"source":"billing_config","variant":{"match":{"size":"832x1088"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.0846,"source":"billing_config","variant":{"match":{"size":"1088x832"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.141,"source":"billing_config","variant":{"match":{"size":"1920x1080"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.141,"source":"billing_config","variant":{"match":{"size":"1080x1920"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.141,"source":"billing_config","variant":{"match":{"size":"1440x1440"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.141,"source":"billing_config","variant":{"match":{"size":"1632x1248"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.141,"source":"billing_config","variant":{"match":{"size":"1248x1632"}}},{"billable":"input_video_seconds","unit":"second","cost_usd":0.0846,"source":"billing_config","variant":{"fallback":true}},{"billable":"video_generation","unit":"second","cost_usd":0.0846,"source":"billing_config","variant":{"match":{"size":"720x1280"}}},{"billable":"video_generation","unit":"second","cost_usd":0.0846,"source":"billing_config","variant":{"match":{"size":"1280x720"}}},{"billable":"video_generation","unit":"second","cost_usd":0.0846,"source":"billing_config","variant":{"match":{"size":"960x960"}}},{"billable":"video_generation","unit":"second","cost_usd":0.0846,"source":"billing_config","variant":{"match":{"size":"832x1088"}}},{"billable":"video_generation","unit":"second","cost_usd":0.0846,"source":"billing_config","variant":{"match":{"size":"1088x832"}}},{"billable":"video_generation","unit":"second","cost_usd":0.141,"source":"billing_config","variant":{"match":{"size":"1920x1080"}}},{"billable":"video_generation","unit":"second","cost_usd":0.141,"source":"billing_config","variant":{"match":{"size":"1080x1920"}}},{"billable":"video_generation","unit":"second","cost_usd":0.141,"source":"billing_config","variant":{"match":{"size":"1440x1440"}}},{"billable":"video_generation","unit":"second","cost_usd":0.141,"source":"billing_config","variant":{"match":{"size":"1632x1248"}}},{"billable":"video_generation","unit":"second","cost_usd":0.141,"source":"billing_config","variant":{"match":{"size":"1248x1632"}}},{"billable":"video_generation","unit":"second","cost_usd":0.0846,"source":"billing_config","variant":{"fallback":true}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text,image,video,audio","endpoints":"","max_output":0,"context_length":0,"output_modalities":"video","vendor":"alibaba","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"wan2.7-t2v","model_name":"Wan2.7 T2v","developer_id":13,"desc":"Wanxiang 2.7 — text-to-video: performance capabilities comprehensively upgraded. Dramatic/dialogue scenes convey delicate, natural emotions; action scenes are intense, with every punch landing hard. Paired with more dramatic and rhythmically paced camera cuts, it achieves stronger overall acting performance.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.141,"source":"img_price_config","variant":{"quality":"standard","size":"1080x1920"}},{"billable":"generate","unit":"second","cost_usd":0.0846,"source":"img_price_config","variant":{"quality":"standard","size":"1088x832"}},{"billable":"generate","unit":"second","cost_usd":0.141,"source":"img_price_config","variant":{"quality":"standard","size":"1248x1632"}},{"billable":"generate","unit":"second","cost_usd":0.0846,"source":"img_price_config","variant":{"quality":"standard","size":"1280x720"}},{"billable":"generate","unit":"second","cost_usd":0.141,"source":"img_price_config","variant":{"quality":"standard","size":"1440x1440"}},{"billable":"generate","unit":"second","cost_usd":0.141,"source":"img_price_config","variant":{"quality":"standard","size":"1632x1248"}},{"billable":"generate","unit":"second","cost_usd":0.141,"source":"img_price_config","variant":{"quality":"standard","size":"1920x1080"}},{"billable":"generate","unit":"second","cost_usd":0.0846,"source":"img_price_config","variant":{"quality":"standard","size":"720x1280"}},{"billable":"generate","unit":"second","cost_usd":0.0846,"source":"img_price_config","variant":{"quality":"standard","size":"832x1088"}},{"billable":"generate","unit":"second","cost_usd":0.0846,"source":"img_price_config","variant":{"quality":"standard","size":"960x960"}},{"billable":"generate","unit":"second","cost_usd":0.0846,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text,audio","endpoints":"","max_output":0,"context_length":0,"output_modalities":"video","vendor":"alibaba","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"wan2.7-videoedit","model_name":"Wan2.7 Videoedit","developer_id":13,"desc":"Wanxiang 2.7 — video editing: edit videos using natural-language commands, supporting local or global edits; can use reference images to replace video elements; supports replicating video actions, special effects, camera movements, and other dynamic processes.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.141,"source":"img_price_config","variant":{"quality":"standard","size":"1080x1920"}},{"billable":"generate","unit":"second","cost_usd":0.0846,"source":"img_price_config","variant":{"quality":"standard","size":"1088x832"}},{"billable":"generate","unit":"second","cost_usd":0.141,"source":"img_price_config","variant":{"quality":"standard","size":"1248x1632"}},{"billable":"generate","unit":"second","cost_usd":0.0846,"source":"img_price_config","variant":{"quality":"standard","size":"1280x720"}},{"billable":"generate","unit":"second","cost_usd":0.141,"source":"img_price_config","variant":{"quality":"standard","size":"1440x1440"}},{"billable":"generate","unit":"second","cost_usd":0.141,"source":"img_price_config","variant":{"quality":"standard","size":"1632x1248"}},{"billable":"generate","unit":"second","cost_usd":0.141,"source":"img_price_config","variant":{"quality":"standard","size":"1920x1080"}},{"billable":"generate","unit":"second","cost_usd":0.0846,"source":"img_price_config","variant":{"quality":"standard","size":"720x1280"}},{"billable":"generate","unit":"second","cost_usd":0.0846,"source":"img_price_config","variant":{"quality":"standard","size":"832x1088"}},{"billable":"generate","unit":"second","cost_usd":0.0846,"source":"img_price_config","variant":{"quality":"standard","size":"960x960"}},{"billable":"generate","unit":"second","cost_usd":0.0846,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text,image,video","endpoints":"","max_output":0,"context_length":0,"output_modalities":"video","vendor":"alibaba","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-minimax-m3-free","model_name":"Coding MiniMax M3 (free)","developer_id":18,"desc":"coding-minimax-m3-free is a free and open version offered by AIHubMix specifically for MiniMax users.  To maintain reliable service, each account is limited to 5 requests per minute, 500 requests per day, and 1 million tokens per day.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,video","endpoints":"","max_output":524288,"context_length":1000000,"release_date":"2026-05-31","last_updated":"2026-05-31","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"minimax","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seedance-2-0-260128","model_name":"Doubao Seedance 2.0 260128","developer_id":4,"desc":"The Doubao large-model team has launched a new-generation professional-grade multimodal video-creation model, Seedance 2.0. It supports images, videos, and audio as multimodal reference inputs to generate videos, and also offers video editing and extension capabilities. It can accurately reproduce various details while maintaining stable character features, delivers highly realistic audiovisual stability, and is deeply adapted to core scenarios such as commercial advertising, film and TV production, and social media marketing.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.352,"source":"img_price_config","variant":{"quality":"standard","size":"1080p"}},{"billable":"generate","unit":"second","cost_usd":0.071,"source":"img_price_config","variant":{"quality":"standard","size":"480p"}},{"billable":"generate","unit":"second","cost_usd":0.704,"source":"img_price_config","variant":{"quality":"standard","size":"4k"}},{"billable":"generate","unit":"second","cost_usd":0.142,"source":"img_price_config","variant":{"quality":"standard","size":"720p"}},{"billable":"generate","unit":"second","cost_usd":0.704,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"video_reference","unit":"second","cost_usd":0.423,"source":"img_price_config","variant":{"quality":"standard","size":"1080p"}},{"billable":"video_reference","unit":"second","cost_usd":0.078,"source":"img_price_config","variant":{"quality":"standard","size":"480p"}},{"billable":"video_reference","unit":"second","cost_usd":0.876,"source":"img_price_config","variant":{"quality":"standard","size":"4k"}},{"billable":"video_reference","unit":"second","cost_usd":0.171,"source":"img_price_config","variant":{"quality":"standard","size":"720p"}},{"billable":"video_reference","unit":"second","cost_usd":0.876,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text,image,video,audio","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-01-28","last_updated":"2026-01-28","output_modalities":"video","vendor":"bytedance","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"doubao-seedance-2-0-fast-260128","model_name":"Doubao Seedance 2.0 Fast 260128","developer_id":4,"desc":"Seedance 2.0 fast is a next-generation multimodal video-creation model launched by the Doubao large-model team; it inherits the core features and advantages of Seedance 2.0 and generates content faster.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.055,"source":"img_price_config","variant":{"quality":"standard","size":"480p"}},{"billable":"generate","unit":"second","cost_usd":0.113,"source":"img_price_config","variant":{"quality":"standard","size":"720p"}},{"billable":"generate","unit":"second","cost_usd":0.113,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"video_reference","unit":"second","cost_usd":0.124,"source":"img_price_config","variant":{"quality":"standard","size":"480p"}},{"billable":"video_reference","unit":"second","cost_usd":0.268,"source":"img_price_config","variant":{"quality":"standard","size":"720p"}},{"billable":"video_reference","unit":"second","cost_usd":0.268,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text,image,video,audio","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-01-28","last_updated":"2026-01-28","output_modalities":"video","vendor":"bytedance","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"doubao-seedance-2-0-mini-260615","model_name":"Doubao Seedance 2.0 Mini 260615","developer_id":4,"desc":"Seedance 2.0 mini is a next-generation, cost-effective video generation model launched to address broader video-generation needs. While maintaining competitive performance, it brings video-generation capabilities to lower barriers to entry, more frequent use, and more scalable/large-scale application scenarios.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.0344,"source":"img_price_config","variant":{"quality":"standard","size":"480p"}},{"billable":"generate","unit":"second","cost_usd":0.0706,"source":"img_price_config","variant":{"quality":"standard","size":"720p"}},{"billable":"generate","unit":"second","cost_usd":0.0706,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}},{"billable":"video_reference","unit":"second","cost_usd":0.0775,"source":"img_price_config","variant":{"quality":"standard","size":"480p"}},{"billable":"video_reference","unit":"second","cost_usd":0.1675,"source":"img_price_config","variant":{"quality":"standard","size":"720p"}},{"billable":"video_reference","unit":"second","cost_usd":0.1675,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text,image,video,audio","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-06-15","last_updated":"2026-06-15","output_modalities":"video","vendor":"bytedance","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"glm-5.1","model_name":"GLM 5.1","developer_id":5,"desc":"GLM-5.1 is Zhipu's latest flagship model, with greatly enhanced coding capabilities and significantly improved long-range task performance. It can continuously and autonomously work for up to 8 hours on a single task, completing the full closed loop from planning and execution to iterative optimization, delivering engineering-grade results.\nIn terms of general capability and coding ability, GLM-5.1's overall performance aligns with Claude Opus 4.6, and it demonstrates stronger sustained work capability in long-range autonomous execution, complex engineering optimization, and real-world development scenarios, making it an ideal foundation for building Autonomous Agents and long-horizon Coding Agents.","pricing":{"cache_read":0.183112,"input":0.845,"output":3.38},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"chat_completions,claude_api","max_output":131072,"context_length":200000,"release_date":"2026-04-07","last_updated":"2026-04-07","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"glm-image","model_name":"GLM Image","developer_id":5,"desc":"GLM-Image is Zhipu AI's new flagship image generation model. The model is trained entirely on domestic chips and adopts an original hybrid architecture combining \"autoregressive + diffusion decoder,\" balancing global instruction understanding with local detail depiction. It overcomes generation challenges in knowledge-intensive scenarios such as posters, PPTs, and popular science illustrations. This represents an important exploration towards the new generation of \"cognitive generation\" technology paradigms exemplified by Nano Banana Pro.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"image","cost_usd":0.015,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"image","vendor":"zhipu","open_weights":true,"schema_checked":true,"retire_stage":"active"},{"model_id":"gemma-4-26b-a4b-it","model_name":"Gemma 4 26B A4B It","developer_id":8,"desc":"A Mixture-of-Experts model that activates only 4B parameters per inference,delivering high-performance reasoning with a fraction of the memory cost - idealfor cost-efficient, high-throughput server deployments.","pricing":{"input":0.14,"output":0.39998},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"","input_modalities":"text,image,video","endpoints":"","max_output":131100,"context_length":262144,"release_date":"2026-04-02","last_updated":"2026-04-02","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","high"]}],"vendor":"google","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemma-4-31b-it","model_name":"Gemma 4 31B It","developer_id":8,"desc":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.","pricing":{"input":0.2,"output":0.4},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"","input_modalities":"text,image,video","endpoints":"","max_output":131100,"context_length":262144,"release_date":"2026-04-02","last_updated":"2026-04-02","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","high"]}],"vendor":"google","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"wan2.7-image","model_name":"Wan2.7 Image","developer_id":13,"desc":"Wanxiang 2.7 — image generation and editing: supports text-to-image, text-to-multi-image, image-to-multi-image, image editing, multi-image reference generation, and interactive editing, with stronger performance in text rendering, subject consistency, and following complex instructions.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"image","cost_usd":0.0282,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-05-29","last_updated":"2026-05-29","output_modalities":"image","vendor":"alibaba","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"wan2.7-image-pro","model_name":"Wan2.7 Image Pro","developer_id":13,"desc":"Wanxiang 2.7 — image generation and editing: supports text-to-image, text-to-multi-image, image-to-multi-image, image editing, multi-image reference generation, and interactive editing, with stronger performance in text rendering, subject consistency, and following complex instructions.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"image","cost_usd":0.0704,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-05-29","last_updated":"2026-05-29","output_modalities":"image","vendor":"alibaba","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"gpt-5.4","model_name":"GPT 5.4","developer_id":12,"desc":"GPT-5.4 is our frontier model for complex professional work.Reasoning.effort supports: none (default), low, medium, high and xhigh.","pricing":{"cache_read":0.25,"input":2.5,"output":15,"tiers":[{"cache_read":0.5,"input":5,"output":22.5,"tier":{"size":272000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":15,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":22.5,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,function_calling,structured_outputs,web,tools","input_modalities":"text,image,pdf","endpoints":"chat_completions,responses,claude_api","max_output":128000,"context_length":1050000,"release_date":"2026-03-05","last_updated":"2026-03-05","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"],"default":"medium"}],"interleaved":{"openai.responses":true},"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"cc-k2.6-code-preview","model_name":"CC K2.6 Code Preview","developer_id":15,"desc":"for claude code","pricing":{"cache_read":0.02,"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image,video","endpoints":"","max_output":0,"context_length":262144,"output_modalities":"text","interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"moonshot","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"claude-sonnet-4-6","model_name":"Claude Sonnet 4.6","developer_id":2,"desc":"Claude Sonnet 4.6 delivers frontier intelligence at scale—built for coding, agents, and enterprise workflows. Use cases include: Agents: Sonnet 4.6 excels at complex, multi-step tasks requiring sustained reasoning and adaptive decision-making—ideal for workflows where reliability and autonomy matter most. Coding: Sonnet 4.6 is built for iterative development work, handling complex codebases without losing quality as you guide it through building, refactoring, and debugging. It can compress multi-day projects into hours with the technical depth to deliver production-ready solutions. Enterprise workflows: Sonnet 4.6 powers agents that manage professional projects from start to finish, leveraging memory to maintain context across files with a step-change improvement in creating spreadsheets, slides, and docs. Financial analysis: Sonnet 4.6 connects the dots across regulatory filings, market reports, and internal data—enabling sophisticated modeling and proactive compliance. Cybersecurity: Sonnet 4.6 brings professional-grade analysis to security workflows, correlating logs, vulnerability databases, and threat intelligence for proactive threat detection and automated incident response. Computer use: Sonnet 4.6 delivers confident, consistent navigation with more human-like browsing—enabling better web QA, workflow automation, and advanced user experiences.","pricing":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":6,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":3.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":3.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.3,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":15,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":3,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,pdf","endpoints":"chat_completions,gemini_api,claude_api","max_output":128000,"context_length":1000000,"release_date":"2026-02-17","last_updated":"2026-02-17","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"],"default":"medium"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true},"vendor":"anthropic","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-xiaomi-mimo-v2.6-pro","model_name":"Coding Xiaomi Mimo V2.6 Pro","developer_id":31,"desc":"Only supports OpenAI-compatible formats.","pricing":{"cache_read":0.0016,"input":0.2,"output":0.4},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0016,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.4,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.005,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":1048576,"release_date":"2026-04-22","last_updated":"2026-04-22","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3.5-plus","model_name":"Qwen3.5 Plus","developer_id":13,"desc":"The Qwen 3.5 native vision-language Plus model is built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In multiple task evaluations, the 3.5 series has demonstrated outstanding performance comparable to current leading frontier models, with leapfrog improvements over the 3 series in both pure-text and multimodal capabilities. This model version is functionally equivalent to the snapshot model qwen3.5-plus-2026-02-15.","pricing":{"cache_read":0.01096,"cache_write":0.137,"input":0.1096,"output":0.6576,"tiers":[{"cache_read":0.0274,"cache_write":0.3425,"input":0.274,"output":1.644,"tier":{"size":128000,"type":"context"}},{"cache_read":0.0548,"cache_write":0.685,"input":0.548,"output":3.288,"tier":{"size":256000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.137,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":128000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.3425,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.685,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":1000000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.01096,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0274,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0548,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":1000000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.6576,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.644,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.288,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":1000000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.1096,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.274,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.548,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":1000000}},{"billable":"web_search_requests","unit":"request","cost_usd":0.000548,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,web,long_context,thinking","input_modalities":"text,image,video","endpoints":"","max_output":65536,"context_length":1000000,"release_date":"2026-02-16","last_updated":"2026-02-16","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"alibaba","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seed-2-0-lite-260428","model_name":"Doubao Seed 2.0 Lite 260428","developer_id":4,"desc":"Doubao  Coding model optimized for real-world programming environments that can reliably invoke tools in common IDEs such as Claude Code. The model is specially optimized for frontend capabilities and performs well with common frontend frameworks. The model supports Skills and can work with various custom skills.","pricing":{"cache_read":0.018082,"input":0.09041,"output":0.54246,"tiers":[{"cache_read":0.027123,"input":0.135616,"output":0.813696,"tier":{"size":32000,"type":"context"}},{"cache_read":0.054246,"input":0.271232,"output":1.627392,"tier":{"size":128000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.018082,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0271232,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0542464,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.54246,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.813696,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.627392,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":-1}},{"billable":"input_audio_tokens","unit":"million_tokens","cost_usd":1.35615,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"input_audio_tokens","unit":"million_tokens","cost_usd":2.03424,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"input_audio_tokens","unit":"million_tokens","cost_usd":4.06848,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.09041,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.135616,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.271232,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":-1}}],"has_zdr_provider":false,"types":"llm","features":"thinking,web,tools,function_calling,structured_outputs","input_modalities":"text,image,video,document,audio","endpoints":"","max_output":128000,"context_length":256000,"release_date":"2026-04-28","last_updated":"2026-04-28","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"],"default":"medium"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"bytedance","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seed-2-0-mini-260428","model_name":"Doubao Seed 2.0 Mini 260428","developer_id":4,"desc":"Doubao  Coding model optimized for real-world programming environments that can reliably invoke tools in common IDEs such as Claude Code. The model is specially optimized for frontend capabilities and performs well with common frontend frameworks. The model supports Skills and can work with various custom skills.","pricing":{"cache_read":0.006027,"input":0.030136,"output":0.30136,"tiers":[{"cache_read":0.012055,"input":0.060274,"output":0.60274,"tier":{"size":32000,"type":"context"}},{"cache_read":0.02411,"input":0.120548,"output":1.20548,"tier":{"size":128000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0060272,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0120548,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0241096,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.30136,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.60274,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.20548,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.030136,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.060274,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.120548,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}}],"has_zdr_provider":false,"types":"llm","features":"thinking,web,tools,function_calling,structured_outputs","input_modalities":"text,image,video,document,audio","endpoints":"","max_output":128000,"context_length":256000,"release_date":"2026-04-28","last_updated":"2026-04-28","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"],"default":"medium"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"bytedance","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-3.1-flash-image-preview","model_name":"Gemini 3.1 Flash Image Preview","developer_id":8,"desc":"gemini-3.1-flash-image-preview (Nano Banana 2) features professional-grade visual intelligence, lightning-fast efficiency, and realistic, grounded generative capabilities. This model serves as the high-efficiency counterpart to Gemini 3 Pro Image, optimized for speed and high-volume developer use cases.","pricing":{"cache_read":0.05,"input":0.5,"output":3},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.05,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_image_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_image_tokens","unit":"million_tokens","cost_usd":60,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"image_generation,llm","features":"thinking","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-02-26","last_updated":"2026-02-26","output_modalities":"image,text","reasoning":true,"schema_checked":false,"retire_stage":"deprecated","deprecated_at":"2026-09-02T00:00:00Z","successor_model":"gemini-3.1-flash-image"},{"model_id":"gemini-3.1-pro-preview","model_name":"Gemini 3.1 Pro Preview","developer_id":8,"desc":"Gemini 3.1 Pro Preview is designed to further optimize the performance and reliability of the Gemini 3 Pro series, offering improved reasoning capabilities, greater token efficiency, and a more robust, factually consistent user experience. It is optimized for software-engineering behaviors and usability, and is also suitable for agent workflows that require precise tool invocation and reliable multi-step execution, enabling stable operation across a variety of real-world scenarios.","pricing":{"cache_read":0.2,"input":2,"output":12,"tiers":[{"cache_read":0.4,"input":4,"output":18,"tier":{"size":200000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":4.5,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.4,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":12,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":18,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":4,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.014,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs,web,deepsearch,long_context","input_modalities":"text,image,video,audio,pdf","endpoints":"chat_completions,gemini_api,claude_api","max_output":65536,"context_length":1048576,"release_date":"2026-02-19","last_updated":"2026-02-19","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"],"default":"medium"}],"vendor":"google","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-3.1-pro-preview-customtools","model_name":"Gemini 3.1 Pro Preview Customtools","developer_id":8,"desc":"gemini-3.1-pro-preview-customtools\n\nFor users who build applications mixing bash and custom tools, the Gemini 3.1 Pro preview provides a separate endpoint accessible via the API call gemini-3.1-pro-preview-customtools. This endpoint is better at prioritizing your custom tools (for example, view_file or search_code).\n\nPlease note that while gemini-3.1-pro-preview-customtools is optimized for agent workflows that use custom tools and Bash, you may experience quality fluctuations in some use cases that cannot benefit from these tools.","pricing":{"cache_read":0.2,"input":2,"output":12,"tiers":[{"cache_read":0.4,"input":4,"output":18,"tier":{"size":200000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":4.5,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.4,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":12,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":18,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":4,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.014,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs,web,deepsearch,long_context","input_modalities":"text,image,video,audio,pdf","endpoints":"chat_completions,gemini_api,claude_api","max_output":65536,"context_length":1048576,"release_date":"2026-02-19","last_updated":"2026-02-19","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"],"default":"medium"}],"vendor":"google","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-3.1-pro-preview-search","model_name":"Gemini 3.1 Pro Preview Search","developer_id":8,"desc":"Gemini-3.1-pro-preview-search integrates Google's official search functionality; the search feature incurs an additional separate fee log directly incorporated into the scoring, but the log details are not displayed; this will be fixed in the future to show the details; it only supports OpenAI-compatible format calls and does not support the Gemini SDK; for the Gemini native SDK, please directly set the official search parameters.","pricing":{"cache_read":0.2,"input":2,"output":12,"tiers":[{"cache_read":0.4,"input":4,"output":18,"tier":{"size":200000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":4.5,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.4,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":12,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":18,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":4,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.014,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,web,deepsearch,tools,function_calling,structured_outputs,long_context","input_modalities":"text,image,video,audio,pdf","endpoints":"chat_completions","max_output":65536,"context_length":1048576,"release_date":"2026-02-19","last_updated":"2026-02-19","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"],"default":"medium"}],"vendor":"google","variant_of":"gemini-3.1-pro-preview","variant_kind":"mode-preset","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.4-mini","model_name":"GPT 5.4 Mini","developer_id":12,"desc":"GPT-5.4 mini is a faster, more efficient model that inherits the advantages of GPT-5.4 and is specifically optimized for high-volume workloads.","pricing":{"cache_read":0.075,"input":0.75,"output":4.5},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.075,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":4.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,web","input_modalities":"text,image","endpoints":"chat_completions,responses,claude_api","max_output":128000,"context_length":400000,"release_date":"2026-03-17","last_updated":"2026-03-17","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"],"default":"medium"}],"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.4-nano","model_name":"GPT 5.4 Nano","developer_id":12,"desc":"GPT-5.4 nano is designed for tasks where speed and cost are most important, such as classification, data extraction, ranking, and sub-agent scenarios.","pricing":{"cache_read":0.02,"input":0.2,"output":1.25},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.02,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,thinking,web","input_modalities":"text,image","endpoints":"","max_output":128000,"context_length":400000,"release_date":"2026-03-17","last_updated":"2026-03-17","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"],"default":"medium"}],"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.3-chat-latest","model_name":"GPT 5.3 Chat","developer_id":12,"desc":"GPT-5.3Chat refers to the GPT-5.3 snapshot currently used in ChatGPT and is optimized for conversational use cases. While GPT-5.2 is recommended for most API applications, GPT-5.3Chat is ideal for testing the latest improvements in chat-based interactions.","pricing":{"cache_read":0.175,"input":1.75,"output":14},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":16384,"context_length":128000,"release_date":"2026-03-03","last_updated":"2026-03-03","output_modalities":"text","tool_call":true,"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.3-codex","model_name":"GPT-5.3-Codex","developer_id":12,"desc":"GPT-5.3-Codex is optimized for agentic coding tasks in Codex or similar environments. GPT-5.3-Codex supports low, medium, high, and xhigh reasoning effort settings. If you want to learn more about prompting GPT-5.3-Codex, refer to our dedicated guide.","pricing":{"cache_read":0.175,"input":1.75,"output":14},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,function_calling,structured_outputs","input_modalities":"text,image,pdf","endpoints":"","max_output":128000,"context_length":400000,"release_date":"2026-02-05","last_updated":"2026-02-05","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"],"default":"medium"}],"interleaved":{"openai.responses":true},"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3.5-122b-a10b","model_name":"Qwen3.5 122B A10B","developer_id":13,"desc":"The Qwen 3.5 native vision-language Plus model is built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In multiple task evaluations, the 3.5 series has demonstrated outstanding performance comparable to current leading frontier models, with leapfrog improvements over the 3 series in both pure-text and multimodal capabilities. This model version is functionally equivalent to the snapshot model qwen3.5-plus-2026-02-15.","pricing":{"input":0.1126,"output":0.9008,"tiers":[{"input":0.2818,"output":2.2544,"tier":{"size":128000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.9008,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.2544,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.1126,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.2818,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"web_search_requests","unit":"request","cost_usd":0.000548,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,web,long_context,thinking","input_modalities":"text,image,video","endpoints":"","max_output":65536,"context_length":262144,"release_date":"2026-02-23","last_updated":"2026-02-23","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"alibaba","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3.5-27b","model_name":"Qwen3.5 27B","developer_id":13,"desc":"The Qwen 3.5 native vision-language Plus model is built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In multiple task evaluations, the 3.5 series has demonstrated outstanding performance comparable to current leading frontier models, with leapfrog improvements over the 3 series in both pure-text and multimodal capabilities. This model version is functionally equivalent to the snapshot model qwen3.5-plus-2026-02-15.","pricing":{"input":0.0846,"output":0.6768,"tiers":[{"input":0.2536,"output":2.0288,"tier":{"size":128000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.6768,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.0288,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.0846,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.2536,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"web_search_requests","unit":"request","cost_usd":0.000563,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,web,long_context,thinking","input_modalities":"text,image,video","endpoints":"","max_output":65536,"context_length":262144,"release_date":"2026-02-23","last_updated":"2026-02-23","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"alibaba","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3.5-35b-a3b","model_name":"Qwen3.5 35B A3B","developer_id":13,"desc":"The Qwen 3.5 native vision-language Plus model is built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In multiple task evaluations, the 3.5 series has demonstrated outstanding performance comparable to current leading frontier models, with leapfrog improvements over the 3 series in both pure-text and multimodal capabilities. This model version is functionally equivalent to the snapshot model qwen3.5-plus-2026-02-15.","pricing":{"input":0.0564,"output":0.4512,"tiers":[{"input":0.2254,"output":1.8032,"tier":{"size":128000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.4512,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.8032,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.0564,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.2254,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"web_search_requests","unit":"request","cost_usd":0.000563,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,web,long_context,thinking","input_modalities":"text,image,video","endpoints":"","max_output":65536,"context_length":262144,"release_date":"2026-02-23","last_updated":"2026-02-23","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"alibaba","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3.5-397b-a17b","model_name":"Qwen3.5 397B A17B","developer_id":13,"desc":"The Qwen 3.5 native vision-language Plus model is built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In multiple task evaluations, the 3.5 series has demonstrated outstanding performance comparable to current leading frontier models, with leapfrog improvements over the 3 series in both pure-text and multimodal capabilities. This model version is functionally equivalent to the snapshot model qwen3.5-plus-2026-02-15.","pricing":{"input":0.1644,"output":0.9864,"tiers":[{"input":0.411,"output":2.466,"tier":{"size":128000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.9864,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.466,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.1644,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.411,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"web_search_requests","unit":"request","cost_usd":0.000548,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,web,long_context,thinking","input_modalities":"text,image,video","endpoints":"","max_output":65536,"context_length":262144,"release_date":"2026-02-15","last_updated":"2026-02-15","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"alibaba","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3.5-flash","model_name":"Qwen3.5 Flash","developer_id":13,"desc":"The Qwen3.5 native vision-language Flash series models are designed with a hybrid architecture that integrates linear attention mechanisms and sparse mixture-of-experts models, achieving higher inference efficiency. Compared with the 3 series, the models deliver leapfrog improvements in both pure-text and multimodal performance; they respond quickly and combine inference speed with high performance.","pricing":{"cache_read":0.00282,"cache_write":0.03525,"input":0.0282,"output":0.282,"tiers":[{"cache_read":0.01126,"cache_write":0.14075,"input":0.1126,"output":1.126,"tier":{"size":128000,"type":"context"}},{"cache_read":0.0169,"cache_write":0.21125,"input":0.169,"output":1.69,"tier":{"size":256000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.03525,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":128000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.14075,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.21125,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":1000000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.00282,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.01126,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0169,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":1000000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.282,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.126,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.69,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":1000000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.0282,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.1126,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.169,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":1000000}},{"billable":"web_search_requests","unit":"request","cost_usd":0.000548,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,web,long_context,thinking","input_modalities":"text,image,video","endpoints":"","max_output":65536,"context_length":1000000,"release_date":"2026-02-23","last_updated":"2026-02-23","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"alibaba","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"claude-sonnet-4-6-think","model_name":"Claude Sonnet 4.6 Thinking","developer_id":2,"desc":"Claude sonnet 4.6 does not enable reasoning mode by default. To access its deep reasoning capabilities, users would typically need to call the native Claude API. To make this capability available through an OpenAI-compatible interface, we provide the claude-sonnet-4-6-think model, which has reasoning mode pre-enabled and a default 32k-token context window, allowing it to be called directly via the OpenAI unified API.\nClaude sonnet 4.5 Think is a reasoning-focused variant of Claude sonnet 4.6 designed for advanced tasks that require rigorous reasoning, complex decision-making, and long-chain analysis. Aside from its enhanced reasoning mechanism, all other capabilities remain consistent with the standard Claude sonnet 4.6 model, making it well suited for complex engineering problem decomposition, multi-stage planning, and logic-intensive analysis.","pricing":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":6,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":3.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":3.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.3,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":15,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":3,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,pdf","endpoints":"","max_output":128000,"context_length":1000000,"release_date":"2026-02-17","last_updated":"2026-02-17","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"],"default":"medium"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true},"vendor":"anthropic","variant_of":"claude-sonnet-4-6","variant_kind":"mode-preset","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-glm-5.1","model_name":"Coding GLM 5.1","developer_id":5,"desc":"Only supports OpenAI-compatible formats.","pricing":{"input":0.06,"output":0.22},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":131072,"context_length":200000,"release_date":"2026-04-11","last_updated":"2026-04-11","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-coder-next","model_name":"Qwen3 Coder Next","developer_id":13,"desc":"The Qwen3 series is a next-generation code-generation model with results close to Qwen3-Coder-Plus while offering superior performance. The model is optimized for repository-level understanding, supports multi-turn tool interactions, and improves compatibility with agentic coding tools.","pricing":{"input":0.137,"output":0.548,"tiers":[{"input":0.2054,"output":0.8216,"tier":{"size":32000,"type":"context"}},{"input":0.3424,"output":1.3696,"tier":{"size":128000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.548,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.8216,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.3696,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.137,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.2054,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.3424,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":65536,"context_length":262144,"release_date":"2026-02-03","last_updated":"2026-02-03","output_modalities":"text","tool_call":true,"vendor":"alibaba","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.4-high","model_name":"GPT 5.4 High","developer_id":12,"desc":"GPT-5.4 supports configurable reasoning effort only through the /responses endpoint. To make higher-intensity reasoning available directly via the /chat interface, GPT-5.4-High is provided as a reasoning-enhanced variant of GPT-5.4 with reasoning_effort preset to high. It is designed for tasks that require deeper analysis, stronger result consistency, and greater controllability. By applying more aggressive reasoning strategies and more effective use of extended context, the model delivers clearer and more reliable responses, making it well suited for complex agent workflows, long-chain decision-making, and reliability-critical advanced applications.","pricing":{"cache_read":0.25,"input":2.5,"output":15,"tiers":[{"cache_read":0.5,"input":5,"output":22.5,"tier":{"size":272000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":15,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":22.5,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,function_calling,web,structured_outputs,tools","input_modalities":"text,image,pdf","endpoints":"","max_output":128000,"context_length":1050000,"output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"],"default":"medium"}],"interleaved":{"openai.responses":true},"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.4-low","model_name":"GPT 5.4 Low","developer_id":12,"desc":"GPT-5.4 supports configuring reasoning strength only through the /responses endpoint. To make lower-overhead reasoning available directly in the /chat endpoint, the GPT-5.4-Low model is provided. This model is based on GPT-5.4 with reasoning_effort preset to low. This model is designed for use cases that are sensitive to response latency and cost. By adopting a lighter reasoning strategy, it delivers stable responses with lower latency and higher throughput. It is well suited for high-concurrency conversations, real-time interactions, basic Q\u0026A, and scenarios where deep reasoning is not required.","pricing":{"cache_read":0.25,"input":2.5,"output":15,"tiers":[{"cache_read":0.5,"input":5,"output":22.5,"tier":{"size":272000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":15,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":22.5,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,function_calling,web,structured_outputs,tools","input_modalities":"text,image,pdf","endpoints":"","max_output":128000,"context_length":1050000,"output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"],"default":"medium"}],"interleaved":{"openai.responses":true},"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.4-pro","model_name":"GPT 5.4 Pro","developer_id":12,"desc":"Please note: this model is extremely expensive and very slow. If a request fails due to network issues, you may still be charged heavily; we cannot refund charges incurred by requests to this model.\nGPT-5.4 pro is available in the Responses API only to enable support for multi-turn model interactions before responding to API requests, and other advanced API features in the future. Since GPT-5.4 pro is designed to tackle tough problems, some requests may take several minutes to finish. To avoid timeout, please set a longer timeout duration. It is recommended to use this under good network conditions.","pricing":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"size":272000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":180,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":270,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":30,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":272000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":60,"source":"billing_config","tier":{"name":"tier2","min_tokens":272001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,web,tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":128000,"context_length":1050000,"release_date":"2026-03-05","last_updated":"2026-03-05","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"],"default":"medium"}],"interleaved":{"openai.responses":true},"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seed-2-0-pro","model_name":"Doubao Seed 2.0 Pro","developer_id":4,"desc":"Doubao flagship all-purpose general model, targeting complex reasoning and long-chain task execution scenarios in the Agent era. It emphasizes multimodal understanding, long-context reasoning, structured generation, and tool-augmented execution. It excels at handling complex instructions and multi-constraint execution, reliably addressing multi-step complex planning, intricate image-text reasoning, video content understanding, and high-difficulty analysis scenarios.","pricing":{"cache_read":0.09916,"input":0.4958,"output":2.479,"tiers":[{"cache_read":0.14872,"input":0.7436,"output":3.718,"tier":{"size":32000,"type":"context"}},{"cache_read":0.29744,"input":1.4872,"output":7.436,"tier":{"size":128000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.09916,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.14872,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.29744,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.479,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.718,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":7.436,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.4958,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.7436,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.4872,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}}],"has_zdr_provider":false,"types":"llm","features":"thinking,web,tools,function_calling,structured_outputs","input_modalities":"text,image,video,document","endpoints":"","max_output":128000,"context_length":256000,"release_date":"2026-02-14","last_updated":"2026-02-14","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"],"default":"medium"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"bytedance","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"glm-5v-turbo","model_name":"GLM 5 Vision Turbo","developer_id":5,"desc":"GLM-5V-Turbo is Zhipu's first multimodal coding foundation model, built for visual programming tasks. It can natively handle multimodal inputs such as images, videos, and text, and is adept at long-horizon planning, complex programming, and action execution; deeply adapted to Agent workflows, it can collaborate closely with agents like Claude Code and OpenClaw to complete the full closed loop of \"understand the environment → plan actions → execute tasks.\"","pricing":{"cache_read":0.169008,"input":0.7042,"output":3.09848,"tiers":[{"cache_read":0.253402,"input":0.986,"output":3.662004,"tier":{"size":32000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.169008,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.253402,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.09848,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.662004,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.7042,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.986,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}}],"has_zdr_provider":true,"types":"llm","features":"","input_modalities":"text,image,video,document","endpoints":"","max_output":131072,"context_length":200000,"release_date":"2026-04-01","last_updated":"2026-04-01","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"claude-opus-4-6","model_name":"Claude Opus 4.6","developer_id":2,"desc":"Claude Opus 4.6 is Anthropic’s latest state-of-the-art reasoning model. It features an adaptive “thinking” mode that dynamically decides when to think and how much to think. At the default effort level (high), Claude will almost always engage in thinking. At lower effort levels, it may skip thinking for simple problems.\n ⚠️ The minimum cache token for claude-opus-4-6 has been increased from 1,024 to 4,096 tokens.","pricing":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":6.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":6.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,pdf","endpoints":"","max_output":128000,"context_length":1000000,"release_date":"2026-02-05","last_updated":"2026-02-05","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"],"default":"medium"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true},"vendor":"anthropic","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-glm-5.1-free","model_name":"Coding GLM 5.1 (free)","developer_id":5,"desc":"coding-glm-5.1-free is the open and free version of coding-glm-5.1.  To maintain reliable service, each account is limited to 5 requests per minute, 100 requests per day, and 1 million tokens per day.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":131072,"context_length":200000,"release_date":"2026-04-11","last_updated":"2026-04-11","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","variant_of":"coding-glm-5.1","variant_kind":"pricing-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-minimax-m2.7-free","model_name":"Coding MiniMax M2.7 (free)","developer_id":18,"desc":"coding-minimax-m2.7-free is a free and open version offered by AIHubMix specifically for MiniMax users.  To maintain reliable service, each account is limited to 5 requests per minute, 100 requests per day, and 1 million tokens per day.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":204800,"context_length":204800,"release_date":"2026-03-18","last_updated":"2026-03-18","output_modalities":"text","reasoning":true,"tool_call":true,"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"minimax","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"minimax-m2.7","model_name":"MiniMax M2.7","developer_id":18,"desc":"MiniMax M2.7 can autonomously build complex Agent Harnesses and, leveraging capabilities such as Agent Teams, complex Skills, and the Tool Search tool, complete highly complex productivity tasks.","pricing":{"cache_read":0.05916,"input":0.2958,"output":1.1832},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":204800,"context_length":204800,"release_date":"2026-03-18","last_updated":"2026-03-18","output_modalities":"text","reasoning":true,"tool_call":true,"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"minimax","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seed-2-0-code-preview","model_name":"Doubao Seed 2.0 Code Preview","developer_id":4,"desc":"The Doubao 2.0 series is a coding model optimized for real programming environments, capable of reliably invoking tools in common IDEs such as Claude Code. The model is specially optimized for frontend capabilities and performs well with common frontend frameworks. The model supports using Skills and can work with various custom skills.","pricing":{"cache_read":0.09644,"input":0.4822,"output":2.411,"tiers":[{"cache_read":0.144656,"input":0.72328,"output":3.6164,"tier":{"size":32000,"type":"context"}},{"cache_read":0.28932,"input":1.4466,"output":7.233,"tier":{"size":128000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.09644,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.144656,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.28932,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.411,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.6164,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":7.233,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.4822,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.72328,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.4466,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}}],"has_zdr_provider":false,"types":"llm","features":"thinking,web,tools,function_calling","input_modalities":"text,image,video,document","endpoints":"","max_output":128000,"context_length":256000,"release_date":"2026-02-14","last_updated":"2026-02-14","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"],"default":"medium"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"bytedance","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seed-2-0-lite-260215","model_name":"Doubao Seed 2.0 Lite 260215","developer_id":4,"desc":"Doubao  Coding model optimized for real-world programming environments that can reliably invoke tools in common IDEs such as Claude Code. The model is specially optimized for frontend capabilities and performs well with common frontend frameworks. The model supports Skills and can work with various custom skills.","pricing":{"cache_read":0.018082,"input":0.09041,"output":0.54246,"tiers":[{"cache_read":0.027123,"input":0.135616,"output":0.813696,"tier":{"size":32000,"type":"context"}},{"cache_read":0.054246,"input":0.271232,"output":1.627392,"tier":{"size":128000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.018082,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0271232,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0542464,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.54246,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.813696,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.627392,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.09041,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.135616,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.271232,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}}],"has_zdr_provider":false,"types":"llm","features":"thinking,web,tools,function_calling,structured_outputs","input_modalities":"text,image,video,document","endpoints":"","max_output":128000,"context_length":256000,"release_date":"2026-02-15","last_updated":"2026-02-15","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"],"default":"medium"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"bytedance","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-3-flash-preview","model_name":"Gemini 3 Flash Preview","developer_id":8,"desc":"gemini-3-flash-preview is Google's latest released, most balanced model, excelling in speed, scale, and cutting-edge intelligence.","pricing":{"cache_read":0.05,"input":0.5,"output":3},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":1,"source":"billing_config"},{"billable":"cached_audio_tokens","unit":"million_tokens","cost_usd":0.1,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.05,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_audio_tokens","unit":"million_tokens","cost_usd":1,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.014,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,web,tools,function_calling,structured_outputs","input_modalities":"text,image,video,audio,pdf","endpoints":"","max_output":65536,"context_length":1048576,"release_date":"2025-12-17","last_updated":"2025-12-17","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"],"default":"medium"}],"vendor":"google","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-3-flash-preview-search","model_name":"Gemini 3 Flash Preview Search","developer_id":8,"desc":"Gemini-3-flash-preview-search integrates Google's official search functionality; the search feature incurs an additional separate fee log directly incorporated into the scoring, but the log details are not displayed; this will be fixed in the future to show the details; it only supports OpenAI-compatible format calls and does not support the Gemini SDK; for the Gemini native SDK, please directly set the official search parameters.","pricing":{"cache_read":0.05,"input":0.5,"output":3},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":1,"source":"billing_config"},{"billable":"cached_audio_tokens","unit":"million_tokens","cost_usd":0.1,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.05,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_audio_tokens","unit":"million_tokens","cost_usd":1,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.014,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,web,tools,function_calling,structured_outputs","input_modalities":"text,image,video,audio,pdf","endpoints":"","max_output":65536,"context_length":1048576,"release_date":"2025-12-17","last_updated":"2025-12-17","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"],"default":"medium"}],"vendor":"google","variant_of":"gemini-3-flash-preview","variant_kind":"mode-preset","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"glm-5-turbo","model_name":"GLM 5 Turbo","developer_id":5,"desc":"GLM-5-Turbo is a foundational model deeply optimized for the OpenClaw scenario. From the training stage it has been specifically optimized for the core requirements of OpenClaw tasks, enhancing key capabilities such as tool invocation, instruction following, scheduled and persistent tasks, and long-chain execution.","pricing":{"cache_read":0.24,"input":1.2,"output":3.9996},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":131072,"context_length":204800,"release_date":"2026-03-16","last_updated":"2026-03-16","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"claude-opus-4-6-think","model_name":"Claude Opus 4.6 Thinking","developer_id":2,"desc":"Claude Opus 4.6 does not enable reasoning mode by default. To access its deep reasoning capabilities, users would typically need to call the native Claude API. To make this capability available through an OpenAI-compatible interface, we provide the claude-opus-4-6-think model, which has reasoning mode pre-enabled and a default 32k-token context window, allowing it to be called directly via the OpenAI unified API.\nClaude Opus 4.5 Think is a reasoning-focused variant of Claude Opus 4.6 designed for advanced tasks that require rigorous reasoning, complex decision-making, and long-chain analysis. Aside from its enhanced reasoning mechanism, all other capabilities remain consistent with the standard Claude Opus 4.6 model, making it well suited for complex engineering problem decomposition, multi-stage planning, and logic-intensive analysis.","pricing":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":6.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":6.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,pdf","endpoints":"","max_output":128000,"context_length":1000000,"release_date":"2026-02-05","last_updated":"2026-02-05","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"],"default":"medium"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true},"vendor":"anthropic","variant_of":"claude-opus-4-6","variant_kind":"mode-preset","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-glm-5-free","model_name":"Coding GLM 5 (free)","developer_id":5,"desc":"coding-glm-5-free is the open and free version of coding-glm-5. To ensure stable service performance, usage limits are in place: up to 5 requests per minute, 100 requests per day, and a daily token allowance of 1 million.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":131072,"context_length":200000,"release_date":"2026-02-11","last_updated":"2026-02-11","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-glm-5-turbo-free","model_name":"Coding GLM 5 Turbo (free)","developer_id":5,"desc":"coding-glm-5-turbo-free is the open and free version of coding-glm-5-turbo. To ensure stable service performance, usage limits are in place: up to 5 requests per minute, 100 requests per day, and a daily token allowance of 1 million.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":131072,"context_length":204800,"release_date":"2026-03-16","last_updated":"2026-03-16","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-minimax-m2.5-free","model_name":"Coding MiniMax M2.5 (free)","developer_id":18,"desc":"coding-minimax-m2.5-free is a free and open version offered by AIHubMix specifically for MiniMax users. To maintain stable service operations, the following usage limits apply: a maximum of 5 requests per minute, 100 total requests per day, and a daily quota of 1 million tokens.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":204800,"context_length":204800,"release_date":"2026-02-12","last_updated":"2026-02-12","output_modalities":"text","reasoning":true,"tool_call":true,"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"minimax","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"cc-glm-5.1","model_name":"CC GLM 5.1","developer_id":5,"desc":"Supports Claude native interface, can be directly requested in Claude Code.","pricing":{"input":0.06,"output":0.22},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":131072,"context_length":200000,"output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"claude-opus-4-5","model_name":"Claude Opus 4.5","developer_id":2,"desc":"Claude Opus 4.5 is Anthropic’s latest frontier reasoning model, optimized for complex engineering, agentic workflows, and long-horizon computer use. It features strong multimodal capabilities, improved resistance to prompt injection, and a new Verbosity parameter to control token efficiency. With advanced tool use, extended context, and multi-agent support, Opus 4.5 excels in autonomous research, debugging, planning, and spreadsheet/browser operations.\n⚠️ The minimum cache token for claude-opus-4-5 has been increased from 1,024 to 4,096 tokens.","pricing":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":6.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":6.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,pdf","endpoints":"","max_output":64000,"context_length":200000,"release_date":"2025-11-24","last_updated":"2025-11-24","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"],"default":"medium"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true},"vendor":"anthropic","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"claude-opus-4-5-think","model_name":"Claude Opus 4.5 Thinking","developer_id":2,"desc":"Claude Opus 4.5 does not enable reasoning mode by default. To access its deep reasoning capabilities, users would typically need to call the native Claude API. To make this capability available through an OpenAI-compatible interface, we provide the claude-opus-4-5-think model, which has reasoning mode pre-enabled and a default 32k-token context window, allowing it to be called directly via the OpenAI unified API.\nClaude Opus 4.5 Think is a reasoning-focused variant of Claude Opus 4.5 designed for advanced tasks that require rigorous reasoning, complex decision-making, and long-chain analysis. Aside from its enhanced reasoning mechanism, all other capabilities remain consistent with the standard Claude Opus 4.5 model, making it well suited for complex engineering problem decomposition, multi-stage planning, and logic-intensive analysis.","pricing":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":6.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":6.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,pdf","endpoints":"","max_output":64000,"context_length":200000,"release_date":"2025-11-24","last_updated":"2025-11-24","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"],"default":"medium"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true},"vendor":"anthropic","variant_of":"claude-opus-4-5","variant_kind":"mode-preset","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"xing4.0-29b-a4b-free","model_name":"Xing4.0 29B A4B (free)","developer_id":51,"desc":"Xing4.0-29B-A4B is an open-weight mixture-of-experts (MoE) language model developed by Xingchen Agi and China Telecom's AI team (TeleAI) as the successor to the TeleChat series. It features a total of 29 billion parameters, with 4 billion active per token, to deliver highly efficient performance. With an expansive context length of 262,144 tokens, this model is well-suited for processing long-form documents and complex tasks.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":262144,"output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"xingchen","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"embed-v-4-0","model_name":"Embed V 4.0","developer_id":6,"desc":"Cohere’s Embed 4 is a multilingual multimodal embedding model. It is capable of transforming different modalities such as images, texts, and interleaved images and texts into a single vector representation. Embed 4 offers state-of-the-art performance across all modalities (texts, images, interleaved texts and image) and in both English and multilingual settings. Embed 4 supports a 128k context length and an images can have a maximum of 2MM pixels.","pricing":{"input":0.12,"output":0},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_image_tokens","unit":"million_tokens","cost_usd":0.4704,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.12,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":128000,"schema_checked":false,"retire_stage":"active"},{"model_id":"ernie-image-turbo","model_name":"ERNIE Image Turbo","developer_id":25,"desc":"The Ernie-image-Turbo model is an 8-step distilled version of the Ernie-image model, also with 8 billion parameters, offering a 6x speedup compared to pre-distillation, and is suitable for low-latency, local/on-device scenarios.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"image","cost_usd":0.0155,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"image","schema_checked":false,"retire_stage":"active"},{"model_id":"flint-v1.0-free","model_name":"Flint V1.0 (free)","developer_id":52,"desc":"Flint is an open-weight mixture-of-experts model developed by Recursive for coding agents, featuring an expansive context length of 262,144 tokens. Built by Recursive's autoresearch system Eureka Machine, it operates with approximately 2.5B active parameters out of 40B total parameters. This model offers an efficient and powerful solution tailored for complex development workflows and agentic tasks.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"cohere-command-a","model_name":"Cohere Command A","developer_id":6,"desc":"Command A is Cohere most performant model to date, excelling at tool use, agents, retrieval augmented generation (RAG), and multilingual use cases. Command A has a context length of 256K, only requires two GPUs to run, and has 150% higher throughput compared to Command R+ 08-2024.","pricing":{"input":2.5,"output":10},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":8000,"context_length":256000,"release_date":"2025-03-13","last_updated":"2025-03-13","output_modalities":"text","vendor":"cohere","variant_of":"command-a-03-2025","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"cc-minimax-m3","model_name":"CC MiniMax M3","developer_id":18,"desc":"For Claude Code only","pricing":{"input":0.1,"output":0.1},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text,image,video","endpoints":"","max_output":524288,"context_length":1000000,"output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"minimax","variant_of":"minimax-m3","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-minimax-m3","model_name":"Coding MiniMax M3","developer_id":18,"desc":"","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,video","endpoints":"","max_output":524288,"context_length":1000000,"release_date":"2026-06-01","last_updated":"2026-06-01","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"minimax","variant_of":"minimax-m3","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-glm-5","model_name":"Coding GLM 5","developer_id":5,"desc":"Only supports OpenAI-compatible formats.","pricing":{"input":0.06,"output":0.22},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":131072,"context_length":200000,"release_date":"2026-02-12","last_updated":"2026-02-12","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","variant_of":"glm-5","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-glm-5-turbo","model_name":"Coding GLM 5 Turbo","developer_id":5,"desc":"Only supports OpenAI-compatible formats.","pricing":{"input":0.06,"output":0.22},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":131072,"context_length":204800,"release_date":"2026-03-16","last_updated":"2026-03-16","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","variant_of":"glm-5-turbo","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"glm-4.7","model_name":"GLM 4.7","developer_id":5,"desc":"GLM-4.7 is Zhiyuan's latest flagship model. GLM-4.7 enhances coding capabilities, long-range task planning, and tool collaboration for Agentic Coding scenarios, achieving leading performance among open-source models on several current public benchmarks. It features improved general capabilities, with responses that are more concise and natural, and writing that is more immersive. When executing complex agent tasks and tool usage, it follows instructions more strictly, with further improvements in the frontend aesthetics of Artifacts and Agentic Coding as well as the efficiency of completing long-range tasks.","pricing":{"cache_read":0.054795,"input":0.273974,"output":1.095896,"tiers":[{"cache_read":0.109589,"input":0.547946,"output":2.191784,"tier":{"size":32000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0547948,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000,"max_output_tokens":200}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0821916,"source":"billing_config","tier":{"name":"tier2","min_tokens":0,"max_tokens":32000,"min_output_tokens":200,"max_output_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.1095892,"source":"billing_config","tier":{"name":"tier3","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.095896,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000,"max_output_tokens":200}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.917804136986,"source":"billing_config","tier":{"name":"tier2","min_tokens":0,"max_tokens":32000,"min_output_tokens":200,"max_output_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.191784,"source":"billing_config","tier":{"name":"tier3","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.273974,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000,"max_output_tokens":200}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.410958,"source":"billing_config","tier":{"name":"tier2","min_tokens":0,"max_tokens":32000,"min_output_tokens":200,"max_output_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.547946,"source":"billing_config","tier":{"name":"tier3","min_tokens":32001,"max_tokens":128000}}],"has_zdr_provider":true,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":131072,"context_length":200000,"release_date":"2025-12-22","last_updated":"2025-12-22","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"glm-4.7-flash-free","model_name":"GLM 4.7 Flash (free)","developer_id":5,"desc":"The glm-4.7-flash free model has usage restrictions to ensure stable service operation: a maximum of 5 requests per minute, no more than 500 requests per day, and a daily usage quota of 1 million tokens.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,structured_outputs,function_calling","input_modalities":"text","endpoints":"","max_output":131072,"context_length":200000,"release_date":"2026-01-19","last_updated":"2026-01-19","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-glm-4.7-free","model_name":"Coding GLM 4.7 (free)","developer_id":5,"desc":"coding-glm-4.7-free is the open and free version of coding-glm-4.7. To ensure stable service performance, usage limits are in place: up to 5 requests per minute, 500 requests per day, and a daily token allowance of 1 million.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":131072,"context_length":200000,"release_date":"2025-12-22","last_updated":"2025-12-22","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","variant_of":"glm-4.7","variant_kind":"pricing-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seedance-1-5-pro-251215","model_name":"Doubao Seedance 1.5 Pro 251215","developer_id":4,"desc":"The Doubao video generation model Seedance 1.5 Pro, as a world-leading video generation model, can produce video content with high-precision audio–visual synchronization. It supports multi-person, multi-language dialogue and comprehensively covers ambient sounds, action sounds, synthesized sounds, musical instrument sounds, background sounds, and human voices. It supports start-and-end frames to achieve film-level narrative effects, meeting the advanced creative needs of film, animated series, e-commerce, and advertising.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.11,"source":"img_price_config","variant":{"quality":"standard","size":"1080p"}},{"billable":"generate","unit":"second","cost_usd":0.0225,"source":"img_price_config","variant":{"quality":"standard","size":"480p"}},{"billable":"generate","unit":"second","cost_usd":0.0487,"source":"img_price_config","variant":{"quality":"standard","size":"720p"}},{"billable":"generate","unit":"second","cost_usd":0.0487,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"image,text","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-12-15","last_updated":"2025-12-15","output_modalities":"video","schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seedance-1-0-pro-250528","model_name":"Doubao Seedance 1.0 Pro 250528","developer_id":4,"desc":"Seedance 1.0 Pro is a foundational video-generation model that supports multi-shot storytelling and excels across multiple dimensions. It has made breakthroughs in semantic understanding and instruction-following, enabling the generation of 1080P HD videos with smooth motion, rich detail, diverse styles, and cinematic aesthetics.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.102,"source":"img_price_config","variant":{"quality":"standard","size":"1080p"}},{"billable":"generate","unit":"second","cost_usd":0.021,"source":"img_price_config","variant":{"quality":"standard","size":"480p"}},{"billable":"generate","unit":"second","cost_usd":0.044,"source":"img_price_config","variant":{"quality":"standard","size":"720p"}},{"billable":"generate","unit":"second","cost_usd":0.044,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"image,text","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-05-28","last_updated":"2025-05-28","output_modalities":"video","schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seedance-1-0-pro-fast-251015","model_name":"Doubao Seedance 1.0 Pro Fast 251015","developer_id":4,"desc":"Seedance 1.0 Pro Fast is a comprehensive model that delivers rock-bottom prices and peak performance, striking an outstanding balance among video generation quality, speed, and cost. It inherits the core advantages of Seedance 1.0 Pro while increasing generation speed and offering more competitive pricing, providing creators with dual optimization of efficiency and cost.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.0298,"source":"img_price_config","variant":{"quality":"standard","size":"1080p"}},{"billable":"generate","unit":"second","cost_usd":0.0062,"source":"img_price_config","variant":{"quality":"standard","size":"480p"}},{"billable":"generate","unit":"second","cost_usd":0.0123,"source":"img_price_config","variant":{"quality":"standard","size":"720p"}},{"billable":"generate","unit":"second","cost_usd":0.0123,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"image,text","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-10-15","last_updated":"2025-10-15","output_modalities":"video","schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-3-pro-image-preview","model_name":"Gemini 3 Pro Image Preview","developer_id":8,"desc":"Gemini-3-Pro-Image-Preview (Nano Banana Pro) is a high-performance image generation and editing model built on Gemini 3 Pro. It delivers enhanced multimodal understanding and real-world semantic reasoning, enabling fast creation of well-structured visual content such as infographics, product sketches, and multi-subject scenes. It can also leverage real-time knowledge through Search grounding. The model excels in text rendering, consistent multi-image blending, and identity preservation, while offering fine-grained creative controls like localized edits, lighting and focus adjustments, camera transformations, and flexible aspect ratios. It’s ideal for rapid design, concept previews, product visualization, and everyday image generation workflows.","pricing":{"cache_read":0.2,"input":2,"output":12},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":12,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_image_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_image_tokens","unit":"million_tokens","cost_usd":120,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"image_generation,llm","features":"thinking","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-11-20","last_updated":"2025-11-20","output_modalities":"image,text","reasoning":true,"schema_checked":false,"retire_stage":"deprecated","deprecated_at":"2026-09-02T00:00:00Z","successor_model":"gemini-3-pro-image"},{"model_id":"gemini-embedding-2","model_name":"Gemini Embedding 2","developer_id":8,"desc":"Google's first multimodal embedding model .","pricing":{"input":0.2,"output":0},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_audio_tokens","unit":"million_tokens","cost_usd":6.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_document_tokens","unit":"million_tokens","cost_usd":0.45,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_image_tokens","unit":"million_tokens","cost_usd":0.45,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_video_tokens","unit":"million_tokens","cost_usd":12,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"text,image,audio,video","endpoints":"","max_output":0,"context_length":0,"release_date":"2026-04-22","last_updated":"2026-04-22","schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.2-codex","model_name":"GPT-5.2-Codex","developer_id":12,"desc":"GPT-5.2-Codex is an upgraded version of GPT-5.2, optimized for agentic coding tasks in Codex and similar execution environments. The model is specifically enhanced for code generation, modification, refactoring, and automated execution workflows, enabling more efficient participation in multi-step, tool-driven programming processes. GPT-5.2-Codex supports low, medium, high, and xhigh reasoning effort settings, allowing flexible trade-offs between latency, reasoning depth, and token usage depending on task complexity.","pricing":{"cache_read":0.175,"input":1.75,"output":14},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,function_calling,structured_outputs","input_modalities":"text,image,pdf","endpoints":"","max_output":128000,"context_length":400000,"release_date":"2025-12-11","last_updated":"2025-12-11","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"],"default":"medium"}],"interleaved":{"openai.responses":true},"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"deepinfra-gemma-4-26b-a4b-it","model_name":"Deepinfra Gemma 4 26B A4B It","developer_id":8,"desc":"A Mixture-of-Experts model that activates only 4B parameters per inference,delivering high-performance reasoning with a fraction of the memory cost - idealfor cost-efficient, high-throughput server deployments.","pricing":{"cache_read":0.011,"input":0.088,"output":0.385},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":131100,"context_length":262100,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seedream-5.0-lite","model_name":"Doubao Seedream 5.0 Lite","developer_id":4,"desc":"Doubao-Seedream-5.0-lite is the latest image-creation model released by ByteDance. For the first time, the model includes an online retrieval capability, allowing it to integrate real-time web information and improve the timeliness of generated images. At the same time, the model’s intelligence has been further upgraded, enabling it to accurately parse complex instructions and visual content. In addition, the model has been enhanced in terms of breadth of world knowledge, reference consistency, and generation quality in professional scenarios, better meeting enterprise-level visual-creation needs.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"image","cost_usd":0.034,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"image","schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-image-1.5","model_name":"GPT Image 1.5","developer_id":12,"desc":"GPT Image 1.5 is a new image generation model powered by OpenAI’s flagship visual capabilities, comprehensively upgraded for high-quality creative and production workflows. It delivers significant improvements in instruction understanding, fine-grained image editing, and detail preservation, while achieving up to 4× faster generation compared to previous versions — reducing latency without compromising quality.\n\nGPT Image 1.5 is well suited for image generation, precise visual editing, and professional content creation, balancing performance with efficiency.","pricing":{"input":5,"output":10},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_image_tokens","unit":"million_tokens","cost_usd":8,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_image_tokens","unit":"million_tokens","cost_usd":32,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-11-25","last_updated":"2025-11-25","output_modalities":"image","vendor":"openai","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"doubao-seed-2-1-pro-260628","model_name":"Doubao Seed 2.1 Pro 260628","developer_id":4,"desc":"A new generation of large models moving toward production-grade intelligence, comprehensively upgrading coding, agent, and multimodal capabilities with stronger autonomous planning, long-horizon execution, and dynamic recovery abilities to handle real, complex enterprise tasks.","pricing":{"cache_read":0.1859,"input":0.9295,"output":4.6475},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.1859,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":4.6475,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.9295,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"llm","features":"thinking,web,tools,function_calling,structured_outputs","input_modalities":"text,image,video","endpoints":"","max_output":256000,"context_length":256000,"output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.2","model_name":"GPT 5.2","developer_id":12,"desc":"GPT-5.2 is an advanced general-purpose model that improves on GPT-5.1 with more reliable, flexible, and user-friendly interactions. It delivers clearer responses, stronger instruction-following, and adaptive reasoning that scales from simple requests to complex, multi-step tasks. With enhanced control over tone and structure and support for extended context, GPT-5.2 is well suited for agent workflows, analysis, coding, and cross-domain applications.","pricing":{"cache_read":0.175,"input":1.75,"output":14},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.175,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":14,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,function_calling,structured_outputs,web,tools","input_modalities":"text,image,pdf","endpoints":"","max_output":128000,"context_length":400000,"release_date":"2025-12-11","last_updated":"2025-12-11","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"],"default":"medium"}],"interleaved":{"openai.responses":true},"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.2-chat-latest","model_name":"GPT 5.2 Chat","developer_id":12,"desc":"GPT-5.2Chat refers to the GPT-5.2 snapshot currently used in ChatGPT and is optimized for conversational use cases. While GPT-5.2 is recommended for most API applications, GPT-5.2Chat is ideal for testing the latest improvements in chat-based interactions.","pricing":{"cache_read":0.175,"input":1.75,"output":14},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":16384,"context_length":128000,"release_date":"2025-12-11","last_updated":"2025-12-11","output_modalities":"text","tool_call":true,"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.2-high","model_name":"GPT 5.2 High","developer_id":12,"desc":"GPT-5.2 supports configurable reasoning effort only through the /responses endpoint. To make higher-intensity reasoning available directly via the /chat interface, GPT-5.2-High is provided as a reasoning-enhanced variant of GPT-5.2 with reasoning_effort preset to high. It is designed for tasks that require deeper analysis, stronger result consistency, and greater controllability. By applying more aggressive reasoning strategies and more effective use of extended context, the model delivers clearer and more reliable responses, making it well suited for complex agent workflows, long-chain decision-making, and reliability-critical advanced applications.","pricing":{"cache_read":0.175,"input":1.75,"output":14},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.175,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":14,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,function_calling,web,structured_outputs,tools","input_modalities":"text,image,pdf","endpoints":"","max_output":128000,"context_length":400000,"output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"],"default":"high"}],"interleaved":{"openai.responses":true},"vendor":"openai","variant_of":"gpt-5.2","variant_kind":"mode-preset","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.2-low","model_name":"GPT 5.2 Low","developer_id":12,"desc":"GPT-5.2 supports configuring reasoning strength only through the /responses endpoint. To make lower-overhead reasoning available directly in the /chat endpoint, the GPT-5.2-Low model is provided. This model is based on GPT-5.2 with reasoning_effort preset to low. This model is designed for use cases that are sensitive to response latency and cost. By adopting a lighter reasoning strategy, it delivers stable responses with lower latency and higher throughput. It is well suited for high-concurrency conversations, real-time interactions, basic Q\u0026A, and scenarios where deep reasoning is not required.","pricing":{"cache_read":0.175,"input":1.75,"output":14},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.175,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":14,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.75,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,function_calling,web,structured_outputs,tools","input_modalities":"text,image,pdf","endpoints":"","max_output":128000,"context_length":400000,"output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"],"default":"low"}],"interleaved":{"openai.responses":true},"vendor":"openai","variant_of":"gpt-5.2","variant_kind":"mode-preset","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.2-pro","model_name":"GPT 5.2 Pro","developer_id":12,"desc":"GPT-5.2 pro is available in the Responses API only to enable support for multi-turn model interactions before responding to API requests, and other advanced API features in the future. Since GPT-5.2 pro is designed to tackle tough problems, some requests may take several minutes to finish. To avoid timeout, please set a longer timeout duration. It is recommended to use this under good network conditions.","pricing":{"cache_read":2.1,"input":21,"output":168},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":2.1,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":168,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":21,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,web,tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":128000,"context_length":400000,"release_date":"2025-12-11","last_updated":"2025-12-11","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"],"default":"medium"}],"interleaved":{"openai.responses":true},"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.1","model_name":"GPT 5.1","developer_id":12,"desc":"GPT-5 is OpenAI’s most advanced language model, designed for complex tasks that require step-by-step reasoning, precise instruction following, and high reliability. It improves reasoning, code generation, and prompt understanding—including test-time routing and intent cues like “think hard about this”—while reducing hallucination and sycophancy.","pricing":{"cache_read":0.125,"input":1.25,"output":10},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,web,tools,deepsearch,function_calling,structured_outputs","input_modalities":"text,image,pdf","endpoints":"","max_output":128000,"context_length":400000,"release_date":"2025-11-13","last_updated":"2025-11-13","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"],"default":"medium"}],"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.1-codex-max","model_name":"GPT-5.1-Codex Max","developer_id":12,"desc":"GPT-5.1-Codex-Max is a frontier programming model built for the agent-driven era. Powered by an upgraded core reasoning architecture, it is specially trained for complex agentic tasks in software engineering, mathematics, and scientific research. It delivers faster performance, greater stability, and higher token efficiency across the entire development lifecycle, including code generation, refactoring, debugging, and engineering collaboration. With native support for multiple context windows and a built-in compaction mechanism, the model can coherently process millions of tokens within a single task.","pricing":{"cache_read":0.125,"input":1.25,"output":10},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"function_calling,structured_outputs,thinking","input_modalities":"text,image","endpoints":"","max_output":128000,"context_length":400000,"release_date":"2025-11-13","last_updated":"2025-11-13","output_modalities":"text","reasoning":true,"tool_call":true,"interleaved":{"openai.responses":true},"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.1-chat-latest","model_name":"GPT 5.1 Chat","developer_id":12,"desc":"GPT-5.1 Chat refers to the GPT-5.1 snapshot currently used in ChatGPT and is optimized for conversational use cases. While GPT-5.1 is recommended for most API applications, GPT-5.1 Chat is ideal for testing the latest improvements in chat-based interactions.","pricing":{"cache_read":0.125,"input":1.25,"output":10},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":16384,"context_length":128000,"release_date":"2025-11-13","last_updated":"2025-11-13","output_modalities":"text","tool_call":true,"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.1-codex","model_name":"GPT-5.1-Codex","developer_id":12,"desc":"GPT-5.1-Codex is a version of GPT-5 optimized for agentic coding tasks in Codex or similar environments. It's available in the Responses API only and the underlying model snapshot will be regularly updated. ","pricing":{"cache_read":0.125,"input":1.25,"output":10},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":128000,"context_length":400000,"release_date":"2025-11-13","last_updated":"2025-11-13","output_modalities":"text","reasoning":true,"tool_call":true,"interleaved":{"openai.responses":true},"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.1-codex-mini","model_name":"GPT-5.1-Codex Mini","developer_id":12,"desc":"GPT-5.1 Codex mini is a smaller, more cost-effective, less-capable version of GPT-5.1-Codex.","pricing":{"cache_read":0.025,"input":0.25,"output":2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":128000,"context_length":400000,"release_date":"2025-11-13","last_updated":"2025-11-13","output_modalities":"text","reasoning":true,"tool_call":true,"interleaved":{"openai.responses":true},"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"grok-4.20-multi-agent-0309","model_name":"Grok 4.20 Multi Agent 0309","developer_id":9,"desc":"Grok 4.20 is our newest flagship model with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently precise and truthful responses.","pricing":{"cache_read":0.2,"input":2,"output":6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs,long_context","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":1000000,"release_date":"2026-03-09","last_updated":"2026-03-09","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"],"default":"medium"}],"interleaved":{"openai.responses":true},"vendor":"xai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"mistral-large-3","model_name":"Mistral Large 3","developer_id":10,"desc":"Mistral Large 3 is a MoE model with 67.5B total parameters and 41B active parameters, supporting a 256K-token context window. Trained from scratch on 3,000 NVIDIA H200 GPUs, it is one of the strongest permissively licensed open-weight models available.\n\nDesigned for advanced reasoning and long-context understanding, Mistral Large 3 delivers performance on par with the best instruction-tuned open-weight models for general-purpose tasks, while also offering image understanding capabilities. Its multilingual strengths are particularly notable for non-English/Chinese languages, making it well-suited for global applications.\n\nTypical use cases include enterprise assistants, multilingual customer support, content generation and editing, data analysis over long documents, code assistance, and research workflows that require handling large corpora or complex instructions. With its MoE architecture, Mistral Large 3 balances strong performance with efficient inference, providing a versatile backbone for building reliable, production-grade AI systems.","pricing":{"input":0.5,"output":1.5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":131072,"context_length":256000,"release_date":"2024-11-01","last_updated":"2024-11-01","output_modalities":"text","tool_call":true,"vendor":"mistral","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"claude-haiku-4-5","model_name":"Claude Haiku 4.5","developer_id":2,"desc":"Claude Haiku 4.5 is a fast, affordable, and highly capable AI model, excelling at coding and agentic tasks. Its combination of speed and low cost makes it ideal for powering real-time applications like chatbots, high-volume free services, and specialized \"sub-agents\" for complex tasks in coding, finance, and research. It can also handle common business tasks like creating office documents and assisting with strategy and analysis.\n⚠️ The minimum cache token for claude-haiku-4-5 has been increased from 1,024 to 4,096 tokens.","pricing":{"cache_read":0.11,"cache_write":1.375,"input":1.1,"output":5.5},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":2.2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":1.375,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":1.375,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.11,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":5.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.1,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,pdf","endpoints":"","max_output":64000,"context_length":200000,"release_date":"2025-10-01","last_updated":"2025-10-01","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true},"vendor":"anthropic","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"claude-sonnet-4-5","model_name":"Claude Sonnet 4.5","developer_id":2,"desc":"Sonnet 4.5 is the best model in the world for agents, coding, and computer usage. It is also our most accurate and detailed model for long-running tasks, with enhanced knowledge in coding, finance, and cybersecurity.  \nThis model supports a thinking parameter to enable thinking requests in Claude mode.","pricing":{"cache_read":0.33,"cache_write":4.125,"input":3.3,"output":16.5,"tiers":[{"cache_read":0.66,"cache_write":8.25,"input":6.6,"output":24.75,"tier":{"size":200000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":6.6,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":13.2,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":4.125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":8.25,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":4.125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":8.25,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.33,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.66,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":16.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":24.75,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":3.3,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":6.6,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,pdf","endpoints":"","max_output":64000,"context_length":200000,"release_date":"2025-09-29","last_updated":"2025-09-29","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true},"vendor":"anthropic","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"claude-sonnet-4-5-think","model_name":"Claude Sonnet 4.5 Thinking","developer_id":2,"desc":"Claude Sonnet 4.5 does not enable reasoning mode by default. To access its deep reasoning capabilities, users would typically need to call the native Claude API. To make this capability available through an OpenAI-compatible interface, the claude-sonnet-4-5-think model is provided with reasoning mode pre-enabled and a default 64k-token context window, allowing it to be called directly via the OpenAI unified API. Claude Sonnet 4.5 Think is a reasoning-focused variant of Claude Sonnet 4.5 designed for advanced tasks that require rigorous reasoning, complex decision-making, and long-chain analysis; aside from its enhanced reasoning mechanism, all other capabilities remain consistent with the standard Claude Sonnet 4.5 model, making it well suited for complex problem decomposition, multi-step planning, and logic-intensive analysis.","pricing":{"cache_read":0.33,"cache_write":4.125,"input":3.3,"output":16.5,"tiers":[{"cache_read":0.66,"cache_write":8.25,"input":6.6,"output":24.75,"tier":{"size":200000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":6.6,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":13.2,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":4.125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":8.25,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":4.125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":8.25,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.33,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.66,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":16.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":24.75,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":3.3,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":6.6,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,pdf","endpoints":"","max_output":64000,"context_length":200000,"release_date":"2025-09-29","last_updated":"2025-09-29","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true},"vendor":"anthropic","variant_of":"claude-sonnet-4-5","variant_kind":"mode-preset","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"cc-glm-5","model_name":"CC GLM 5","developer_id":5,"desc":"Supports Claude native interface, can be directly requested in Claude Code.","pricing":{"input":0.06,"output":0.22},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":131072,"context_length":200000,"output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","variant_of":"glm-5","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"cc-glm-5-turbo","model_name":"CC GLM 5 Turbo","developer_id":5,"desc":"Supports Claude native interface, can be directly requested in Claude Code.","pricing":{"input":0.06,"output":0.22},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":131072,"context_length":204800,"output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","variant_of":"glm-5-turbo","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"cloudflare-glm-5.2","model_name":"Cloudflare Glm 5.2","developer_id":5,"desc":"","pricing":{"cache_read":0.2604,"input":1.4,"output":4.4002},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":131072,"context_length":1000000,"output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high","max"],"default":"max"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","variant_of":"glm-5.2","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"grok-4-1-fast-non-reasoning","model_name":"Grok 4.1 Fast","developer_id":9,"desc":"Grok 4.1 is a new conversational model with significant improvements in real-world usability, delivering exceptional performance in creative, emotional, and collaborative interactions. It is more perceptive to nuanced user intent, more engaging to converse with, and more coherent in personality, while fully preserving its core intelligence and reliability. Built on large-scale reinforcement learning infrastructure, the model is optimized for style, personality, helpfulness, and alignment, and leverages frontier agentic reasoning models as reward evaluators to autonomously assess and iterate on responses at scale, significantly enhancing overall interaction quality.","pricing":{"cache_read":0.05,"input":0.2,"output":0.5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":1000000,"release_date":"2025-11-19","last_updated":"2025-11-19","output_modalities":"text","tool_call":true,"interleaved":{"anthropic.messages":true,"openai.responses":true},"vendor":"xai","variant_of":"grok-4.3","variant_kind":"deprecated-alias","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"grok-4-1-fast-reasoning","model_name":"Grok 4.1 Fast (reasoning)","developer_id":9,"desc":"Grok 4.1 is a new conversational model with significant improvements in real-world usability, delivering exceptional performance in creative, emotional, and collaborative interactions. It is more perceptive to nuanced user intent, more engaging to converse with, and more coherent in personality, while fully preserving its core intelligence and reliability. Built on large-scale reinforcement learning infrastructure, the model is optimized for style, personality, helpfulness, and alignment, and leverages frontier agentic reasoning models as reward evaluators to autonomously assess and iterate on responses at scale, significantly enhancing overall interaction quality.","pricing":{"cache_read":0.05,"input":0.2,"output":0.5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":1000000,"release_date":"2025-11-19","last_updated":"2025-11-19","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"],"default":"low"}],"interleaved":{"anthropic.messages":true,"openai.responses":true},"vendor":"xai","variant_of":"grok-4.3","variant_kind":"deprecated-alias","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"grok-code-fast-1","model_name":"Grok Code Fast 1","developer_id":9,"desc":"Grok 4.1 is a new conversational model with significant improvements in real-world usability, delivering exceptional performance in creative, emotional, and collaborative interactions. It is more perceptive to nuanced user intent, more engaging to converse with, and more coherent in personality, while fully preserving its core intelligence and reliability. Built on large-scale reinforcement learning infrastructure, the model is optimized for style, personality, helpfulness, and alignment, and leverages frontier agentic reasoning models as reward evaluators to autonomously assess and iterate on responses at scale, significantly enhancing overall interaction quality.","pricing":{"cache_read":0.2,"input":1,"output":2,"tiers":[{"cache_read":0.4,"input":2,"output":2,"tier":{"size":200000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.4,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":10000,"context_length":256000,"release_date":"2024-08-25","last_updated":"2024-08-25","output_modalities":"text","reasoning":true,"tool_call":true,"vendor":"xai","variant_of":"grok-build-0.1","variant_kind":"deprecated-alias","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"k2.6-code-preview-free","model_name":"K2.6 Code Preview (free)","developer_id":15,"desc":"kimi-for-coding-free is a free and open version offered by AIHubMix specifically for Kimi users. To maintain stable service operations, the following usage limits apply: a maximum of 5 requests per minute 500 total requests per day, and a daily quota of 1 million tokens.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,video","endpoints":"","max_output":256000,"context_length":262144,"output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"moonshot","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"musesteamer-air-image","model_name":"Musesteamer Air Image","developer_id":25,"desc":"musesteamer-air-image is a text-to-image model developed by the Baidu Search team aimed at providing extreme cost-effectiveness. It can quickly generate clear images with coherent actions based on user prompts, making it easy to convert users' descriptions into images.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"image","cost_usd":0.0071,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"image","schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-2.5-flash-image","model_name":"Gemini 2.5 Flash Image","developer_id":8,"desc":"Gemini 2.5 Flash Image (Nano-Banana) is a state-of-the-art image generation and editing model that enables seamless blending of multiple images into a single composition while maintaining character consistency for rich visual storytelling. It supports precise, targeted image transformations through natural language instructions and leverages built-in world knowledge for both image generation and editing, making it well suited for creative design, content production, advertising, and visual expression workflows.","pricing":{"cache_read":0.03,"input":0.3,"output":2.499},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.03,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.499,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_image_tokens","unit":"million_tokens","cost_usd":0.3,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_image_tokens","unit":"million_tokens","cost_usd":30,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.3,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"image_generation,llm","features":"","input_modalities":"text,image","endpoints":"","max_output":32768,"context_length":65536,"release_date":"2025-08-26","last_updated":"2025-08-26","output_modalities":"image,text","vendor":"google","open_weights":false,"schema_checked":true,"retire_stage":"active"},{"model_id":"qwen3.6-plus-preview-free","model_name":"Qwen3.6 Plus Preview (free)","developer_id":13,"desc":"This model has been removed from the platform.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,long_context","input_modalities":"text","endpoints":"","max_output":65535,"context_length":1000000,"output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"alibaba","variant_of":"qwen3.6-plus","variant_kind":"pricing-tier","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"zai-glm-5-turbo","model_name":"Zai Glm 5 Turbo","developer_id":5,"desc":"","pricing":{"cache_read":0.24,"input":1.2,"output":3.9996},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":131072,"context_length":204800,"output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","variant_of":"glm-5-turbo","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5","model_name":"GPT 5","developer_id":12,"desc":"GPT-5 is OpenAI’s most advanced general-purpose model, delivering major improvements in reasoning, code quality, and overall user experience. It is optimized for complex tasks that require step-by-step reasoning, precise instruction following, and high accuracy in high-stakes scenarios. The model supports test-time routing and advanced prompt understanding, including user-specified intent such as “think hard about this,” while significantly reducing hallucination and sycophancy and improving performance in coding, writing, and health-related tasks.","pricing":{"cache_read":0.125,"input":1.25,"output":10},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":128000,"context_length":400000,"release_date":"2025-08-07","last_updated":"2025-08-07","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"],"default":"medium"}],"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-v3.2","model_name":"DeepSeek V3.2","developer_id":7,"desc":"DeepSeek-V3.2 is an efficient large language model equipped with DeepSeek Sparse Attention and reinforced reasoning performance, but its core strength lies in powerful agentic capabilities—enabled by large-scale task-synthesis that tightly integrates reasoning with real-world tool use, delivering robust, compliant, and generalizable agent behaviour. Users can toggle deeper reasoning through the reasoning_enabled switch.","pricing":{"input":0.58,"output":1.680028},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,thinking","input_modalities":"text","endpoints":"","max_output":64000,"context_length":163840,"release_date":"2025-12-01","last_updated":"2025-12-01","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"deepseek","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5-codex","model_name":"GPT-5-Codex","developer_id":12,"desc":"GPT-5-Codex is a version of GPT-5 optimized for autonomous coding tasks in Codex or similar environments. It is only available in the Responses API, and the underlying model snapshots will be updated regularly. https://docs.aihubmix.com/en/api/Responses-API You can also use it in codex-cll; see https://docs.aihubmix.com/en/api/Codex-CLI for using codex-cll through Aihubmix.","pricing":{"cache_read":0.125,"input":1.25,"output":10},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":128000,"context_length":400000,"release_date":"2025-09-15","last_updated":"2025-09-15","output_modalities":"text","reasoning":true,"tool_call":true,"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5-pro","model_name":"GPT 5 Pro","developer_id":12,"desc":"GPT-5 pro uses more compute to think harder and provide consistently better answers.\n\nGPT-5 pro is available in the Responses API only to enable support for multi-turn model interactions before responding to API requests, and other advanced API features in the future. Since GPT-5 pro is designed to tackle tough problems, some requests may take several minutes to finish. To avoid timeouts, try using background mode. As our most advanced reasoning model, GPT-5 pro defaults to (and only supports) reasoning.effort: high. GPT-5 pro does not support code interpreter.","pricing":{"input":15,"output":120},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":272000,"context_length":400000,"release_date":"2025-10-06","last_updated":"2025-10-06","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["high"],"default":"high"}],"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"DeepSeek-V3.1-Think","model_name":"DeepSeek V3.1 Thinking","developer_id":7,"desc":"Thinking mode of DeepSeek-V3.1;  \nDeepSeek V3.1 is a text generation model provided by DeepSeek, featuring a hybrid reasoning architecture that achieves an effective integration of thinking and non-thinking modes.","pricing":{"input":0.56,"output":1.68},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":32000,"context_length":128000,"release_date":"2025-08-21","last_updated":"2025-08-21","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"vendor":"deepseek","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5-mini","model_name":"GPT 5 Mini","developer_id":12,"desc":"GPT-5 mini is a faster, more cost-efficient version of GPT-5. It's great for well-defined tasks and precise prompts.","pricing":{"cache_read":0.025,"input":0.25,"output":2},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.025,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":128000,"context_length":400000,"release_date":"2025-08-07","last_updated":"2025-08-07","output_modalities":"text","reasoning":true,"tool_call":true,"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5-nano","model_name":"GPT 5 Nano","developer_id":12,"desc":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, designed specifically for developer tools and environments that demand rapid interactions and ultra-low latency. While it offers a more lightweight solution with limited reasoning depth compared to its larger counterparts, GPT-5-Nano excels in core capabilities such as instruction-following and maintaining critical safety features. As the successor to GPT-4.1-nano, it provides an optimal choice for cost-sensitive or real-time applications, where efficiency and speed are paramount. Particularly well-suited for summarization and classification tasks, GPT-5-Nano is a powerful tool for developers needing a swift, reliable AI model for streamlined processes.","pricing":{"cache_read":0.005,"input":0.05,"output":0.4},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.005,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.4,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.05,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":128000,"context_length":400000,"release_date":"2025-08-07","last_updated":"2025-08-07","output_modalities":"text","reasoning":true,"tool_call":true,"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5-chat-latest","model_name":"GPT 5 Chat","developer_id":12,"desc":"GPT-5 Chat points to the GPT-5 snapshot currently used in ChatGPT. GPT-5 is our next-generation, high-intelligence flagship model. It accepts both text and image inputs, and produces text outputs.","pricing":{"cache_read":0.125,"input":1.25,"output":10},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":16384,"context_length":128000,"release_date":"2025-08-07","last_updated":"2025-08-07","output_modalities":"text","vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"claude-opus-4-1","model_name":"Claude Opus 4.1","developer_id":2,"desc":"Opus 4.1 is an upgraded version of Claude Opus 4, with improvements mainly in agent tasks, practical coding, and reasoning. Compared to Opus 4, there is a slight improvement in software engineering accuracy; Opus 4.1 has higher accuracy at 74.5%.","pricing":{"input":16.5,"output":82.5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":32000,"context_length":200000,"release_date":"2025-08-05","last_updated":"2025-08-05","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true},"vendor":"anthropic","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"o3-deep-research","model_name":"O3 Deep Research","developer_id":12,"desc":"Only supported through requests to the v1/responses interface.\no3-deep-research is OpenAI most advanced model for deep research, designed to tackle complex, multi-step research tasks. It can search and synthesize information from across the internet as well as from your own data—brought in through MCP connectors.","pricing":{"cache_read":2.5,"input":10,"output":40},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":40,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-06-27","last_updated":"2025-06-27","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"kimi-k2.5","model_name":"Kimi K2.5","developer_id":15,"desc":"Kimi K2.5 is the smartest model of Kimi to date, achieving open-source state-of-the-art (SoTA) performance in Agent, coding, visual understanding, and a series of general intelligent tasks. At the same time, Kimi K2.5 is also the most versatile model of Kimi so far, with a native multimodal architecture design that supports both visual and text input, thinking and non-thinking modes, as well as dialogue and Agent tasks.","pricing":{"cache_read":0.105,"input":0.6,"output":3},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,function_calling,structured_outputs","input_modalities":"text,image,video","endpoints":"","max_output":0,"context_length":262144,"release_date":"2026-01","last_updated":"2026-01","output_modalities":"text","reasoning":true,"tool_call":true,"vendor":"moonshot","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-max-2026-01-23","model_name":"Qwen3 Max 2026 01-23","developer_id":13,"desc":"The snapshot version of the Tongyi Qianwen 3 series Max model is from January 23, 2026. By default, it does not require thinking, but thinking mode can be enabled through the enable_thinking parameter, as detailed in the code example. (After enabling thinking by passing parameters, it becomes: Qwen3-Max-Thinking). This model has a total parameter count exceeding one trillion (1T) and a pre-training data volume of up to 36T Tokens, making it the largest and most powerful reasoning model from Alibaba to date.","pricing":{"cache_read":0.09016,"cache_write":0.5635,"input":0.4508,"output":1.8032,"tiers":[{"cache_read":0.1804,"cache_write":1.1275,"input":0.902,"output":3.608,"tier":{"size":32000,"type":"context"}},{"cache_read":0.27044,"cache_write":1.69025,"input":1.3522,"output":5.4088,"tier":{"size":128000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.5635,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":32000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":1.1275,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":1.69025,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.09016,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.1804,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.27044,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.8032,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.608,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":5.4088,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.4508,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.902,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.3522,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"web_search_requests","unit":"request","cost_usd":0.000548,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":65536,"context_length":262144,"release_date":"2026-01-23","last_updated":"2026-01-23","output_modalities":"text","reasoning":true,"tool_call":true,"vendor":"alibaba","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-vl-plus","model_name":"Qwen3 VL Plus","developer_id":13,"desc":"The Qwen3 series visual understanding model achieves an effective fusion of thinking and non-thinking modes. Its visual agent capabilities reach world-class levels on public test sets such as OS World. This version features comprehensive upgrades in visual coding, spatial perception, and multimodal reasoning; visual perception and recognition abilities are greatly enhanced, supporting ultra-long video understanding.","pricing":{"cache_read":0.0274,"input":0.137,"output":1.37,"tiers":[{"input":0.2054,"output":2.054,"tier":{"size":32000,"type":"context"}},{"input":0.411,"output":4.11,"tier":{"size":128000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":2520000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.37,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.054,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":4.11,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":2520000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.137,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.2054,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.411,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":2520000}}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text,image,video","endpoints":"","max_output":32768,"context_length":262144,"release_date":"2025-09-23","last_updated":"2025-09-23","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved":{"openai.chat_completions":true},"vendor":"alibaba","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"cc-minimax-m2.7","model_name":"CC MiniMax M2.7","developer_id":18,"desc":"For Claude Code only","pricing":{"input":0.1,"output":0.1},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":204800,"context_length":204800,"output_modalities":"text","tool_call":true,"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"minimax","variant_of":"minimax-m2.7","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"cc-minimax-m2.7-highspeed","model_name":"CC MiniMax M2.7 Highspeed","developer_id":18,"desc":"For Claude Code only","pricing":{"input":0.1,"output":0.1},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":204800,"context_length":204800,"output_modalities":"text","tool_call":true,"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"minimax","variant_of":"minimax-m2.7-highspeed","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"minimax-m2.5","model_name":"MiniMax M2.5","developer_id":18,"desc":"The MiniMax M2.5 is a flagship programming model built for real-world productivity. As a production-grade model natively designed for Agent scenarios, it has achieved state-of-the-art (SOTA) performance in coding, agentic tool use, search, and office work.","pricing":{"input":0.288,"output":1.152},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":204800,"context_length":204800,"release_date":"2026-02-12","last_updated":"2026-02-12","output_modalities":"text","reasoning":true,"tool_call":true,"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"minimax","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"minimax-m2.5-highspeed","model_name":"MiniMax M2.5 Highspeed","developer_id":18,"desc":"• Same performance as minimax-m2.5\n• Significantly faster inference","pricing":{"input":0.288,"output":1.152},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":204800,"context_length":204800,"release_date":"2026-02-13","last_updated":"2026-02-13","output_modalities":"text","reasoning":true,"tool_call":true,"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"minimax","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"mm-minimax-m2.7-highspeed","model_name":"Mm Minimax M2.7 Highspeed","developer_id":18,"desc":"For Claude Code only","pricing":{"input":0.1,"output":0.1},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":204800,"context_length":204800,"output_modalities":"text","tool_call":true,"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"minimax","variant_of":"minimax-m2.7-highspeed","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-minimax-m2.7","model_name":"Coding MiniMax M2.7","developer_id":18,"desc":"","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":204800,"context_length":204800,"release_date":"2026-03-18","last_updated":"2026-03-18","output_modalities":"text","reasoning":true,"tool_call":true,"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"minimax","variant_of":"minimax-m2.7","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-minimax-m2.7-highspeed","model_name":"Coding MiniMax M2.7 Highspeed","developer_id":18,"desc":"","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":204800,"context_length":204800,"release_date":"2026-03-18","last_updated":"2026-03-18","output_modalities":"text","reasoning":true,"tool_call":true,"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"minimax","variant_of":"minimax-m2.7-highspeed","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"cc-minimax-m2.5","model_name":"CC MiniMax M2.5","developer_id":18,"desc":"For Claude Code only","pricing":{"input":0.1,"output":0.1},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":204800,"context_length":204800,"output_modalities":"text","tool_call":true,"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"minimax","variant_of":"minimax-m2.5","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"cc-minimax-m2.5-highspeed","model_name":"CC MiniMax M2.5 Highspeed","developer_id":18,"desc":"For Claude Code only","pricing":{"input":0.1,"output":0.1},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":204800,"context_length":204800,"output_modalities":"text","tool_call":true,"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"minimax","variant_of":"minimax-m2.5-highspeed","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-minimax-m2.5","model_name":"Coding MiniMax M2.5","developer_id":18,"desc":"","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":204800,"context_length":204800,"release_date":"2026-02-12","last_updated":"2026-02-12","output_modalities":"text","reasoning":true,"tool_call":true,"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"minimax","variant_of":"minimax-m2.5","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-minimax-m2.5-highspeed","model_name":"Coding MiniMax M2.5 Highspeed","developer_id":18,"desc":"","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":204800,"context_length":204800,"release_date":"2026-02-13","last_updated":"2026-02-13","output_modalities":"text","reasoning":true,"tool_call":true,"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"minimax","variant_of":"minimax-m2.5-highspeed","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"sora-2","model_name":"Sora 2","developer_id":12,"desc":"Sora-2 is the next-generation text-to-video model evolved from Sora, optimized for higher visual realism, stronger physical consistency, and longer temporal coherence. It delivers more stable character consistency, complex motion rendering, camera control, and narrative continuity, while supporting higher resolutions and minute-level video generation for film production, advertising, virtual content creation, and creative multimedia workflows.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.1,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-10-06","last_updated":"2025-10-06","output_modalities":"video","schema_checked":false,"retire_stage":"active"},{"model_id":"sora-2-pro","model_name":"Sora 2 Pro","developer_id":12,"desc":"OpenAI video model Sora2-pro official API.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.5,"source":"img_price_config","variant":{"quality":"standard","size":"1024x1792"}},{"billable":"generate","unit":"second","cost_usd":0.5,"source":"img_price_config","variant":{"quality":"standard","size":"1792x1024"}},{"billable":"generate","unit":"second","cost_usd":0.3,"source":"img_price_config","variant":{"quality":"standard","size":"720x1280"}},{"billable":"generate","unit":"second","cost_usd":0.3,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-10-06","last_updated":"2025-10-06","output_modalities":"video","schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seedream-4-5","model_name":"Doubao Seedream 4.5","developer_id":4,"desc":"Seedream 4.5 is ByteDance's latest multimodal image model, integrating capabilities such as text-to-image, image-to-image, and multi-image output, along with incorporating common sense and reasoning abilities. Compared to the previous 4.0 model, it significantly improves generation quality, offering better editing consistency and multi-image fusion effects, with more precise control over image details. The generation of small text and small faces is more natural.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"image","cost_usd":0.0387,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"image","schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-4o-mini-audio-preview","model_name":"GPT 4o Mini Audio Preview","developer_id":12,"desc":"","pricing":{"input":0.15,"output":0.6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,audio","endpoints":"","max_output":16384,"context_length":128000,"output_modalities":"text","vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"wan2.6-i2v","model_name":"Wan2.6 I2v","developer_id":13,"desc":"Wan 2.6 - Text-to-Video generation features intelligent storyboard scheduling supporting multi-shot narration, higher quality sound generation, stable multi-person dialogue, more natural and realistic voice tones, and supports video generation up to 15 seconds in length.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.151,"source":"img_price_config","variant":{"quality":"standard","size":"1080x1920"}},{"billable":"generate","unit":"second","cost_usd":0.0904,"source":"img_price_config","variant":{"quality":"standard","size":"1088x832"}},{"billable":"generate","unit":"second","cost_usd":0.151,"source":"img_price_config","variant":{"quality":"standard","size":"1248x1632"}},{"billable":"generate","unit":"second","cost_usd":0.0904,"source":"img_price_config","variant":{"quality":"standard","size":"1280x720"}},{"billable":"generate","unit":"second","cost_usd":0.151,"source":"img_price_config","variant":{"quality":"standard","size":"1440x1440"}},{"billable":"generate","unit":"second","cost_usd":0.151,"source":"img_price_config","variant":{"quality":"standard","size":"1632x1248"}},{"billable":"generate","unit":"second","cost_usd":0.151,"source":"img_price_config","variant":{"quality":"standard","size":"1920x1080"}},{"billable":"generate","unit":"second","cost_usd":0.0904,"source":"img_price_config","variant":{"quality":"standard","size":"720x1280"}},{"billable":"generate","unit":"second","cost_usd":0.0904,"source":"img_price_config","variant":{"quality":"standard","size":"832x1088"}},{"billable":"generate","unit":"second","cost_usd":0.0904,"source":"img_price_config","variant":{"quality":"standard","size":"960x960"}},{"billable":"generate","unit":"second","cost_usd":0.0904,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"image,text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"video","schema_checked":false,"retire_stage":"active"},{"model_id":"wan2.6-t2v","model_name":"Wan2.6 T2v","developer_id":13,"desc":"Wan 2.6 - Text-to-Video generation features intelligent storyboard scheduling supporting multi-shot narration, higher quality sound generation, stable multi-person dialogue, more natural and realistic voice tones, and supports video generation up to 15 seconds in length.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.151,"source":"img_price_config","variant":{"quality":"standard","size":"1080x1920"}},{"billable":"generate","unit":"second","cost_usd":0.0904,"source":"img_price_config","variant":{"quality":"standard","size":"1088x832"}},{"billable":"generate","unit":"second","cost_usd":0.151,"source":"img_price_config","variant":{"quality":"standard","size":"1248x1632"}},{"billable":"generate","unit":"second","cost_usd":0.0904,"source":"img_price_config","variant":{"quality":"standard","size":"1280x720"}},{"billable":"generate","unit":"second","cost_usd":0.151,"source":"img_price_config","variant":{"quality":"standard","size":"1440x1440"}},{"billable":"generate","unit":"second","cost_usd":0.151,"source":"img_price_config","variant":{"quality":"standard","size":"1632x1248"}},{"billable":"generate","unit":"second","cost_usd":0.151,"source":"img_price_config","variant":{"quality":"standard","size":"1920x1080"}},{"billable":"generate","unit":"second","cost_usd":0.0904,"source":"img_price_config","variant":{"quality":"standard","size":"720x1280"}},{"billable":"generate","unit":"second","cost_usd":0.0904,"source":"img_price_config","variant":{"quality":"standard","size":"832x1088"}},{"billable":"generate","unit":"second","cost_usd":0.0904,"source":"img_price_config","variant":{"quality":"standard","size":"960x960"}},{"billable":"generate","unit":"second","cost_usd":0.151,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"video","schema_checked":false,"retire_stage":"active"},{"model_id":"cc-glm-4.7","model_name":"CC GLM 4.7","developer_id":5,"desc":"Supports Claude native interface, can be directly requested in Claude Code.","pricing":{"input":0.06,"output":0.22},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"cc-minimax-m2.1","model_name":"CC MiniMax M2.1","developer_id":18,"desc":"For Claude Code only","pricing":{"input":0.1,"output":0.1},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":204800,"context_length":204800,"output_modalities":"text","tool_call":true,"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"minimax","variant_of":"minimax-m2.1","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-glm-4.7","model_name":"Coding GLM 4.7","developer_id":5,"desc":"Only supports OpenAI-compatible formats.","pricing":{"cache_read":0.010998,"input":0.06,"output":0.22},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":131072,"context_length":200000,"release_date":"2025-12-22","last_updated":"2025-12-22","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","variant_of":"glm-4.7","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-minimax-m2.1","model_name":"Coding MiniMax M2.1","developer_id":18,"desc":"","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":204800,"context_length":204800,"release_date":"2025-12-23","last_updated":"2025-12-23","output_modalities":"text","reasoning":true,"tool_call":true,"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"minimax","variant_of":"minimax-m2.1","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-minimax-m2.1-free","model_name":"Coding MiniMax M2.1 (free)","developer_id":18,"desc":"coding-minimax-m2.1-free is a free and open version offered by AIHubMix specifically for MiniMax users. To maintain stable service operations, the following usage limits apply: a maximum of 5 requests per minute, 500 total requests per day, and a daily quota of 1 million tokens.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":204800,"context_length":204800,"release_date":"2025-12-23","last_updated":"2025-12-23","output_modalities":"text","reasoning":true,"tool_call":true,"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"minimax","variant_of":"minimax-m2.1","variant_kind":"pricing-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"minimax-m2.1","model_name":"MiniMax M2.1","developer_id":18,"desc":"MiniMax-M2.1 redefines efficiency for intelligent agents. It is a compact, fast, and cost-effective MoE model with a total of 230 billion parameters and 10 billion active parameters, designed for top performance in coding and intelligent agent tasks while maintaining strong general intelligence. With only 10 billion active parameters, MiniMax-M2 delivers the complex end-to-end tool usage performance expected from today's leading models, but in a more streamlined form factor, making deployment and scaling easier than ever before.","pricing":{"input":0.288,"output":1.152},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":204800,"context_length":204800,"release_date":"2025-12-23","last_updated":"2025-12-23","output_modalities":"text","reasoning":true,"tool_call":true,"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"minimax","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"o3","model_name":"O3","developer_id":12,"desc":"OpenAI o3 is a powerful model across multiple domains, setting a new standard for coding, math, science, and visual reasoning tasks.","pricing":{"cache_read":0.5,"input":2,"output":8},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":8,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,pdf","endpoints":"","max_output":100000,"context_length":200000,"release_date":"2025-04-16","last_updated":"2025-04-16","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"],"default":"medium"}],"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"kimi-for-coding-free","model_name":"Kimi For Coding (free)","developer_id":15,"desc":"kimi-for-coding-free is a free and open version offered by AIHubMix specifically for Kimi users. To maintain stable service operations, the following usage limits apply: a maximum of 5 requests per minute 500 total requests per day, and a daily quota of 1 million tokens.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,video","endpoints":"","max_output":32768,"context_length":256000,"release_date":"2026-06-12","last_updated":"2026-06-12","output_modalities":"text","reasoning":true,"tool_call":true,"vendor":"moonshot","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"o3-pro","model_name":"O3 Pro","developer_id":12,"desc":"o3-pro\nThis model only supports Requests API interface requests.The model's thinking time is relatively long, so the response will be slow.","pricing":{"cache_read":20,"input":20,"output":80},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":20,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":80,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":20,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":100000,"context_length":200000,"release_date":"2025-06-10","last_updated":"2025-06-10","output_modalities":"text","reasoning":true,"tool_call":true,"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"qianfan-ocr","model_name":"Qianfan Ocr","developer_id":25,"desc":"Qianfan-OCR-Fast is a multimodal large model specialized for OCR, trained primarily on OCR-domain data while retaining appropriate general multimodal capabilities, and it outperforms Qianfan-OCR.","pricing":{"input":0.062,"output":0.248},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"ocr","features":"","input_modalities":"text,image","endpoints":"","max_output":28000,"context_length":32000,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qianfan-ocr-fast","model_name":"Qianfan Ocr Fast","developer_id":25,"desc":"Qianfan-OCR-Fast is a multimodal large model specialized for OCR, trained primarily on OCR-domain data while retaining appropriate general multimodal capabilities, and it outperforms Qianfan-OCR.","pricing":{"input":0.664,"output":2.738336},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"ocr","features":"","input_modalities":"text,image","endpoints":"","max_output":28000,"context_length":32000,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"step-3.5-flash","model_name":"Step 3.5 Flash","developer_id":16,"desc":"step-3.5-flash is stepfun's flagship inference model, designed for high-complexity tasks that require deep reasoning and fast execution. It excels at decomposing multi-step problems, performing tool calls, and maintaining consistency across massive datasets. It is the preferred choice for complex workloads such as long-context agents, advanced software engineering, and end-to-end research automation.","pricing":{"input":0.11,"output":0.33},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":256000,"release_date":"2026-01-29","last_updated":"2026-01-29","output_modalities":"text","interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"stepfun","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"wan2.2-i2v-plus","model_name":"Wan2.2 I2v Plus","developer_id":13,"desc":"The newly upgraded Tongyi Wanxiang 2.2 text-to-video offers higher video quality. It optimizes video generation stability and success rate, features stronger instruction-following capabilities, consistently maintains image text, portrait, and product consistency, and provides precise camera motion control.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.0959,"source":"img_price_config","variant":{"quality":"standard","size":"1080x1920"}},{"billable":"generate","unit":"second","cost_usd":0.0959,"source":"img_price_config","variant":{"quality":"standard","size":"1248x1632"}},{"billable":"generate","unit":"second","cost_usd":0.0959,"source":"img_price_config","variant":{"quality":"standard","size":"1440x1440"}},{"billable":"generate","unit":"second","cost_usd":0.0959,"source":"img_price_config","variant":{"quality":"standard","size":"1632x1248"}},{"billable":"generate","unit":"second","cost_usd":0.0959,"source":"img_price_config","variant":{"quality":"standard","size":"1920x1080"}},{"billable":"generate","unit":"second","cost_usd":0.0192,"source":"img_price_config","variant":{"quality":"standard","size":"480x832"}},{"billable":"generate","unit":"second","cost_usd":0.0192,"source":"img_price_config","variant":{"quality":"standard","size":"624x624"}},{"billable":"generate","unit":"second","cost_usd":0.0192,"source":"img_price_config","variant":{"quality":"standard","size":"832x480"}},{"billable":"generate","unit":"second","cost_usd":0.0959,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"video","schema_checked":false,"retire_stage":"active"},{"model_id":"wan2.5-i2v-preview","model_name":"Wan2.5 I2v Preview","developer_id":13,"desc":"Tongyi Wanxiang 2.5 - Text-to-Video Preview features a newly upgraded technical architecture, supporting sound generation synchronized with visuals, 10-second long video generation, stronger instruction-following capabilities, and further improvements in motion ability and visual quality.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.137,"source":"img_price_config","variant":{"quality":"standard","size":"1080x1920"}},{"billable":"generate","unit":"second","cost_usd":0.0822,"source":"img_price_config","variant":{"quality":"standard","size":"1088x832"}},{"billable":"generate","unit":"second","cost_usd":0.137,"source":"img_price_config","variant":{"quality":"standard","size":"1248x1632"}},{"billable":"generate","unit":"second","cost_usd":0.0822,"source":"img_price_config","variant":{"quality":"standard","size":"1280x720"}},{"billable":"generate","unit":"second","cost_usd":0.137,"source":"img_price_config","variant":{"quality":"standard","size":"1440x1440"}},{"billable":"generate","unit":"second","cost_usd":0.137,"source":"img_price_config","variant":{"quality":"standard","size":"1632x1248"}},{"billable":"generate","unit":"second","cost_usd":0.137,"source":"img_price_config","variant":{"quality":"standard","size":"1920x1080"}},{"billable":"generate","unit":"second","cost_usd":0.0411,"source":"img_price_config","variant":{"quality":"standard","size":"480x832"}},{"billable":"generate","unit":"second","cost_usd":0.0411,"source":"img_price_config","variant":{"quality":"standard","size":"624x624"}},{"billable":"generate","unit":"second","cost_usd":0.0822,"source":"img_price_config","variant":{"quality":"standard","size":"720x1280"}},{"billable":"generate","unit":"second","cost_usd":0.0822,"source":"img_price_config","variant":{"quality":"standard","size":"832x1088"}},{"billable":"generate","unit":"second","cost_usd":0.0411,"source":"img_price_config","variant":{"quality":"standard","size":"832x480"}},{"billable":"generate","unit":"second","cost_usd":0.0822,"source":"img_price_config","variant":{"quality":"standard","size":"960x960"}},{"billable":"generate","unit":"second","cost_usd":0.0411,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"video","schema_checked":false,"retire_stage":"active"},{"model_id":"wan2.5-t2v-preview","model_name":"Wan2.5 T2v Preview","developer_id":13,"desc":"Tongyi Wanxiang 2.5 - Text-to-Video Preview, newly upgraded model architecture, supports sound generation synchronized with visuals, supports 10-second long video generation, enhanced instruction compliance, improved motion capability, and further enhanced visual quality.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.137,"source":"img_price_config","variant":{"quality":"standard","size":"1080x1920"}},{"billable":"generate","unit":"second","cost_usd":0.0822,"source":"img_price_config","variant":{"quality":"standard","size":"1088x832"}},{"billable":"generate","unit":"second","cost_usd":0.137,"source":"img_price_config","variant":{"quality":"standard","size":"1248x1632"}},{"billable":"generate","unit":"second","cost_usd":0.0822,"source":"img_price_config","variant":{"quality":"standard","size":"1280x720"}},{"billable":"generate","unit":"second","cost_usd":0.137,"source":"img_price_config","variant":{"quality":"standard","size":"1440x1440"}},{"billable":"generate","unit":"second","cost_usd":0.137,"source":"img_price_config","variant":{"quality":"standard","size":"1632x1248"}},{"billable":"generate","unit":"second","cost_usd":0.137,"source":"img_price_config","variant":{"quality":"standard","size":"1920x1080"}},{"billable":"generate","unit":"second","cost_usd":0.0411,"source":"img_price_config","variant":{"quality":"standard","size":"480x832"}},{"billable":"generate","unit":"second","cost_usd":0.0411,"source":"img_price_config","variant":{"quality":"standard","size":"624x624"}},{"billable":"generate","unit":"second","cost_usd":0.0822,"source":"img_price_config","variant":{"quality":"standard","size":"720x1280"}},{"billable":"generate","unit":"second","cost_usd":0.0822,"source":"img_price_config","variant":{"quality":"standard","size":"832x1088"}},{"billable":"generate","unit":"second","cost_usd":0.0411,"source":"img_price_config","variant":{"quality":"standard","size":"832x480"}},{"billable":"generate","unit":"second","cost_usd":0.0822,"source":"img_price_config","variant":{"quality":"standard","size":"960x960"}},{"billable":"generate","unit":"second","cost_usd":0.137,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"video","schema_checked":false,"retire_stage":"active"},{"model_id":"flux-2-flex","model_name":"Flux 2 Flex","developer_id":27,"desc":"FLUX.2 is purpose-built for real-world creative production workflows. It delivers high-quality images while maintaining character and style consistency across multiple reference images, shows exceptional understanding and execution of structured prompts, and supports complex text reading and writing. It also adheres to brand guidelines, handles lighting, layout, and logo elements with stability, and enables image editing at resolutions up to 4MP — all while preserving fine details, striking a balance between creativity and professional-grade visual output.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"megapixel","cost_usd":0.05,"source":"img_price_config","variant":{"quality":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-11-25","last_updated":"2025-11-25","output_modalities":"image","schema_checked":false,"retire_stage":"active"},{"model_id":"flux-2-pro","model_name":"Flux 2 Pro","developer_id":27,"desc":"FLUX.2 is purpose-built for real-world creative production workflows. It delivers high-quality images while maintaining character and style consistency across multiple reference images, shows exceptional understanding and execution of structured prompts, and supports complex text reading and writing. It also adheres to brand guidelines, handles lighting, layout, and logo elements with stability, and enables image editing at resolutions up to 4MP — all while preserving fine details, striking a balance between creativity and professional-grade visual output.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"megapixel","cost_usd":0.03,"source":"img_price_config","variant":{"quality":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-11-25","last_updated":"2025-11-25","output_modalities":"image","schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-2.5-pro","model_name":"Gemini 2.5 Pro","developer_id":8,"desc":"Gemini 2.5 Pro is an advanced reasoning model developed by Google, optimized for solving highly complex problems across multiple domains. It can deeply understand large-scale information from diverse sources, including text, audio, images, video, and even entire codebases. The model demonstrates strong reasoning capabilities in coding, mathematics, and STEM-related tasks, and supports long-context analysis for large datasets, codebases, and technical documentation.","pricing":{"cache_read":0.125,"input":1.25,"output":10,"tiers":[{"cache_read":0.25,"input":2.5,"output":15,"tier":{"size":200000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":4.5,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.25,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":15,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.035,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,long_context,web,thinking,deepsearch","input_modalities":"text,image,video,audio,pdf","endpoints":"","max_output":65536,"context_length":1048576,"release_date":"2025-06-17","last_updated":"2025-06-17","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"],"default":"medium"},{"type":"budget_tokens"}],"vendor":"google","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"glm-4.6","model_name":"GLM 4.6","developer_id":5,"desc":"GLM-4.6 is Zhipu’s latest flagship model (total parameters 355B, activation parameters 32B), comprehensively surpassing GLM-4.5. Its coding capability is aligned with Claude Sonnet 4, making it a top domestic coding model; the context window has been expanded from 128K to 200K, better suited for long code and agent tasks; inference capabilities have been significantly enhanced and support tool invocation during processing; improvements have been made in tool calling, search agents, writing style, role play, and multilingual translation. The model is named glm-4.6 and is provided by three vendors, with calls prioritized to the Sophnet platform.","pricing":{"cache_read":0.054795,"input":0.273974,"output":1.095896,"tiers":[{"cache_read":0.109589,"input":0.547946,"output":2.191784,"tier":{"size":32000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0547948,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000,"max_output_tokens":200}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0821916,"source":"billing_config","tier":{"name":"tier2","min_tokens":0,"max_tokens":32000,"min_output_tokens":200,"max_output_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.1095892,"source":"billing_config","tier":{"name":"tier3","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.095896,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000,"max_output_tokens":200}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.917804136986,"source":"billing_config","tier":{"name":"tier2","min_tokens":0,"max_tokens":32000,"min_output_tokens":200,"max_output_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.191784,"source":"billing_config","tier":{"name":"tier3","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.273974,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000,"max_output_tokens":200}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.410958,"source":"billing_config","tier":{"name":"tier2","min_tokens":0,"max_tokens":32000,"min_output_tokens":200,"max_output_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.547946,"source":"billing_config","tier":{"name":"tier3","min_tokens":32001,"max_tokens":128000}}],"has_zdr_provider":true,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":131072,"context_length":200000,"release_date":"2025-09-30","last_updated":"2025-09-30","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"glm-4.6v","model_name":"GLM 4.6 Vision","developer_id":5,"desc":"Zhipu's latest visual reasoning model achieves state-of-the-art visual understanding accuracy at the same scale upon release. It natively supports tool invocation, can automatically complete tasks, supports ultra-long 128K context length, and allows flexible toggling of reasoning.","pricing":{"cache_read":0.0274,"input":0.137,"output":0.411,"tiers":[{"cache_read":0.0548,"input":0.274,"output":0.822,"tier":{"size":32000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0274,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0548,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.411,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.822,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.137,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.274,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}}],"has_zdr_provider":true,"types":"llm","features":"","input_modalities":"text,image,video,document","endpoints":"","max_output":32768,"context_length":131072,"release_date":"2025-12-08","last_updated":"2025-12-08","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"}],"vendor":"zhipu","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"glm-ocr","model_name":"GLM Ocr","developer_id":5,"desc":"GLM-OCR is a lightweight professional OCR model with only 0.9B parameters, yet multiple capabilities have reached SOTA levels, establishing a new benchmark for document parsing with a \"small size, high precision\" approach.","pricing":{"input":0.0282,"output":0.0282},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"ocr","features":"","input_modalities":"image","endpoints":"","max_output":0,"context_length":32000,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"cc-glm-4.6","model_name":"CC GLM 4.6","developer_id":5,"desc":"for claude code","pricing":{"input":0.06,"output":0.22},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"coding-glm-4.6","model_name":"Coding GLM 4.6","developer_id":5,"desc":"","pricing":{"cache_read":0.010998,"input":0.06,"output":0.22},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":131072,"context_length":200000,"release_date":"2025-09-30","last_updated":"2025-09-30","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","variant_of":"glm-4.6","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-glm-4.6-free","model_name":"Coding GLM 4.6 (free)","developer_id":5,"desc":"coding-glm-4.6-free is the open and free version of coding-glm-4.6. To ensure stable service performance, usage limits are in place: up to 5 requests per minute, 500 requests per day, and a daily token allowance of 1 million.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":131072,"context_length":200000,"release_date":"2025-09-30","last_updated":"2025-09-30","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"zhipu","variant_of":"glm-4.6","variant_kind":"pricing-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-minimax-m2","model_name":"Coding MiniMax M2","developer_id":18,"desc":"coding-minimax-m2 is a free and open version offered by AIHubMix specifically for MiniMax users. To maintain stable service operations, the following usage limits apply: a maximum of 10 requests per minute, 1,000 total requests per day, and a daily quota of 5 million tokens.204800","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":204800,"context_length":204800,"release_date":"2025-10-27","last_updated":"2025-10-27","output_modalities":"text","reasoning":true,"tool_call":true,"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"minimax","variant_of":"minimax-m2","variant_kind":"channel-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"coding-minimax-m2-free","model_name":"Coding MiniMax M2 (free)","developer_id":18,"desc":"coding-minimax-m2-free is a free and open version offered by AIHubMix specifically for MiniMax users. To maintain stable service operations, the following usage limits apply: a maximum of 5 requests per minute, 500 total requests per day, and a daily quota of 1 million tokens.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":204800,"context_length":204800,"release_date":"2025-10-27","last_updated":"2025-10-27","output_modalities":"text","reasoning":true,"tool_call":true,"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"minimax","variant_of":"minimax-m2","variant_kind":"pricing-tier","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-2.5-pro-search","model_name":"Gemini 2.5 Pro Search","developer_id":8,"desc":"gemini-2.5-pro-search integrates Google's official search functionality; the search feature will have an additional separate fee log directly incorporated into the scoring, with detailed logs not displayed; this will be fixed and displayed later; only supports OpenAI-compatible formats for invocation, does not support Gemini SDK; for Gemini's native SDK, please set parameters directly using the official search parameters.","pricing":{"cache_read":0.125,"input":1.25,"output":10,"tiers":[{"cache_read":0.25,"input":2.5,"output":15,"tier":{"size":200000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":4.5,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.25,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":15,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.035,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm,search","features":"thinking,web,tools,function_calling,structured_outputs,long_context","input_modalities":"text,image,video,audio,pdf","endpoints":"","max_output":65536,"context_length":1048576,"release_date":"2025-06-17","last_updated":"2025-06-17","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"],"default":"medium"},{"type":"budget_tokens"}],"vendor":"google","variant_of":"gemini-2.5-pro","variant_kind":"mode-preset","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"kimi-k2-thinking","model_name":"Kimi K2 Thinking","developer_id":15,"desc":"Kimi K2 Thinking is Moonshot AI's most advanced open-source inference model to date, extending the K2 series into intelligent agent and long-context inference domains. The model is built on the trillion-parameter mixture of experts (MoE) architecture introduced by Kimi K2, activating 32 billion parameters per forward pass and supporting a context window of 256,000 tokens.","pricing":{"cache_read":0.137,"input":0.548,"output":2.192},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":262144,"context_length":262144,"release_date":"2025-11-06","last_updated":"2025-11-06","output_modalities":"text","reasoning":true,"tool_call":true,"interleaved":{"openai.chat_completions":{"field":"reasoning_content"}},"vendor":"moonshot","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"glm-4.5v","model_name":"GLM 4.5 Vision","developer_id":5,"desc":"GLM-4.5V is a vision-language foundational model designed for multimodal agent applications. Based on a mixture-of-experts (MoE) architecture, it has 106 billion parameters and 12 billion active parameters. It delivers outstanding performance in video understanding, image question answering, OCR, and document parsing, and achieves significant improvements in front-end web encoding, basic reasoning, and spatial reasoning.","pricing":{"input":0.274,"output":0.822,"tiers":[{"input":0.548,"output":1.644,"tier":{"size":32000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":64000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.096,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.644,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":64000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.274,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.548,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":64000}}],"has_zdr_provider":true,"types":"llm,ocr","features":"","input_modalities":"text,image,video,document","endpoints":"","max_output":16384,"context_length":65536,"release_date":"2025-08-11","last_updated":"2025-08-11","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"}],"vendor":"zhipu","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-2.5-flash-search","model_name":"Gemini 2.5 Flash Search","developer_id":8,"desc":"gemini-2.5-flash-search integrates Google's official search functionality; the search feature will have an additional separate fee log directly incorporated into the scoring, with detailed logs not displayed; this will be fixed and displayed later; only supports OpenAI-compatible formats for invocation, does not support Gemini SDK; for Gemini's native SDK, please set parameters directly using the official search parameters.","pricing":{"cache_read":0.03,"input":0.3,"output":2.499},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":1,"source":"billing_config"},{"billable":"cached_audio_tokens","unit":"million_tokens","cost_usd":0.0999,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.03,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.499,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_audio_tokens","unit":"million_tokens","cost_usd":0.9999,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.3,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.035,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm,search","features":"web,tools,function_calling,structured_outputs,long_context","input_modalities":"text,image,video,audio,pdf","endpoints":"","max_output":65536,"context_length":1048576,"release_date":"2025-06-17","last_updated":"2025-06-17","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"],"default":"medium"},{"type":"budget_tokens"}],"vendor":"google","variant_of":"gemini-2.5-flash","variant_kind":"mode-preset","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-2.5-flash-preview-05-20-nothink","model_name":"Gemini 2.5 Flash Preview 05-20 (no think)","developer_id":8,"desc":"Gemini-2.5-flash-preview-05-20 is enabled by default for thinking; to disable it, request the name gemini-2.5-flash-preview-05-20-nothink.Only OpenAI-compatible format calls are supported; Gemini SDK is not supported. For the native Gemini SDK, please set the parameter budget=0 directly.","pricing":{"cache_read":0.03,"input":0.3,"output":2.499},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":1,"source":"billing_config"},{"billable":"cached_audio_tokens","unit":"million_tokens","cost_usd":0.0999,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.03,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.499,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_audio_tokens","unit":"million_tokens","cost_usd":0.9999,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.3,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.035,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,long_context","input_modalities":"text,image,video,audio","endpoints":"","max_output":65536,"context_length":1048576,"output_modalities":"text","tool_call":true,"vendor":"google","variant_of":"gemini-2.5-flash-preview-05-20","variant_kind":"mode-preset","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-2.5-flash-preview-05-20-search","model_name":"Gemini 2.5 Flash Preview 05-20 Search","developer_id":8,"desc":"Gemini-2.5 Flash Preview 05-20 Search integrates Google's official search functionality; the search feature will have an additional separate fee log directly integrated into the scoring deduction, with detailed logs not displayed. It will be fixed and displayed later. Only OpenAI-compatible formats are supported for invocation; Gemini SDK is not supported. For Gemini's native SDK, please set parameters directly using the official search parameters.","pricing":{"cache_read":0.03,"input":0.3,"output":2.499},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":1,"source":"billing_config"},{"billable":"cached_audio_tokens","unit":"million_tokens","cost_usd":0.0999,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.03,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.499,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_audio_tokens","unit":"million_tokens","cost_usd":0.9999,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.3,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.035,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm,search","features":"tools,function_calling,structured_outputs,long_context","input_modalities":"text,image,video,audio","endpoints":"","max_output":65536,"context_length":1048576,"release_date":"2025-05-20","last_updated":"2025-05-20","output_modalities":"text","tool_call":true,"vendor":"google","variant_of":"gemini-2.5-flash-preview-05-20","variant_kind":"mode-preset","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-image-1","model_name":"GPT Image 1","developer_id":12,"desc":"Azure OpenAI’s gpt-image-1 image generation API offers both text-to-image generation and image-to-image editing with text guidance capabilities.\nBefore using this API, please ensure you have the latest OpenAI package installed by running pip install -U openai.","pricing":{"input":5,"output":40},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":40,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_image_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_image_tokens","unit":"million_tokens","cost_usd":40,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-04-24","last_updated":"2025-04-24","output_modalities":"image","schema_checked":true,"retire_stage":"active"},{"model_id":"gpt-image-1-mini","model_name":"GPT Image 1 Mini","developer_id":12,"desc":"OpenAI image generation model gpt-image-1-mini\nBefore use, please run pip install -U openai to upgrade to the latest openai package.","pricing":{"input":5,"output":40},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":8,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_image_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_image_tokens","unit":"million_tokens","cost_usd":8,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-08-26","last_updated":"2025-08-26","output_modalities":"image","schema_checked":false,"retire_stage":"active"},{"model_id":"o4-mini","model_name":"O4 Mini","developer_id":12,"desc":"o4-mini is a remarkably smart model for its speed and cost-efficiency. This allows it to support significantly higher usage limits than o3, making it a strong high-volume, high-throughput option for everyone with questions that benefit from reasoning.","pricing":{"cache_read":0.275,"input":1.1,"output":4.4},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.275,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":4.4,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.1,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tool,function_calling,structured_outputs","input_modalities":"text,image,pdf","endpoints":"","max_output":100000,"context_length":200000,"release_date":"2025-04-16","last_updated":"2025-04-16","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"],"default":"medium"}],"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"paddleocr-vl-0.9b","model_name":"Paddleocr VL 0.9b","developer_id":25,"desc":"PaddleOCR-VL is an advanced and efficient document parsing model specifically designed for element recognition within documents. Its core component, PaddleOCR-VL-0.9B, is a compact yet powerful vision-language model (VLM) composed of a NaViT-style dynamic resolution visual encoder and the ERNIE-4.5-0.3B language model, enabling precise element recognition. This model supports 109 languages and excels at recognizing complex elements such as text, tables, formulas, and charts while maintaining extremely low resource consumption. Through comprehensive evaluations on widely used public benchmarks and internal benchmarks, PaddleOCR-VL achieves state-of-the-art (SOTA) performance in both page-level document parsing and element-level recognition. It significantly outperforms existing pipeline-based solutions, multimodal document parsing approaches, and advanced general-purpose multimodal large models, while also offering faster inference speed.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"page","cost_usd":0.025,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"ocr","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"pp-structurev3","model_name":"Pp Structurev3","developer_id":25,"desc":"PP-StructureV3 is an efficient and comprehensive document parsing solution that can effectively convert document images and PDF files into structured content (such as Markdown format). It features powerful capabilities including layout area detection, table recognition, formula recognition, chart understanding, and multi-column reading order recovery. This tool performs excellently across various document types and can handle complex document data.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"page","cost_usd":0.025,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"ocr","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"veo-3.0-generate-preview","model_name":"Veo 3.0 Generate Preview","developer_id":8,"desc":"Veo 3.0 Generate Preview is an advanced AI video generation model that supports text-to-video creation with synchronized audio, featuring excellent physical simulation and lip-sync capabilities. Users can generate vivid video clips from short story prompts. 🎟️ Limited-Time Deal: Save 10% Now.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"second","cost_usd":0.75,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"video","features":"","input_modalities":"text,image,video","endpoints":"","max_output":0,"context_length":0,"output_modalities":"video","schema_checked":false,"retire_stage":"active"},{"model_id":"grok-4","model_name":"Grok 4","developer_id":9,"desc":"Grok, their latest and greatest flagship model, offers unparalleled performance in natural language, math, and reasoning – the perfect jack of all trades.\nThe current pointing model version is grok-4-0709.","pricing":{"cache_read":0.825,"input":3.3,"output":16.5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"function_calling,structured_outputs,thinking","input_modalities":"text,image","endpoints":"","max_output":64000,"context_length":256000,"release_date":"2025-07-09","last_updated":"2025-07-09","output_modalities":"text","reasoning":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"],"default":"medium"}],"interleaved":{"anthropic.messages":true,"openai.responses":true},"vendor":"xai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"kimi-k2-instruct","model_name":"Kimi K2 Instruct","developer_id":15,"desc":"Kimi-K2 is a MoE architecture foundational model with extremely powerful coding and agent capabilities, featuring a total of 1 trillion parameters and activating 32 billion parameters. In benchmark performance tests across major categories such as general knowledge reasoning, programming, mathematics, and agents, the K2 model outperforms other mainstream open-source models.\nThe Kimi-K2 model supports a context length of 128k tokens.\nIt does not support visual capabilities.","pricing":{"input":0.54,"output":2.16},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-01-01","last_updated":"2024-01-01","output_modalities":"text","tool_call":true,"vendor":"moonshot","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"kimi-k2-turbo-preview","model_name":"Kimi K2 Turbo Preview","developer_id":15,"desc":"The kimi-k2-turbo-preview model is a high-speed version of kimi-k2, with the same model parameters as kimi-k2, but the output speed has been increased from 10 tokens per second to 40 tokens per second.","pricing":{"cache_read":0.3,"input":1.2,"output":4.8},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":8192,"context_length":262144,"release_date":"2025-07-08","last_updated":"2025-07-08","output_modalities":"text","tool_call":true,"vendor":"moonshot","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"alicloud-kimi-k2-instruct","model_name":"Alicloud Kimi K2 Instruct","developer_id":15,"desc":"Kimi-K2 is a MoE architecture foundational model with extremely powerful coding and agent capabilities, featuring a total of 1 trillion parameters and activating 32 billion parameters. In benchmark performance tests across major categories such as general knowledge reasoning, programming, mathematics, and agents, the K2 model outperforms other mainstream open-source models.\nThe Kimi-K2 model supports a context length of 128k tokens.\nIt does not support visual capabilities.","pricing":{"input":0.548,"output":2.192},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-ocr","model_name":"DeepSeek Ocr","developer_id":7,"desc":"DeepSeek-OCR is a vision-language model launched by DeepSeek AI, focusing on optical character recognition (OCR) and “contextual optical compression.” The model is designed to explore the limits of compressing contextual information from images, efficiently processing documents and converting them into structured text formats such as Markdown. The model requires an image as input.","pricing":{"input":0.02,"output":0.02},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"ocr","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":8000,"release_date":"2025-10-20","last_updated":"2025-10-20","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"ernie-5.0-thinking-exp","model_name":"ERNIE 5.0 Thinking Exp","developer_id":25,"desc":"ERNIE 5.0 is the next-generation natively multimodal foundation model in the ERNIE family. Built on a unified multimodal architecture, it jointly learns from text, images, audio, and video to deliver broad multimodal capabilities.\n\nERNIE 5.0 features significantly upgraded core capabilities and shows strong performance across benchmarks, with notable gains in multimodal understanding, instruction following, creative writing, factual accuracy, and agent planning with tool use.","pricing":{"cache_read":0.82192,"input":0.82192,"output":3.28768,"tiers":[{"cache_read":1.36986,"input":1.36986,"output":5.47944,"tier":{"size":32000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.82192,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":1.36986,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.28768,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":5.47944,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.82192,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.36986,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}}],"has_zdr_provider":false,"types":"llm","features":"thinking","input_modalities":"text","endpoints":"","max_output":65536,"context_length":119000,"output_modalities":"text","reasoning":true,"vendor":"baidu","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"flux-kontext-max","model_name":"Flux Kontext Max","developer_id":27,"desc":"","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"image","cost_usd":0.08,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-05-29","last_updated":"2025-05-29","output_modalities":"image","schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-2.5-flash-image-preview","model_name":"Gemini 2.5 Flash Image Preview","developer_id":8,"desc":"Aihubmix supports the gemini-2.5-flash-image-preview model; you can add extra parameters modalities=[\"text\", \"image\"] through the OpenAI-compatible chat interface; https://docs.aihubmix.com/en/api/Gemini-Guides#gemini-2-5-flash%3A-quick-task-support","pricing":{"input":0.3,"output":1.2},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.499,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"input_image_tokens","unit":"million_tokens","cost_usd":0.3,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_image_tokens","unit":"million_tokens","cost_usd":30,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.3,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"image,text","endpoints":"","max_output":8000,"context_length":32800,"output_modalities":"image","schema_checked":false,"retire_stage":"active"},{"model_id":"glm-4.5","model_name":"GLM 4.5","developer_id":5,"desc":"GLM-4.5","pricing":{"input":0.4,"output":1.6},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":98304,"context_length":131072,"release_date":"2025-07-28","last_updated":"2025-07-28","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-4.1","model_name":"GPT 4.1","developer_id":12,"desc":"The latest flagship multimodal model supports million-token context, with encoding capability (SWE-bench 54.6%) and instruction-following (Scale AI 38.3%) performance significantly surpassing GPT-4o, while reducing costs by 26%, making it suitable for complex tasks. Its automatic caching mechanism offers a 75% cost reduction on cache hits.","pricing":{"cache_read":0.5,"input":2,"output":8},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":8,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.025,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,long_context","input_modalities":"text,image,pdf","endpoints":"","max_output":32768,"context_length":1047576,"release_date":"2025-04-14","last_updated":"2025-04-14","output_modalities":"text","tool_call":true,"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-4.1-mini","model_name":"GPT 4.1 Mini","developer_id":12,"desc":"Lightweight, high-performance model with million-token context and near-flagship-level encoding and image understanding capabilities, while reducing costs by 83%. It is suitable for rapid development and small to medium-sized applications. The automatic caching mechanism provides a 75% cost reduction on cache hits.","pricing":{"cache_read":0.1,"input":0.4,"output":1.6},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.1,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.6,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.4,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.025,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,long_context","input_modalities":"text,image,pdf","endpoints":"","max_output":32768,"context_length":1047576,"release_date":"2025-04-14","last_updated":"2025-04-14","output_modalities":"text","tool_call":true,"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"aihubmix-router","model_name":"Aihubmix Router","developer_id":12,"desc":"New model routing capability; request aihubmix-router to automatically route models based on question complexity, so everyone no longer needs to manually switch models; in our tests comparing the use of the model router versus only using GPT-4.1, we observed up to 60% cost savings while maintaining similar accuracy.  \nThe context length of the model router depends on the base model used for each prompt. Input size is 200,000, output size is 32,768.  \nCurrently, there are four routing models: gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, o4-mini.  \nPricing: Due to our current billing structure system, requests through aihubmix-router are billed at the price of gpt-4.1-mini regardless of which final model is used; future billing will be based on the actual model invoked.  \nEveryone is welcome to try it out; the interface will return the name of the actual called model.","pricing":{"cache_read":0.1,"input":0.4,"output":1.6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-4.1-nano","model_name":"GPT 4.1 Nano","developer_id":12,"desc":"Ultra-lightweight model with million-token context, optimized for speed and low latency, costing only $0.10 per million input tokens. It is suitable for edge computing and real-time interaction. The automatic caching mechanism offers a 75% cost reduction on cache hits.","pricing":{"cache_read":0.025,"input":0.1,"output":0.4},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.025,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.4,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.1,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs,long_context","input_modalities":"text,image,pdf","endpoints":"","max_output":32768,"context_length":1047576,"release_date":"2025-04-14","last_updated":"2025-04-14","output_modalities":"text","tool_call":true,"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-2.5-pro-preview-05-06","model_name":"Gemini 2.5 Pro Preview 05-06","developer_id":8,"desc":"gemini-2.5-pro latest model","pricing":{"cache_read":0.125,"input":1.25,"output":10,"tiers":[{"cache_read":0.25,"input":2.5,"output":15,"tier":{"size":200000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":4.5,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.25,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":15,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.035,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,long_context","input_modalities":"text,image,video,audio,pdf","endpoints":"","max_output":65536,"context_length":1048576,"release_date":"2025-05-07","last_updated":"2025-05-07","output_modalities":"text","reasoning":true,"vendor":"google","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-2.5-pro-preview-03-25","model_name":"Gemini 2.5 Pro Preview 03-25","developer_id":8,"desc":"Supports high concurrency.  \nThe Gemini 2.5 Pro preview version is here, with higher limits for production testing.  \nGoogle's latest and most powerful model;","pricing":{"cache_read":0.125,"input":1.25,"output":10,"tiers":[{"cache_read":0.25,"input":2.5,"output":15,"tier":{"size":200000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":4.5,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.25,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":15,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.035,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs,long_context","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-03-25","last_updated":"2025-03-25","output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-2.5-pro-preview-05-06-search","model_name":"Gemini 2.5 Pro Preview 05-06 Search","developer_id":8,"desc":"Integrated with Google's official search function.","pricing":{"cache_read":0.125,"input":1.25,"output":10,"tiers":[{"cache_read":0.25,"input":2.5,"output":15,"tier":{"size":200000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":4.5,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.25,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":15,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.035,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm,search","features":"thinking,web","input_modalities":"text,image,audio,video","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-05-07","last_updated":"2025-05-07","output_modalities":"text","reasoning":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-2.5-pro-preview-03-25-search","model_name":"Gemini 2.5 Pro Preview 03-25 Search","developer_id":8,"desc":"Integrated with Google's official search function.","pricing":{"cache_read":0.125,"input":1.25,"output":10,"tiers":[{"cache_read":0.25,"input":2.5,"output":15,"tier":{"size":200000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":4.5,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.25,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":15,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.035,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm,search","features":"thinking,web,tools,function_calling,structured_outputs,long_context","input_modalities":"text,image,audio,video","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-03-25","last_updated":"2025-03-25","output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-max-preview","model_name":"Qwen3 Max Preview","developer_id":13,"desc":"Qwen3-Max-Preview is the latest preview model in the Qwen3 series. This version is functionally equivalent to Qwen3-Max-Thinking — simply set extra_body={\"enable_thinking\": True} to enable the thinking mode. Compared to the Qwen2.5 series, it delivers significant improvements in overall general capabilities, including English–Chinese text understanding, complex instruction following, open-ended reasoning, multilingual processing, and tool-use proficiency. The model also exhibits fewer hallucinations and stronger overall reliability.","pricing":{"cache_read":0.1692,"input":0.846,"output":3.384,"tiers":[{"cache_read":0.2816,"input":1.408,"output":5.632,"tier":{"size":32000,"type":"context"}},{"cache_read":0.42256,"input":2.1128,"output":8.4512,"tier":{"size":128000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":1.0575,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":32000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":1.76,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":2.641,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.1692,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.2816,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.42256,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.384,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":5.632,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":8.4512,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.846,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.408,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2.1128,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"web_search_requests","unit":"request","cost_usd":0.000548,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-01-01","last_updated":"2025-01-01","output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-next-80b-a3b-thinking","model_name":"Qwen3 Next 80B A3B Thinking","developer_id":13,"desc":"Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that excels by outputting structured 'thinking' traces (Chain-of-Thought) by default.\n\nDesigned for hard, multi-step problems, it is ideal for tasks like math proofs, code synthesis, logic puzzles, and agentic planning. Compared to other Qwen3 variants, it offers greater stability during long reasoning chains and is tuned to follow complex instructions without getting repetitive or off-task.\n\nThis model is perfectly suited for agent frameworks, tool use (function calling), and benchmarks where a step-by-step breakdown is required. It leverages throughput-oriented techniques for fast generation of detailed, procedural outputs.","pricing":{"input":0.142,"output":1.42},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":32768,"context_length":256000,"release_date":"2025-09","last_updated":"2025-09","output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-235b-a22b-instruct-2507","model_name":"Qwen3 235B A22B Instruct 2507","developer_id":13,"desc":"Qwen3-235B-A22B-Instruct-2507","pricing":{"input":0.28,"output":1.12},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":16384,"context_length":262144,"release_date":"2025-07-21","last_updated":"2025-07-21","output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-235b-a22b-thinking-2507","model_name":"Qwen3 235B A22B Thinking 2507","developer_id":13,"desc":"The open-source thinking model based on Qwen3 has significantly improved in logical ability, general capability, knowledge enhancement, and creative ability compared to the previous version (Tongyi Qianwen 3-235B-A22B). It is suitable for high-difficulty and strong reasoning scenarios.","pricing":{"input":0.28,"output":2.8},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":131072,"context_length":262144,"release_date":"2025-07-25","last_updated":"2025-07-25","output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-coder-30b-a3b-instruct","model_name":"Qwen3 Coder 30B A3B Instruct","developer_id":13,"desc":"The code generation model based on Qwen3 has powerful Coding Agent capabilities, achieving state-of-the-art performance compared to open-source models.The model adopts tiered pricing.","pricing":{"input":0.2,"output":0.8,"tiers":[{"input":0.308218,"output":1.232872,"tier":{"size":32000,"type":"context"}},{"input":1.027396,"output":5.13698,"tier":{"size":128000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":200000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.821912,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.232872,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":5.13698,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":200000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.205478,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.308218,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.027396,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":200000}}],"has_zdr_provider":true,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":262000,"context_length":262144,"release_date":"2025-04","last_updated":"2025-04","output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-coder-480b-a35b-instruct","model_name":"Qwen3 Coder 480B A35B Instruct","developer_id":13,"desc":"The code generation model based on Qwen3 has powerful Coding Agent capabilities, achieving state-of-the-art performance compared to open-source models.The model adopts tiered pricing.","pricing":{"input":0.82,"output":3.28,"tiers":[{"input":1.232876,"output":4.931504,"tier":{"size":32000,"type":"context"}},{"input":2.054794,"output":8.219176,"tier":{"size":128000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":200000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.287664,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":4.931504,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":8.219176,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":200000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.821916,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.232876,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2.054794,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":200000}}],"has_zdr_provider":true,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":65536,"context_length":262000,"release_date":"2025-04","last_updated":"2025-04","output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-coder-flash","model_name":"Qwen3 Coder Flash","developer_id":13,"desc":"Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling and environment interaction, combining coding proficiency with versatile general-purpose abilities.","pricing":{"input":0.136,"output":0.544,"tiers":[{"input":0.205478,"output":0.821912,"tier":{"size":32000,"type":"context"}},{"input":0.342464,"output":1.369856,"tier":{"size":128000,"type":"context"}},{"input":0.68493,"output":3.42465,"tier":{"size":256000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier4","min_tokens":256001,"max_tokens":1000000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.547944,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.821912,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.369856,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.42465,"source":"billing_config","tier":{"name":"tier4","min_tokens":256001,"max_tokens":1000000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.136986,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.205478,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.342464,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.68493,"source":"billing_config","tier":{"name":"tier4","min_tokens":256001,"max_tokens":1000000}}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":65536,"context_length":1000000,"release_date":"2025-07-28","last_updated":"2025-07-28","output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-coder-plus","model_name":"Qwen3 Coder Plus","developer_id":13,"desc":"The code generation model based on Qwen3 has powerful Coding Agent capabilities, excels in tool invocation and environment interaction, and can achieve autonomous programming with outstanding coding abilities while also possessing general capabilities.The model adopts tiered pricing.","pricing":{"cache_read":0.108,"input":0.54,"output":2.16,"tiers":[{"input":0.821916,"output":3.287664,"tier":{"size":32000,"type":"context"}},{"input":1.369862,"output":5.479448,"tier":{"size":128000,"type":"context"}},{"input":2.739726,"output":27.39726,"tier":{"size":256000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier4","min_tokens":256001,"max_tokens":1000000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.191776,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.287664,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":5.479448,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":27.39726,"source":"billing_config","tier":{"name":"tier4","min_tokens":256001,"max_tokens":1000000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.547944,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.821916,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.369862,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2.739726,"source":"billing_config","tier":{"name":"tier4","min_tokens":256001,"max_tokens":1000000}}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":65536,"context_length":1048576,"release_date":"2025-07-23","last_updated":"2025-07-23","output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-coder-plus-2025-07-22","model_name":"Qwen3 Coder Plus 2025 07-22","developer_id":13,"desc":"The code generation model based on Qwen3 has powerful Coding Agent capabilities, excels in tool invocation and environment interaction, and can achieve autonomous programming with outstanding coding abilities while also possessing general capabilities.The model adopts tiered pricing.","pricing":{"cache_read":0.108,"input":0.54,"output":2.16,"tiers":[{"input":0.821916,"output":3.287664,"tier":{"size":32000,"type":"context"}},{"input":1.369862,"output":5.479448,"tier":{"size":128000,"type":"context"}},{"input":2.739726,"output":27.39726,"tier":{"size":256000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier4","min_tokens":256001,"max_tokens":1000000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.191776,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.287664,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":5.479448,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":27.39726,"source":"billing_config","tier":{"name":"tier4","min_tokens":256001,"max_tokens":1000000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.547944,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.821916,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.369862,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2.739726,"source":"billing_config","tier":{"name":"tier4","min_tokens":256001,"max_tokens":1000000}}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":65536,"context_length":128000,"output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-2.5-pro-preview-06-05-search","model_name":"Gemini 2.5 Pro Preview 06-05 Search","developer_id":8,"desc":"Integrated with Google's official search function.","pricing":{"cache_read":0.125,"input":1.25,"output":10,"tiers":[{"cache_read":0.25,"input":2.5,"output":15,"tier":{"size":200000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":4.5,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.25,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":15,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.035,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm,search","features":"thinking,web,tools,function_calling,structured_outputs,long_context","input_modalities":"text,image,audio,video","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-06-05","last_updated":"2025-06-05","output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"jina-embeddings-v5-text-nano","model_name":"Jina Embeddings V5 Text Nano","developer_id":22,"desc":"A 3.8-billion-parameter general vector model (embedding model) for state-of-the-art multilingual embeddings for edge deployment.","pricing":{"input":0.05,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"jina-embeddings-v5-text-small","model_name":"Jina Embeddings V5 Text Small","developer_id":22,"desc":"A 3.8-billion-parameter general vector (embedding) model providing state-of-the-art multilingual embeddings with task-specific adapters.","pricing":{"input":0.05,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"LongCat-Flash-Chat","model_name":"Longcat Flash Chat","developer_id":28,"desc":"Meituan has officially released and open-sourced LongCat-Flash-Chat, which utilizes an innovative Mixture of Experts (MoE) and \"zero-computation expert\" mechanism to achieve a total of 560B parameters, while only activating around 27B parameters per token as needed. At the same time, end-to-end optimization for agents (including a self-built evaluation set and multi-agent trajectory data) significantly enhances its performance in tool usage and complex task orchestration.","pricing":{"input":0.14,"output":0.7},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-11-05","last_updated":"2025-11-05","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"ernie-5.0-thinking-preview","model_name":"ERNIE 5.0 Thinking Preview","developer_id":25,"desc":"The new generation Wenxin model, Wenxin 5.0, is a native full-modal large model that adopts native full-modal unified modeling technology, jointly modeling text, images, audio, and video, possessing comprehensive full-modal capabilities. Wenxin 5.0's basic abilities are comprehensively upgraded, performing excellently on benchmark test sets, especially in multimodal understanding, instruction compliance, creative writing, factual accuracy, intelligent agent planning, and tool application.","pricing":{"cache_read":0.822,"input":0.822,"output":3.288,"tiers":[{"cache_read":1.36986,"input":1.36986,"output":5.47944,"tier":{"size":32000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.82192,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":1.36986,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.28768,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":5.47944,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.82192,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.36986,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}}],"has_zdr_provider":false,"types":"llm","features":"thinking,structured_outputs,function_calling","input_modalities":"text","endpoints":"","max_output":64000,"context_length":183000,"release_date":"2025-11-18","last_updated":"2025-11-18","output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"inclusionAI/Ling-1T","model_name":"Ling 1t","developer_id":29,"desc":"Ling-1T is the first flagship non-thinking model in the “Ling 2.0” series, featuring 1 trillion total parameters and approximately 50 billion active parameters per token. Built on the Ling 2.0 architecture, Ling-1T is designed to push the limits of efficient inference and scalable cognition. Ling-1T-base was pretrained on over 20 trillion high-quality, reasoning-intensive tokens, supports up to a 128K context length, and incorporates an Evolutionary Chain of Thought (Evo-CoT) process during mid-stage and post-stage training. This training regimen greatly enhances the model’s efficiency and depth of reasoning, enabling Ling-1T to achieve top performance across multiple complex reasoning benchmarks, balancing accuracy and efficiency.","pricing":{"input":0.548,"output":2.192},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"inclusionAI/Ring-1T","model_name":"Ring 1t","developer_id":29,"desc":"Ring-1T is an open-source idea model with a trillion parameters released by the Bailing team. It is based on the Ling 2.0 architecture and the Ling-1T-base foundational model for training, with a total parameter count of 1 trillion, an active parameter count of 50 billion, and supports up to a 128K context window. The model is trained via large-scale verifiable reward reinforcement learning (RLVR), combined with the self-developed Icepop reinforcement learning stabilization method and the efficient ASystem reinforcement learning system, significantly improving the model’s deep reasoning and natural language reasoning capabilities. Ring-1T achieves leading performance among open-source models on high-difficulty reasoning benchmarks such as mathematics competitions (e.g., IMO 2025), code generation (e.g., ICPC World Finals 2025), and logical reasoning.","pricing":{"input":0.548,"output":2.192},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"gte-rerank-v2","model_name":"Gte Rerank V2","developer_id":13,"desc":"gte-rerank-v2 is a multilingual unified text ranking model developed by Tongyi Lab, covering multiple major languages worldwide and providing high-quality text ranking services. It is typically used in scenarios such as semantic retrieval and RAG, and can simply and effectively improve text retrieval performance. Given a query and a set of candidate texts (documents), the model ranks the candidates from highest to lowest based on their semantic relevance to the query.","pricing":{"input":0.11,"output":0.11},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"rerank","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"inclusionAI/Ling-flash-2.0","model_name":"Ling Flash 2.0","developer_id":29,"desc":"Ling-flash-2.0 is a language model from inclusionAI with a total of 100 billion parameters, of which 6.1 billion are activated per token (4.8 billion non-embedding). As part of the Ling 2.0 architecture series, it is designed as a lightweight yet powerful Mixture-of-Experts (MoE) model. It aims to deliver performance comparable to or even exceeding that of 40B-level dense models and other larger MoE models, but with a significantly smaller active parameter count. The model represents a strategy focused on achieving high performance and efficiency through extreme architectural design and training methods.","pricing":{"input":0.136,"output":0.544},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"inclusionAI/Ling-mini-2.0","model_name":"Ling Mini 2.0","developer_id":29,"desc":"Ling-mini-2.0 is a small-sized, high-performance large language model based on the MoE architecture. It has a total of 16 billion parameters, but only activates 1.4 billion parameters per token (non-embedding 789 million), achieving extremely high generation speed. Thanks to the efficient MoE design and large-scale high-quality training data, despite activating only 1.4 billion parameters, Ling-mini-2.0 still demonstrates top-tier performance on downstream tasks comparable to dense LLMs under 10 billion parameters and even larger-scale MoE models.","pricing":{"input":0.068,"output":0.272},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"inclusionAI/Ring-flash-2.0","model_name":"Ring Flash 2.0","developer_id":29,"desc":"Ring-flash-2.0 is a high-performance thinking model deeply optimized based on the Ling-flash-2.0-base. It uses a mixture-of-experts (MoE) architecture with a total of 100 billion parameters, but only activates 6.1 billion parameters per inference. The model employs the original Icepop algorithm to solve the instability issues of large MoE models during reinforcement learning (RL) training, enabling its complex reasoning capabilities to continuously improve over long training cycles. Ring-flash-2.0 has achieved significant breakthroughs on multiple high-difficulty benchmarks, including mathematics competitions, code generation, and logical reasoning. Its performance not only surpasses top dense models under 40 billion parameters but also rivals larger open-source MoE models and closed-source high-performance thinking models. Although the model focuses on complex reasoning, it also performs exceptionally well on creative writing tasks. Furthermore, thanks to its efficient architecture, Ring-flash-2.0 delivers high performance with low-latency inference, significantly reducing deployment costs in high-concurrency scenarios.","pricing":{"input":0.136,"output":0.544},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"jina-deepsearch-v1","model_name":"Jina Deepsearch V1","developer_id":22,"desc":"DeepSearch combines search, reading, and reasoning capabilities to pursue the best possible answer. It's fully compatible with OpenAI's Chat API format—just replace api.openai.com with aihubmix.com to get started.  \nThe stream will return the thinking process.","pricing":{"input":0.05,"output":0.05},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm,search","features":"thinking,web,deepsearch","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":1000000,"output_modalities":"text","reasoning":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"jina-embeddings-v4","model_name":"Jina Embeddings V4","developer_id":22,"desc":"A general-purpose vector model with 3.8 billion parameters, used for multimodal and multilingual retrieval, supporting both unidirectional and multi-vector embedding outputs.","pricing":{"input":0.05,"output":0.05},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"jina-reranker-v3","model_name":"Jina Reranker V3","developer_id":22,"desc":"Multimodal multilingual document reranker, 131K context, 0.6B parameters, for visual document sorting.","pricing":{"input":0.05,"output":0.05},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"rerank","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":131072,"schema_checked":false,"retire_stage":"active"},{"model_id":"llama-4-maverick","model_name":"Llama 4 Maverick","developer_id":11,"desc":"Llama 4 Maverick is a high-capacity Mixture-of-Experts (MoE) model from Meta, featuring 400B total parameters and 128 experts, while activating an efficient 17B parameters per inference. Engineered for peak performance, it excels at advanced multimodal tasks.\n\nMaverick natively supports text and image input, producing multilingual text and code. With a 1-million-token context window and instruction tuning, it is optimized for complex image reasoning and general-purpose assistant-like interactions.\n\nReleased under the Llama 4 Community License, Maverick is ideal for research and commercial applications demanding state-of-the-art multimodal understanding and high throughput.","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":32000,"context_length":1048576,"release_date":"2025-04-05","last_updated":"2025-04-05","output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"llama-4-scout","model_name":"Llama 4 Scout","developer_id":11,"desc":"Llama 4 Scout is a highly efficient Mixture-of-Experts (MoE) model from Meta, activating 17B out of 109B total parameters per inference. It natively supports multimodal input (text and image) and multilingual output (text and code) across 12 languages.\n\nDesigned for assistant-style interaction and visual reasoning, Scout features a massive 10-million-token context window. It is instruction-tuned for tasks like multilingual chat and image understanding and is released under the Llama 4 Community License for local or commercial deployment.","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":131000,"context_length":131072,"release_date":"2025-04-05","last_updated":"2025-04-05","output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"bce-reranker-base","model_name":"Bce Reranker Base","developer_id":13,"desc":"Based on the dense foundational model of the Qwen3 series, it is specifically designed for ranking tasks. It inherits the base model’s outstanding multilingual capabilities, long-text understanding, and reasoning skills, achieving significant advancements in ranking tasks.","pricing":{"input":0.068,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"rerank","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"codex-mini-latest","model_name":"Codex Mini","developer_id":12,"desc":"Only supports v1/responses API calls.https://docs.aihubmix.com/en/api/Responses-API\ncodex-mini-latest is a fine-tuned version of o4-mini specifically for use in Codex CLI. For direct use in the API, we recommend starting with gpt-4.1.","pricing":{"cache_read":0.375,"input":1.5,"output":6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-image","model_name":"Qwen Image","developer_id":13,"desc":"Qwen-Image is a foundational image generation model in the Qwen series, achieving significant progress in complex text rendering and precise image editing. Experiments show that the model has strong general capabilities in image generation and editing, especially excelling in Chinese text rendering.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"image","cost_usd":0.036,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-08-07","last_updated":"2025-08-07","output_modalities":"image","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-image-edit","model_name":"Qwen Image Edit","developer_id":13,"desc":"Qwen-Image-Edit is the image editing version of Qwen-Image. Based on the 20B Qwen-Image model, Qwen-Image-Edit successfully extends Qwen-Image's unique text rendering capabilities to image editing tasks, achieving precise text editing. Additionally, Qwen-Image-Edit can input the same image into Qwen2.5-VL (for visual semantic control) and the VAE encoder (for visual appearance control), enabling both semantic and appearance editing functionalities.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"image","cost_usd":0.042,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-08-19","last_updated":"2025-08-19","output_modalities":"image","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-image-max","model_name":"Qwen Image Max","developer_id":13,"desc":"Qwen-Image-Edit is the image editing version of Qwen-Image. Based on the 20B Qwen-Image model, Qwen-Image-Edit successfully extends Qwen-Image's unique text rendering capabilities to image editing tasks, achieving precise text editing. Additionally, Qwen-Image-Edit can input the same image into Qwen2.5-VL (for visual semantic control) and the VAE encoder (for visual appearance control), enabling both semantic and appearance editing functionalities.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"image","cost_usd":0.0704,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"image","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-mt-plus","model_name":"Qwen Mt Plus","developer_id":13,"desc":"Based on the comprehensive upgrade of Qwen3, this flagship translation large model supports bidirectional translation across 92 languages. It offers fully enhanced model performance and translation quality, along with more stable terminology customization, format fidelity, and domain-prompting capabilities, making translations more accurate and natural.","pricing":{"input":0.492,"output":1.476},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":8000,"context_length":16000,"release_date":"2025-01","last_updated":"2025-01","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-mt-turbo","model_name":"Qwen Mt Turbo","developer_id":13,"desc":"Based on the comprehensive upgrade of Qwen3, this flagship translation large model supports bidirectional translation across 92 languages. It offers fully enhanced model performance and translation quality, along with more stable terminology customization, format fidelity, and domain-prompting capabilities, making translations more accurate and natural.","pricing":{"input":0.192,"output":0.534912},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":8000,"context_length":16000,"release_date":"2025-01","last_updated":"2025-01","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-embedding-0.6b","model_name":"Qwen3 Embedding 0.6b","developer_id":13,"desc":"The Qwen3 Embedding model series is the latest proprietary model family from Qwen, specifically designed for text embedding and ranking tasks. Based on the dense base models of the Qwen3 series, it offers comprehensive text embedding and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the excellent multilingual capabilities, long-text understanding, and reasoning skills of its base models. The Qwen3 Embedding series demonstrates significant advancements in various text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bilingual text mining.","pricing":{"input":0.068,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"embedding","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-06-03","last_updated":"2025-06-03","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-embedding-4b","model_name":"Qwen3 Embedding 4B","developer_id":13,"desc":"The Qwen3 Embedding model series is the latest proprietary model family from Qwen, specifically designed for text embedding and ranking tasks. Based on the dense base models of the Qwen3 series, it offers comprehensive text embedding and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the excellent multilingual capabilities, long-text understanding, and reasoning skills of its base models. The Qwen3 Embedding series demonstrates significant advancements in various text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bilingual text mining.","pricing":{"input":0.068,"output":0.068},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-01-01","last_updated":"2025-01-01","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-embedding-8b","model_name":"Qwen3 Embedding 8B","developer_id":13,"desc":"The Qwen3 Embedding model series is the latest proprietary model family from Qwen, specifically designed for text embedding and ranking tasks. Based on the dense base models of the Qwen3 series, it offers comprehensive text embedding and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the excellent multilingual capabilities, long-text understanding, and reasoning skills of its base models. The Qwen3 Embedding series demonstrates significant advancements in various text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bilingual text mining.","pricing":{"input":0.068,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-06-05","last_updated":"2025-06-05","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-reranker-0.6b","model_name":"Qwen3 Reranker 0.6b","developer_id":13,"desc":"Based on the dense foundational model of the Qwen3 series, it is specifically designed for ranking tasks. It inherits the base model’s outstanding multilingual capabilities, long-text understanding, and reasoning skills, achieving significant advancements in ranking tasks.","pricing":{"input":0.11,"output":0.11},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"rerank","features":"","input_modalities":"text,image","endpoints":"","max_output":8000,"context_length":16000,"release_date":"2025-06-03","last_updated":"2025-06-03","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-reranker-4b","model_name":"Qwen3 Reranker 4B","developer_id":13,"desc":"Based on the dense foundational model of the Qwen3 series, it is specifically designed for ranking tasks. It inherits the base model’s outstanding multilingual capabilities, long-text understanding, and reasoning skills, achieving significant advancements in ranking tasks.","pricing":{"input":0.11,"output":0.11},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"rerank","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-07-30","last_updated":"2025-07-30","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-reranker-8b","model_name":"Qwen3 Reranker 8B","developer_id":13,"desc":"Based on the dense foundational model of the Qwen3 series, it is specifically designed for ranking tasks. It inherits the base model’s outstanding multilingual capabilities, long-text understanding, and reasoning skills, achieving significant advancements in ranking tasks.","pricing":{"input":0.11,"output":0.11},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"rerank","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"tao-8k","model_name":"Tao 8K","developer_id":25,"desc":"","pricing":{"input":0.068,"output":0.068},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seedream-4-0","model_name":"Doubao Seedream 4.0","developer_id":4,"desc":"Seedream 4.0 is a SOTA-level multimodal image creation model based on leading architecture. It breaks the creative boundaries of traditional text-to-image models by natively supporting text, single image, and multiple image inputs. Users can freely combine text and images to achieve various creative styles within the same model, such as multi-image fusion creation based on subject consistency, image editing, and set image generation, making image creation more flexible and controllable.\nSeedream 4.0 supports composite editing with up to 10 images in a single input. Through deep reasoning of prompt words, it automatically adapts the optimal image aspect ratio and generation quantity, enabling continuous output of up to 15 content-related images at one time. Additionally, the model significantly improves the accuracy and content diversity of Chinese generation, supports 4K ultra-high-definition output, and provides a one-stop solution from generation to editing for professional image creation.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"image","cost_usd":0.028,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"image","schema_checked":false,"retire_stage":"active"},{"model_id":"embedding-v1","model_name":"Embedding V1","developer_id":25,"desc":"Embedding-V1 is a text representation model based on Baidu's Wenxin large model technology, capable of converting text into numerical vector forms for applications such as text retrieval, information recommendation, and knowledge mining. Embedding-V1 provides an Embeddings interface that generates corresponding vector representations based on the input content. By calling this interface, you can input text into the model and obtain the corresponding vector representations for subsequent text processing and analysis.","pricing":{"input":0.068,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"ernie-4.5-turbo-latest","model_name":"ERNIE 4.5 Turbo","developer_id":25,"desc":"Wenxin 4.5 Turbo also has significant improvements in hallucination reduction, logical reasoning, and coding capabilities. Compared to Wenxin 4.5, it is faster and more affordable.","pricing":{"input":0.11,"output":0.44},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":12000,"context_length":135000,"output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"glm-4.5-x","model_name":"GLM 4.5 X","developer_id":5,"desc":"GLM-4.5-X is the high-speed version of GLM-4.5, offering powerful performance with a generation speed of up to 100 tokens per second.","pricing":{"cache_read":0.44,"input":2.2,"output":8.91},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-07-28","last_updated":"2025-07-28","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gme-qwen2-vl-2b-instruct","model_name":"Gme Qwen2 VL 2B Instruct","developer_id":13,"desc":"The GME-Qwen2VL series is a unified multimodal Embedding model trained based on the Qwen2-VL multimodal large language model (MLLMs). The GME model supports three types of inputs: text, images, and image-text pairs. All these input types can generate universal vector representations and exhibit excellent retrieval performance.","pricing":{"input":0.138,"output":0.138},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"text,image,video","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"jina-clip-v2","model_name":"Jina Clip V2","developer_id":22,"desc":"Multi-modal Embeddings Model, multilingual, 1024-dimensional, 865M parameters.","pricing":{"input":0.05,"output":0.05},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"jina-reranker-m0","model_name":"Jina Reranker M0","developer_id":22,"desc":"Multimodal multilingual document reranker, 10K context, 2.4B parameters, for visual document sorting.","pricing":{"input":0.05,"output":0.05},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"rerank","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"jina-colbert-v2","model_name":"Jina Colbert V2","developer_id":22,"desc":"Multi-language ColBERT embeddings model, 560M parameters, used for embedding and reranking.","pricing":{"input":0.05,"output":0.05},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding,rerank","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-4o-search-preview","model_name":"GPT 4o Search Preview","developer_id":12,"desc":"Using the Chat Completions API, you can directly access the fine-tuned models and tool used by Search in ChatGPT.\n\nWhen using Chat Completions, the model always retrieves information from the web before responding to your query. To use web_search_preview as a tool that models like gpt-4o and gpt-4o-mini invoke only when necessary, switch to using the Responses API.\n\nCurrently, you need to use one of these models to use web search in Chat Completions:\n\ngpt-4o-search-preview\ngpt-4o-mini-search-preview\nWeb search parameter example\nimport OpenAI from \"openai\";\nconst client = new OpenAI();\n\nconst completion = await client.chat.completions.create({\n    model: \"gpt-4o-search-preview\",\n    web_search_options: {},\n    messages: [{\n        \"role\": \"user\",\n        \"content\": \"What was a positive news story from today?\"\n    }],\n});\n\nconsole.log(completion.choices[0].message.content);\nOutput and citations\nThe API response item in the choices array will include:\n\nmessage.content with the text result from the model, inclusive of any inline citations\nannotations with a list of cited URLs\nBy default, the model's response will include inline citations for URLs found in the web search results. In addition to this, the url_citation annotation object will contain the URL and title of the cited source, as well as the start and end index characters in the model's response where those sources were used.","pricing":{"cache_read":1.25,"input":2.5,"output":10},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm,search","features":"web,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":16384,"context_length":128000,"output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-4o-mini-search-preview","model_name":"GPT 4o Mini Search Preview","developer_id":12,"desc":"Using the Chat Completions API, you can directly access the fine-tuned models and tool used by Search in ChatGPT.\n\nWhen using Chat Completions, the model always retrieves information from the web before responding to your query. To use web_search_preview as a tool that models like gpt-4o and gpt-4o-mini invoke only when necessary, switch to using the Responses API.\n\nCurrently, you need to use one of these models to use web search in Chat Completions:\n\ngpt-4o-search-preview\ngpt-4o-mini-search-preview\nWeb search parameter example\nimport OpenAI from \"openai\";\nconst client = new OpenAI();\n\nconst completion = await client.chat.completions.create({\n    model: \"gpt-4o-search-preview\",\n    web_search_options: {},\n    messages: [{\n        \"role\": \"user\",\n        \"content\": \"What was a positive news story from today?\"\n    }],\n});\n\nconsole.log(completion.choices[0].message.content);\nOutput and citations\nThe API response item in the choices array will include:\n\nmessage.content with the text result from the model, inclusive of any inline citations\nannotations with a list of cited URLs\nBy default, the model's response will include inline citations for URLs found in the web search results. In addition to this, the url_citation annotation object will contain the URL and title of the cited source, as well as the start and end index characters in the model's response where those sources were used.","pricing":{"cache_read":0.075,"input":0.15,"output":0.6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm,search","features":"web,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":16384,"context_length":128000,"output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"jina-embeddings-v3","model_name":"Jina Embeddings V3","developer_id":22,"desc":"Text Embeddings Model, multilingual, 1024-dimensional, 570M parameters.","pricing":{"input":0.05,"output":0.05},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"mimo-v2-flash-free","model_name":"MiMo V2 Flash (free)","developer_id":31,"desc":"MiMo-V2-Flash is an open-source foundation language model developed by Xiaomi. It adopts a MoE architecture with 309B total parameters and 15B active parameters per inference, balancing performance and efficiency. The model features a hybrid attention architecture, supports a hybrid-thinking toggle, and offers a 256K context window, enabling strong capabilities in complex reasoning, code generation, and agent-based scenarios. On SWE-bench Verified and SWE-bench Multilingual, MiMo-V2-Flash ranks #1 among open-source models globally, delivering performance comparable to Claude Sonnet 4.5 while costing only about 3.5% as much.","pricing":{"input":0,"output":0},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"web","input_modalities":"text","endpoints":"","max_output":65536,"context_length":256000,"release_date":"2025-12-16","last_updated":"2025-12-16","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"ernie-4.5","model_name":"ERNIE 4.5","developer_id":25,"desc":"Wenxin Large Model 4.5 is a next-generation native multimodal foundational model independently developed by Baidu. It achieves collaborative optimization through joint modeling of multiple modalities, demonstrating excellent multimodal understanding capabilities; it possesses more advanced language abilities, with comprehensive improvements in comprehension, generation, logic, and memory, as well as significant enhancements in hallucination reduction, logical reasoning, and coding capabilities.ERNIE-4.5-21B-A3B is an aligned open-source model with a MoE structure, having a total of 21 billion parameters and 3 billion activated parameters.","pricing":{"input":0.068,"output":0.272},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":64000,"context_length":160000,"output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"ernie-4.5-turbo-vl","model_name":"ERNIE 4.5 Turbo VL","developer_id":25,"desc":"The new version of the Wenxin Yiyan large model significantly improves capabilities in image understanding, creation, translation, and coding. It supports a context length of up to 32K tokens for the first time, with a notable reduction in the latency of the first token.","pricing":{"input":0.4,"output":1.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":16000,"context_length":139000,"output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"FLUX-1.1-pro","model_name":"Flux 1.1 Pro","developer_id":27,"desc":"FLUX-1.1-pro is an AI image generation tool for professional creators and content workflows. It understands complex semantic and structural instructions to deliver high consistency, multi-image coherence, and style customization from text prompts.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"image","cost_usd":0.04,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"image","schema_checked":false,"retire_stage":"active"},{"model_id":"o3-mini","model_name":"O3 Mini","developer_id":12,"desc":"OpenAI's latest fast inference model excels at STEAM tasks and offers exceptional cost-effectiveness. Official support for cache hits reduces input prices by half.","pricing":{"cache_read":0.55,"input":1.1,"output":4.4},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.55,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":4.4,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.1,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking","input_modalities":"text,image","endpoints":"","max_output":100000,"context_length":200000,"release_date":"2024-12-20","last_updated":"2024-12-20","output_modalities":"text","reasoning":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seed-1-6","model_name":"Doubao Seed 1.6","developer_id":4,"desc":"Doubao-Seed-1.6 is a brand new multimodal deep reasoning model that supports four types of reasoning effort: minimal, low, medium, and high. It offers stronger model performance, serving complex tasks and challenging scenarios. It supports a 256k context window, with output length up to a maximum of 32k tokens.","pricing":{"cache_read":0.036,"input":0.18,"output":1.8,"tiers":[{"cache_read":0.021863,"input":0.164384,"output":2.191239,"tier":{"size":32000,"type":"context"}},{"cache_read":0.022027,"input":0.328768,"output":3.28768,"tier":{"size":128000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":0.002329,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.021918,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.021863072,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.022027456,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.0959,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.19123872,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.28768,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.10959,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.164384,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.328768,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,video","endpoints":"","max_output":32000,"context_length":256000,"release_date":"2025-10-15","last_updated":"2025-10-15","output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seed-1-6-flash","model_name":"Doubao Seed 1.6 Flash","developer_id":4,"desc":"Doubao-Seed-1.6-flash is an extremely fast multimodal deep thinking model, with TPOT requiring only 10ms. It supports both text and visual understanding, with its text comprehension skills surpassing the previous generation lite model and its visual understanding on par with competitor's pro series models. It supports a 256k context window and an output length of up to 16k tokens.","pricing":{"cache_read":0.0088,"input":0.044,"output":0.44,"tiers":[{"cache_read":0.00411,"input":0.041096,"output":0.41096,"tier":{"size":32000,"type":"context"}},{"cache_read":0.00411,"input":0.082192,"output":0.82192,"tier":{"size":128000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":0.002329,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0041096,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0041096,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0041096,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.20548,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.41096,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.82192,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.020548,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.041096,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.082192,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,video","endpoints":"","max_output":33000,"context_length":256000,"release_date":"2025-08-28","last_updated":"2025-08-28","output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seed-1-6-lite","model_name":"Doubao Seed 1.6 Lite","developer_id":4,"desc":"Doubao-Seed-1.6-lite is a brand new multimodal deep reasoning model that supports adjustable reasoning effort, with four modes: Minimal, Low, Medium, and High. It offers better cost performance, making it the best choice for common tasks, with a context window of up to 256k.","pricing":{"cache_read":0.0164,"input":0.082,"output":0.656,"tiers":[{"cache_read":0.00822,"input":0.0822,"output":0.548027,"tier":{"size":32000,"type":"context"}},{"cache_read":0.00822,"input":0.1644,"output":1.644,"tier":{"size":128000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":0.002329,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0082192,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.00822,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.00822,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.328768,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.5480274,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.644,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.041096,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.0822,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.1644,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,video","endpoints":"","max_output":32000,"context_length":256000,"output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seed-1-6-thinking","model_name":"Doubao Seed 1.6 Thinking","developer_id":4,"desc":"The Doubao-Seed-1.6-thinking model has significantly enhanced reasoning capabilities. Compared with Doubao-1.5-thinking-pro, it has further improvements in fundamental abilities such as coding, mathematics, and logical reasoning, and now also supports visual understanding. It supports a 256k context window, with output length supporting up to 16k tokens.","pricing":{"cache_read":0.036,"input":0.18,"output":1.8,"tiers":[{"cache_read":0.021863,"input":0.164384,"output":2.191239,"tier":{"size":32000,"type":"context"}},{"cache_read":0.022027,"input":0.328768,"output":3.28768,"tier":{"size":128000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":0.002329,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.021918,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.021863072,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.022027456,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.0959,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.19123872,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.28768,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.10959,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.164384,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.328768,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image,video","endpoints":"","max_output":32000,"context_length":256000,"output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-30b-a3b-instruct-2507","model_name":"Qwen3 30B A3B Instruct 2507","developer_id":13,"desc":"Significantly improved performance on reasoning tasks, including logical reasoning, mathematics, science, coding, and academic benchmarks that typically require human expertise.\nMarkedly better general capabilities, such as instruction following, tool usage, text generation, and alignment with human preferences.\nEnhanced 256K long-context understanding capabilities.","pricing":{"input":0.1028,"output":0.4112},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-07-30","last_updated":"2025-07-30","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-30b-a3b-thinking-2507","model_name":"Qwen3 30B A3B Thinking 2507","developer_id":13,"desc":"Significantly improved performance on reasoning tasks, including logical reasoning, mathematics, science, coding, and academic benchmarks that typically require human expertise.\nMarkedly better general capabilities, such as instruction following, tool usage, text generation, and alignment with human preferences.\nEnhanced 256K long-context understanding capabilities.","pricing":{"input":0.12,"output":1.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-08-28","last_updated":"2025-08-28","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-3-235b-a22b-thinking-2507","model_name":"Qwen 3 235B A22B Thinking 2507","developer_id":13,"desc":"cerebras","pricing":{"input":0.28,"output":2.8},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-oss-120b","model_name":"gpt-oss-120b","developer_id":12,"desc":"gpt-oss-120b is a 117B-parameter open-weight Mixture-of-Experts (MoE) language model from OpenAI, designed for high-reasoning, agentic, and general-purpose production use cases. Activating just 5.1B parameters per pass, it is optimized to run on a single H100 GPU with native MXFP4 quantization. The model features configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.","pricing":{"input":0.18,"output":0.9},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"thinking,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":32768,"context_length":131072,"release_date":"2025-08-05","last_updated":"2025-08-05","output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"Qwen2-VL-72B-Instruct","model_name":"Qwen2 VL 72B Instruct","developer_id":13,"desc":"The model provider is the Sophnet platform. Qwen2-VL-72B-Instruct is the latest iteration in the Qwen2-VL series launched by Alibaba Cloud, representing nearly a year of innovative achievements. This model has 72 billion parameters and can understand images of various resolutions and aspect ratios. Additionally, it supports video understanding of over 20 minutes, enabling high-quality video question answering, dialogue, and content creation, along with complex reasoning and decision-making capabilities.\n\n- State-of-the-art image understanding: capable of processing images of various resolutions and aspect ratios, performing excellently across multiple visual understanding benchmarks.\n- Long video understanding: supports video comprehension exceeding 20 minutes, enabling high-quality video Q\u0026A, dialogues, and content creation.\n- Agent operation capability: equipped with complex reasoning and decision-making abilities, it can integrate with devices such as phones and robots to perform automated operations based on visual environments and textual instructions.\n- Multilingual support: in addition to English and Chinese, it supports understanding text in images in multiple languages, including most European languages, Japanese, Korean, Arabic, Vietnamese, and more.\n- Supports a maximum context length of 128K tokens, offering powerful processing capabilities.","pricing":{"input":2.18,"output":6.54},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image,video","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Qwen2-VL-7B-Instruct","model_name":"Qwen2 VL 7B Instruct","developer_id":13,"desc":"The model provider is the Sophnet platform. Qwen2-VL-7B-Instruct is the latest vision-language model launched by Alibaba Cloud and the newest member of the Qwen family. This model is proficient not only in recognizing common objects but also in analyzing text, charts, icons, and layouts within images. As a visual agent, it can reason and dynamically guide tool usage, supporting operations on computers and mobile phones. Additionally, it can understand long videos exceeding one hour and capture key events, accurately locate objects in images, and generate structured outputs for data such as invoices and tables, making it suitable for various scenarios including finance and business.\n\n- Vision understanding capability: not only recognizes common objects but also analyzes text, charts, icons, and layouts within images.\n- Agent capability: functions as a visual agent capable of reasoning and dynamically guiding tool usage, supporting operations on computers and mobile phones.\n- Long video understanding: can comprehend video content over one hour in length and accurately localize relevant video segments.\n- Visual localization: precisely locates objects within images by generating bounding boxes or points, providing stable JSON coordinate outputs.\n- Structured output: supports structured data output for invoices, tables, and other data, suitable for finance, business, and various other scenarios.","pricing":{"input":0.28,"output":0.7},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image,video","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"cc-kimi-for-coding","model_name":"CC Kimi For Coding","developer_id":15,"desc":"for claude code","pricing":{"cache_read":0.02,"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-embedding-001","model_name":"Gemini Embedding 001","developer_id":8,"desc":"Latest version","pricing":{"input":0.15,"output":0.15},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-05-20","last_updated":"2025-05-20","schema_checked":false,"retire_stage":"active"},{"model_id":"Qwen/Qwen3-30B-A3B","model_name":"Qwen3 30B A3B","developer_id":13,"desc":"Provided by chutes.ai","pricing":{"input":1,"output":1},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Qwen/Qwen3-32B","model_name":"Qwen3 32B","developer_id":13,"desc":"","pricing":{"input":0.4,"output":0.8},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-32b","model_name":"Qwen3 32B","developer_id":13,"desc":"","pricing":{"input":0.16,"output":0.64},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-04","last_updated":"2025-04","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Qwen/Qwen3-14B","model_name":"Qwen3 14B","developer_id":13,"desc":"Provided by chutes.ai","pricing":{"input":0.5,"output":0.5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Qwen/Qwen3-8B","model_name":"Qwen3 8B","developer_id":13,"desc":"Provided by chutes.ai","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"embedding-2","model_name":"Embedding 2","developer_id":5,"desc":"A text vector model that converts input text information into vector representations so that, in conjunction with a vector database, it provides an external knowledge base for the large model, thereby improving the accuracy of the model’s reasoning.","pricing":{"input":0.0686,"output":0.0686},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"embedding","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":8000,"schema_checked":false,"retire_stage":"active"},{"model_id":"embedding-3","model_name":"Embedding 3","developer_id":5,"desc":"A text vector model that converts input text into vector representations to work with a vector database and provide an external knowledge base for a large model. The model supports custom vector dimensions; it is recommended to choose 256, 512, 1024, or 2048 dimensions.","pricing":{"input":0.0686,"output":0.0686},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"embedding","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":8000,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-2.5-pro-preview-06-05","model_name":"Gemini 2.5 Pro Preview 06-05","developer_id":8,"desc":"Google’s latest multimodal flagship model, combining exceptional coding and reasoning capabilities. Its massive 1 million token context window (soon to expand to 2 million) places it at the top of the WebDevArena and LMArena leaderboards. It is particularly well-suited for developing aesthetically pleasing and highly functional interactive web applications, code transformation, and complex workflows. The newly introduced \"reasoning budget\" feature cleverly balances cost and performance, while optimized tool calls and response styles further enhance development efficiency, making it the ideal choice for rapid prototyping and advanced coding.","pricing":{"cache_read":0.125,"input":1.25,"output":10,"tiers":[{"cache_read":0.25,"input":2.5,"output":15,"tier":{"size":200000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":4.5,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.25,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":15,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.035,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs,long_context","input_modalities":"text,image,audio,video","endpoints":"","max_output":65536,"context_length":1048576,"release_date":"2025-06-05","last_updated":"2025-06-05","output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"Qwen/Qwen2.5-VL-72B-Instruct","model_name":"Qwen2.5 VL 72B Instruct","developer_id":13,"desc":"Qwen2.5-VL is a visual language model from the Qwen2.5 series, equipped with strong visual understanding and reasoning capabilities. It can recognize objects, analyze text and charts, understand key events in long videos, and accurately locate targets within images. The model supports structured output, making it suitable for data such as invoices and forms, and performs excellently in multiple benchmark tests.","pricing":{"input":0.5,"output":0.5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image,video","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"o1","model_name":"O1","developer_id":12,"desc":"OpenAI's most powerful O-series model supports official cache hits that halve the input cost.","pricing":{"cache_read":7.5,"input":15,"output":60},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":7.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":60,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":15,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-12-05","last_updated":"2024-12-05","output_modalities":"text","reasoning":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"o1-pro","model_name":"O1 Pro","developer_id":12,"desc":"The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide consistently better answers.","pricing":{"cache_read":170,"input":170,"output":680},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":150,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":600,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":150,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-03-19","last_updated":"2025-03-19","output_modalities":"text","reasoning":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"ByteDance-Seed/Seed-OSS-36B-Instruct","model_name":"Seed Oss 36B Instruct","developer_id":4,"desc":"Seed-OSS is a series of open-source large language models developed by ByteDance's Seed team, designed specifically for powerful long-context processing, reasoning, agents, and general capabilities. Among this series, Seed-OSS-36B-Instruct is an instruction-tuned model with 36 billion parameters that natively supports ultra-long context lengths, enabling it to process massive documents or complex codebases in a single pass. This model is specially optimized for reasoning, code generation, and agent tasks (such as tool usage), while maintaining balanced and excellent general capabilities. A notable feature of this model is the \"Thinking Budget\" functionality, which allows users to flexibly adjust the inference length as needed, thereby effectively improving inference efficiency in practical applications.","pricing":{"input":0.2,"output":0.534},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":32000,"context_length":256000,"output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seed-1-6-250615","model_name":"Doubao Seed 1.6 250615","developer_id":4,"desc":"Doubao-Seed-1.6 is a brand new multimodal deep reasoning model that supports four types of reasoning effort: minimal, low, medium, and high. It offers stronger model performance, serving complex tasks and challenging scenarios. It supports a 256k context window, with output length up to a maximum of 32k tokens.","pricing":{"cache_read":0.036,"input":0.18,"output":2.52,"tiers":[{"cache_read":0.021863,"input":0.164384,"output":2.191239,"tier":{"size":32000,"type":"context"}},{"cache_read":0.022027,"input":0.328768,"output":3.28768,"tier":{"size":128000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":0.002329,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.021918,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.021863072,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.022027456,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.0959,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.19123872,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.28768,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.10959,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.164384,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.328768,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-06-15","last_updated":"2025-06-15","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seed-1-6-flash-250615","model_name":"Doubao Seed 1.6 Flash 250615","developer_id":4,"desc":"Doubao-Seed-1.6-flash is an extremely fast multimodal deep thinking model, with TPOT requiring only 10ms. It supports both text and visual understanding, with its text comprehension skills surpassing the previous generation lite model and its visual understanding on par with competitor's pro series models. It supports a 256k context window and an output length of up to 16k tokens.","pricing":{"cache_read":0.0088,"input":0.044,"output":0.44,"tiers":[{"cache_read":0.00411,"input":0.041096,"output":0.41096,"tier":{"size":32000,"type":"context"}},{"cache_read":0.00411,"input":0.082192,"output":0.82192,"tier":{"size":128000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":0.002329,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0041096,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0041096,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0041096,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.20548,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.41096,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.82192,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.020548,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.041096,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.082192,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-06-15","last_updated":"2025-06-15","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seed-1-6-thinking-250615","model_name":"Doubao Seed 1.6 Thinking 250615","developer_id":4,"desc":"The Doubao-Seed-1.6-thinking model has significantly enhanced reasoning capabilities. Compared with Doubao-1.5-thinking-pro, it has further improvements in fundamental abilities such as coding, mathematics, and logical reasoning, and now also supports visual understanding. It supports a 256k context window, with output length supporting up to 16k tokens.","pricing":{"cache_read":0.036,"input":0.18,"output":2.52,"tiers":[{"cache_read":0.021863,"input":0.164384,"output":2.191239,"tier":{"size":32000,"type":"context"}},{"cache_read":0.022027,"input":0.328768,"output":3.28768,"tier":{"size":128000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":0.002329,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.021918,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.021863072,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.022027456,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.0959,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.19123872,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.28768,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.10959,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.164384,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.328768,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-06-15","last_updated":"2025-06-15","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seed-1-6-vision-250815","model_name":"Doubao Seed 1.6 Vision 250815","developer_id":4,"desc":"Doubao-Seed-1.6-vision is a visual deep-thinking model that demonstrates stronger general multimodal understanding and reasoning capabilities in scenarios such as education, image moderation, inspection and security, and AI search Q\u0026A. It supports a 256K context window and an output length of up to 64K tokens.","pricing":{"cache_read":0.021918,"input":0.10959,"output":1.0959,"tiers":[{"cache_read":0.021863,"input":0.164384,"output":2.191239,"tier":{"size":32000,"type":"context"}},{"cache_read":0.022027,"input":0.328768,"output":3.28768,"tier":{"size":128000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":0.002329,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.021918,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.021863072,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.022027456,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.0959,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.19123872,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.28768,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.10959,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.164384,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.328768,"source":"billing_config","tier":{"name":"tier3","min_tokens":128001,"max_tokens":256000}}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-08-15","last_updated":"2025-08-15","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-ai/DeepSeek-Prover-V2-671B","model_name":"DeepSeek Prover V2 671B","developer_id":7,"desc":"Provided by chutes.ai\nDeepSeek Prover V2 is a 671B parameter model, speculated to be geared towards logic and mathematics. Likely an upgrade from DeepSeek-Prover-V1.5 Not much is known about the model yet, as DeepSeek released it on Hugging Face without an announcement or description.","pricing":{"input":0.1,"output":0.1},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-2.5-flash-preview-tts","model_name":"Gemini 2.5 Flash Preview Tts","developer_id":8,"desc":"Gemini 2.5 Flash Preview TTS is a lightweight, low-latency text-to-speech model designed for real-time voice generation. It produces natural, expressive speech with accurate control over tone, style, and pacing, while dynamically adjusting speaking speed based on context and instructions. The model also maintains consistent and distinguishable voices across multi-turn and multi-speaker conversations, making it well-suited for interactive and conversational applications that require stable, high-quality audio output.","pricing":{"input":0.5,"output":0.5},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_audio_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"tts","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-05-01","last_updated":"2025-05-01","output_modalities":"audio","schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-2.5-pro-preview-tts","model_name":"Gemini 2.5 Pro Preview Tts","developer_id":8,"desc":"Gemini 2.5 Pro Preview TTS is a high-fidelity text-to-speech model designed for premium voice experiences and complex speech generation scenarios. It delivers highly natural and expressive audio with precise control over tone, style, and emotional nuance, while maintaining smooth, context-aware pacing across long-form content. The model excels in multi-speaker and dialogue-heavy use cases, preserving consistent character voices and conversational coherence, making it well-suited for narration, storytelling, and advanced conversational AI applications.","pricing":{"input":1,"output":1},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_audio_tokens","unit":"million_tokens","cost_usd":20,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"tts","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-05-01","last_updated":"2025-05-01","output_modalities":"audio","schema_checked":false,"retire_stage":"active"},{"model_id":"gemma-3-12b-it","model_name":"Gemma 3 12B It","developer_id":8,"desc":"Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone.","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-03-13","last_updated":"2025-03-13","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gemma-3-27b-it","model_name":"Gemma 3 27B It","developer_id":8,"desc":"Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone.","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-03-12","last_updated":"2025-03-12","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gemma-3-4b-it","model_name":"Gemma 3 4B It","developer_id":8,"desc":"Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone.","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-03-13","last_updated":"2025-03-13","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gemma-3n-e4b-it","model_name":"Gemma 3n E4B It","developer_id":8,"desc":"Gemma 3n is a generative AI model optimized for use in everyday devices, such as phones, laptops, and tablets. This model includes innovations in parameter-efficient processing, including Per-Layer Embedding (PLE) parameter caching and a MatFormer model architecture that provides the flexibility to reduce compute and memory requirements. These models feature audio input handling, as well as text and visual data.","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-05-20","last_updated":"2025-05-20","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Doubao-1.5-thinking-pro","model_name":"Doubao 1.5 Thinking Pro","developer_id":4,"desc":"Doubao-1.5 is a brand-new deep thinking model that excels in specialized fields such as mathematics, programming, scientific reasoning, and general tasks like creative writing. It achieves or approaches the top-tier industry level on multiple authoritative benchmarks including AIME 2024, Codeforces, and GPQA. It supports a 128k context window and 16k output.","pricing":{"input":0.62,"output":2.48},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.191784,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.547946,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-08-05","last_updated":"2025-08-05","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"cc-minimax-m2","model_name":"CC MiniMax M2","developer_id":18,"desc":"For Claude Code only","pricing":{"input":0.1,"output":0.1},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemma-3-1b-it","model_name":"Gemma 3 1B It","developer_id":8,"desc":"Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone.","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-r1-distill-llama-70b","model_name":"DeepSeek R1 Distill Llama 70B","developer_id":7,"desc":"Provided by Groq, the DeepSeek-R1-Distill model is fine-tuned based on an open-source model, using samples generated by DeepSeek-R1. We have made slight modifications to their configurations and tokenizers. Please use our settings to run these models.","pricing":{"input":0.8,"output":1.6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-01-23","last_updated":"2025-01-23","output_modalities":"text","reasoning":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-4o-mini-tts","model_name":"GPT 4o Mini Tts","developer_id":12,"desc":"OpenAI’s latest TTS model, gpt-4o-mini-tts, uses the same API endpoint (/v1/audio/speech) as tts-1. However, OpenAI introduced a new pricing method without providing billing details via API, causing discrepancies between official pricing and aihubmix’s charges—some requests may cost more, others less. Avoid using this model if precise billing accuracy is essential.","pricing":{"input":0.6,"output":12},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.6,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"output_audio_tokens","unit":"million_tokens","cost_usd":12,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.6,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"tts","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"audio","vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"tngtech/DeepSeek-R1T-Chimera","model_name":"DeepSeek R1t Chimera","developer_id":7,"desc":"Provided by chutes.ai\nDeepSeek-R1T-Chimera merges DeepSeek-R1’s reasoning strengths with DeepSeek-V3 (0324)’s token-efficiency improvements into a MoE Transformer optimized for general text generation. It integrates pretrained weights from both models and is released under the MIT license for research and commercial use.\n","pricing":{"input":0.02,"output":0.02},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"o1-preview","model_name":"O1 Preview","developer_id":12,"desc":"The latest and most powerful inference model from OpenAI; AiHubMix uses both OpenAI and Microsoft Azure OpenAI channels simultaneously to achieve high-concurrency load balancing.","pricing":{"cache_read":7.5,"input":15,"output":60},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","reasoning":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"o1-mini","model_name":"O1 Mini","developer_id":12,"desc":"o1-mini is faster and 80% cheaper, and is competitive with o1-preview on coding tasks. AiHubMix uses both OpenAI and Microsoft Azure OpenAI channels simultaneously.","pricing":{"cache_read":1.5,"input":3,"output":12},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.55,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":4.4,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.1,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-01-01","last_updated":"2025-01-01","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-4o-2024-11-20","model_name":"GPT 4o 2024 11-20","developer_id":12,"desc":"The latest version of the GPT-4o model; it is recommended to use this version, as it is currently smarter than the regular 4o.","pricing":{"cache_read":1.25,"input":2.5,"output":10},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":16384,"context_length":128000,"release_date":"2024-11-20","last_updated":"2024-11-20","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-4o","model_name":"GPT 4o","developer_id":12,"desc":"GPT-4o (“o” stands for “omni”) is a new-generation multimodal model designed for more natural human–computer interaction. It can accept any combination of text, audio, image, and video as input, and generate multimodal outputs including text, audio, and images. With audio response latency as low as 232 milliseconds on average around 320 milliseconds, it approaches real human conversational speed. The model delivers strong performance in English text and code, significantly improved multilingual understanding, and outstanding capabilities in visual and audio perception, while offering faster API performance and substantially reduced cost for real-time and complex multimodal applications.","pricing":{"cache_read":1.25,"input":2.5,"output":10},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":1.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.025,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text,image,pdf","endpoints":"","max_output":16384,"context_length":128000,"release_date":"2024-05-13","last_updated":"2024-05-13","output_modalities":"text","tool_call":true,"vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-4o-mini","model_name":"GPT 4o Mini","developer_id":12,"desc":"The lightweight version of GPT-4o, which is affordable and fast, suitable for handling simple tasks; our site supports the official automatic caching for this model, and charges for cache hits will be automatically halved.","pricing":{"cache_read":0.075,"input":0.15,"output":0.6},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.075,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.6,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.15,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.025,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":16384,"context_length":128000,"release_date":"2024-07-18","last_updated":"2024-07-18","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"AiHubmix-mistral-medium","model_name":"Aihubmix Mistral Medium","developer_id":10,"desc":"Mistral Medium 3 is a SOTA \u0026 versatile model designed for a wide range of tasks, including programming, mathematical reasoning, understanding long documents, summarization, and dialogue.\n\nIt boasts multi-modal capabilities, enabling it to process visual inputs, and supports dozens of languages, including over 80 coding languages. Additionally, it features function calling and agentic workflows.\n\nMistral Medium 3 is optimized for single-node inference, particularly for long-context applications. Its size allows it to achieve high throughput on a single node.","pricing":{"input":0.4,"output":2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"ERNIE-X1.1-Preview","model_name":"ERNIE X1.1 Preview","developer_id":25,"desc":"The Wenxin large model X1.1 has made significant improvements in question answering, tool invocation, intelligent agents, instruction following, logical reasoning, mathematics, and coding tasks, with notable enhancements in factual accuracy. The context length has been extended to 64K tokens, supporting longer inputs and dialogue history, which improves the coherence of long-chain reasoning while maintaining response speed.","pricing":{"input":0.136,"output":0.544},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":64000,"context_length":119000,"release_date":"2025-09-10","last_updated":"2025-09-10","output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"Qwen/QwQ-32B","model_name":"QwQ 32B","developer_id":13,"desc":"Silicon-based flow provision","pricing":{"input":0.14,"output":0.56},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"chutesai/Mistral-Small-3.1-24B-Instruct-2503","model_name":"Mistral Small 3.1 24B Instruct 2503","developer_id":10,"desc":"Mistral's latest open-source small model; provided by chutes.ai.","pricing":{"input":0.2,"output":0.8},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"ernie-x1.1-preview","model_name":"ERNIE X1.1 Preview","developer_id":25,"desc":"The Wenxin large model X1.1 has made significant improvements in question answering, tool invocation, intelligent agents, instruction following, logical reasoning, mathematics, and coding tasks, with notable enhancements in factual accuracy. The context length has been extended to 64K tokens, supporting longer inputs and dialogue history, which improves the coherence of long-chain reasoning while maintaining response speed.","pricing":{"input":0.136,"output":0.544},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-09-10","last_updated":"2025-09-10","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"ernie-4.5-0.3b","model_name":"ERNIE 4.5 0.3b","developer_id":25,"desc":"Wenxin Large Model 4.5 is a next-generation native multimodal foundational large model independently developed by Baidu. It achieves collaborative optimization through joint modeling of multiple modalities, demonstrating excellent multimodal understanding capabilities. The model possesses enhanced language abilities, with comprehensive improvements in understanding, generation, reasoning, and memory. It significantly reduces hallucinations and shows notable advancements in logical reasoning and coding skills.","pricing":{"input":0.0136,"output":0.0544},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"ernie-4.5-turbo-128k-preview","model_name":"ERNIE 4.5 Turbo 128K Preview","developer_id":25,"desc":"Wenxin 4.5 Turbo also shows significant enhancements in reducing hallucinations, logical reasoning, and coding capabilities. Compared to Wenxin 4.5, it is faster and more cost-effective.","pricing":{"input":0.108,"output":0.432},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"ernie-x1-turbo","model_name":"ERNIE X1 Turbo","developer_id":25,"desc":"Wenxin Large Model X1 possesses enhanced abilities in understanding, planning, reflection, and evolution. As a more comprehensive deep-thinking model, Wenxin X1 combines accuracy, creativity, and literary elegance, excelling particularly in Chinese knowledge Q\u0026A, literary creation, document writing, daily conversations, logical reasoning, complex calculations, and tool invocation.","pricing":{"input":0.136,"output":0.544},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":28000,"context_length":50500,"output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"llama-3.3-70b","model_name":"Llama 3.3 70B","developer_id":11,"desc":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks.","pricing":{"input":0.6,"output":0.6},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":8192,"context_length":65536,"release_date":"2024-12-06","last_updated":"2024-12-06","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"moonshotai/Kimi-Dev-72B","model_name":"Kimi Dev 72B","developer_id":15,"desc":"Kimi-Dev-72B is a new generation open-source programming large model that achieved a leading performance of 60.4% on SWE-bench Verified. Through large-scale reinforcement learning optimization, it can automatically fix code in real Docker environments, receiving rewards only when passing the complete test suite, thereby ensuring the correctness and robustness of solutions and aligning more closely with real software development standards.","pricing":{"input":0.32,"output":1.28},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"moonshotai/Moonlight-16B-A3B-Instruct","model_name":"Moonlight 16B A3B Instruct","developer_id":15,"desc":"Provided by chutes.ai.","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"nvidia-nemotron-3-super-120b-a12b","model_name":"Nvidia Nemotron 3 Super 120B A12B","developer_id":17,"desc":"An open-source, efficient hybrid Mamba-Transformer MoE model that supports a context length of one million tokens and excels at agent reasoning, programming, planning, and tool invocation.","pricing":{"cache_read":0.0275,"input":0.11,"output":0.55},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs,long_context","input_modalities":"text","endpoints":"","max_output":0,"context_length":1000000,"release_date":"2026-03-11","last_updated":"2026-03-11","output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"o1-global","model_name":"O1 Global","developer_id":1,"desc":"OpenAI new model","pricing":{"cache_read":7.5,"input":15,"output":60},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qianfan-qi-vl","model_name":"Qianfan Qi VL","developer_id":25,"desc":"The Qianfan-QI-VL model is a proprietary image quality inspection and visual understanding large model (Quality Inspection Large Vision Language Model, Qianfan-QI-VL) developed by Baidu Cloud’s Qianfan platform. It is designed for quality inspection of product images uploaded in e-commerce scenarios, with detection capabilities including AIGC human defect detection, mosaic recognition, watermark recognition, and trademark detection.","pricing":{"input":0.2,"output":0.6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen2.5-vl-72b-instruct","model_name":"Qwen2.5 VL 72B Instruct","developer_id":13,"desc":"Strong capability in Chinese domain recognition, comparable to ChatGPT-4.0.","pricing":{"input":2.4,"output":7.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-02-01","last_updated":"2025-02-01","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"tencent/Hunyuan-A13B-Instruct","model_name":"Hunyuan A13B Instruct","developer_id":24,"desc":"Hunyuan-A13B-Instruct has 8 billion parameters and can match larger models by activating only 1.3 billion parameters, supporting \"fast thinking/slow thinking\" hybrid inference. It offers stable long text understanding. Verified by BFCL-v3 and τ-Bench, its Agent capabilities are leading in the field. Combined with GQA and multiple quantization formats, it enables efficient inference.","pricing":{"input":0.14,"output":0.56},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"unsloth/gemma-3-27b-it","model_name":"Gemma 3 27B It","developer_id":8,"desc":"Google's latest open-source model; provided by chutes.ai","pricing":{"input":0.22,"output":0.22},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"MiniMaxAI/MiniMax-M1-80k","model_name":"MiniMax M1 80K","developer_id":18,"desc":"MiniMax-M1 is an open-source large-scale hybrid attention model with 456B total parameters (45.9B activated per token). It natively supports 1M-token context and reduces FLOPs by 75% versus DeepSeek R1 in 100K-token generation tasks via lightning attention. Built on MoE architecture and optimized by CISPO algorithm, it achieves state-of-the-art performance in long-context reasoning and real-world software engineering scenarios.","pricing":{"input":0.6,"output":2.4},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Qwen/Qwen2.5-VL-32B-Instruct","model_name":"Qwen2.5 VL 32B Instruct","developer_id":13,"desc":"Qwen2.5-VL-32B-Instruct is an advanced multimodal model from the Tongyi Qianwen team that can recognize objects, analyze text and graphics in images, operate tools, locate objects in images, and generate structured outputs. Through reinforcement learning, it has improved mathematics and problem-solving capabilities, with a more concise and natural response style.","pricing":{"input":0.24,"output":0.24},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text,image,video","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"baidu/ERNIE-4.5-300B-A47B","model_name":"ERNIE 4.5 300B A47B","developer_id":25,"desc":"ERNIE-4.5-300B-A47B is a large language model developed by Baidu based on a Mixture of Experts (MoE) architecture. The model has a total of 300 billion parameters, but only activates 47 billion parameters per token during inference, which balances strong performance with computational efficiency. As one of the core models in the ERNIE 4.5 series, it demonstrates outstanding capabilities in tasks such as text understanding, generation, reasoning, and programming. The model employs an innovative multimodal heterogeneous MoE pretraining approach, leveraging joint training of textual and visual modalities to effectively enhance the model’s overall abilities, particularly excelling in instruction following and world knowledge memorization. Baidu has open-sourced this model along with other models in the series, aiming to promote the research and application of AI technology.","pricing":{"input":0.32,"output":1.28},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"bge-large-en","model_name":"Bge Large En","developer_id":30,"desc":"bge-large-en, open-sourced by the Beijing Academy of Artificial Intelligence (BAAI), is currently the most powerful vector representation model for Chinese tasks, with its semantic representation capabilities comprehensively surpassing those of similar open-source models.","pricing":{"input":0.068,"output":0.068},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"bge-large-zh","model_name":"Bge Large Zh","developer_id":30,"desc":"bge-large-zh, open-sourced by the Beijing Academy of Artificial Intelligence (BAAI), is currently the most powerful vector representation model for Chinese tasks, with its semantic representation capabilities comprehensively surpassing those of similar open-source models.","pricing":{"input":0.068,"output":0.068},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"codestral-latest","model_name":"Codestral","developer_id":10,"desc":"Mistral has launched a new code model - Codestral 25.01; https://mistral.ai/news/codestral-2501/","pricing":{"input":0.4,"output":1.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-05-29","last_updated":"2024-05-29","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-exp-1206","model_name":"Gemini","developer_id":8,"desc":"Google's latest experimental model, currently Google's most powerful model.","pricing":{"input":1.25,"output":5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-12-06","last_updated":"2024-12-06","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-4o-zh","model_name":"GPT 4o Zh","developer_id":12,"desc":"","pricing":{"input":2.5,"output":10},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-qwq-32b","model_name":"Qwen Qwq 32B","developer_id":13,"desc":"","pricing":{"input":0.4,"output":0.8},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"unsloth/gemma-3-12b-it","model_name":"Gemma 3 12B It","developer_id":8,"desc":"Provided by chutes.ai.","pricing":{"input":0.2,"output":0.8},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-max-0125","model_name":"Qwen Max 0125","developer_id":13,"desc":"Qwen 2.5-Max latest model","pricing":{"input":0.38,"output":1.52},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"tencent/Hunyuan-MT-7B","model_name":"Hunyuan Mt 7B","developer_id":24,"desc":"Hunyuan-MT-7B is a lightweight translation model with 7 billion parameters, designed to translate source text into target languages. The model supports translation among 33 languages as well as 5 Chinese minority languages. In the WMT25 International Machine Translation Competition, Hunyuan-MT-7B achieved first place in 30 out of 31 language categories it participated in, demonstrating its exceptional translation capabilities. For translation scenarios, Tencent Hunyuan proposed a complete training paradigm from pre-training to supervised fine-tuning, followed by translation reinforcement and ensemble reinforcement, enabling it to achieve industry-leading performance among models of similar scale. The model is computationally efficient, easy to deploy, and suitable for various application scenarios.","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"BAAI/bge-large-en-v1.5","model_name":"Bge Large En V1.5","developer_id":30,"desc":"BAAI/bge-large-en-v1.5 is a large English text embedding model and part of the BGE (BAAI General Embedding) series. It achieves excellent performance on the MTEB benchmark, with an average score of 64.23 across 56 datasets, excelling in tasks such as retrieval, clustering, and text pair classification. The model supports a maximum input length of 512 tokens and is suitable for various natural language processing tasks, such as text retrieval and semantic similarity computation.","pricing":{"input":0.034,"output":0.034},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"BAAI/bge-large-zh-v1.5","model_name":"Bge Large Zh V1.5","developer_id":30,"desc":"BAAI/bge-large-zh-v1.5 is a large Chinese text embedding model and part of the BGE (BAAI General Embedding) series. It performs excellently on the C-MTEB benchmark, achieving an average score of 64.53 across 31 datasets, with outstanding results in tasks such as retrieval, semantic similarity, and text pair classification. The model supports a maximum input length of 512 tokens and is suitable for various Chinese natural language processing tasks, such as text retrieval and semantic similarity computation.","pricing":{"input":0.034,"output":0.034},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"kimi-thinking-preview","model_name":"Kimi Thinking Preview","developer_id":15,"desc":"The latest kimi model.","pricing":{"input":30,"output":30},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-embedding-large-text-240915","model_name":"Doubao Embedding Large Text 240915","developer_id":4,"desc":"doubao-embedding-large-text-240915\nDoubao Embedding is a semantic vectorization model developed by ByteDance, primarily designed for vector search scenarios. It supports both Chinese and English languages and has a maximum context length of approximately 4K tokens.","pricing":{"input":0.1,"output":0.1},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-09-15","last_updated":"2024-09-15","schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-4o-2024-08-06","model_name":"GPT 4o 2024 08-06","developer_id":12,"desc":"Supports caching, with automatic halving of charges upon a cache hit.","pricing":{"cache_read":1.25,"input":2.5,"output":10},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-08-06","last_updated":"2024-08-06","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-plus-2025-07-28","model_name":"Qwen Plus 2025 07-28","developer_id":13,"desc":"The Tongyi Qianwen series balanced capability model has inference performance and speed between Tongyi Qianwen-Max and Tongyi Qianwen-Turbo, making it suitable for moderately complex tasks. This model adopts tiered pricing.","pricing":{"cache_read":0.02252,"cache_write":0.14075,"input":0.1126,"output":1.126,"tiers":[{"cache_read":0.0676,"cache_write":0.4225,"input":0.338,"output":3.38,"tier":{"size":128000,"type":"context"}},{"cache_read":0.1352,"cache_write":0.845,"input":0.676,"output":9.013311,"tier":{"size":256000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.14075,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":128000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.4225,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.845,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.02252,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0676,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.1352,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.126,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.38,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":9.0133108,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.1126,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.338,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.676,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.000548,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-09-08","last_updated":"2025-09-08","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-plus-latest","model_name":"Qwen Plus","developer_id":13,"desc":"The Qwen series models with balanced capabilities have inference performance and speed between Qwen-Max and Qwen-Turbo, making them suitable for moderately complex tasks. This model is a dynamically updated version, and updates will not be announced in advance. The current version is qwen-plus-2025-04-28.The model adopts tiered pricing.","pricing":{"cache_read":0.02252,"cache_write":0.14075,"input":0.1126,"output":1.126,"tiers":[{"cache_read":0.0676,"cache_write":0.4225,"input":0.338,"output":3.38,"tier":{"size":128000,"type":"context"}},{"cache_read":0.1352,"cache_write":0.845,"input":0.676,"output":9.013311,"tier":{"size":256000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.14075,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":128000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.4225,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.845,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.02252,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0676,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.1352,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.126,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.38,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":9.0133108,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.1126,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.338,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.676,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.000548,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-09-09","last_updated":"2024-09-09","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"stepfun-ai/step3","model_name":"Step3","developer_id":16,"desc":"Step3 is a multimodal reasoning model released by StepFun. It uses a Mixture‑of‑Experts (MoE) architecture with 321 billion total parameters and 38 billion activation parameters. The model follows an end‑to‑end design that reduces decoding cost while delivering top‑tier performance on vision‑language reasoning tasks. Thanks to the combined use of Multi‑Head Factorized Attention (MFA) and Attention‑FFN Decoupling (AFD), Step3 remains highly efficient on both flagship and low‑end accelerators. During pre‑training, it processed over 20 trillion text tokens and 4 trillion image‑text mixed tokens, covering more than ten languages. On benchmarks for mathematics, code, and multimodal tasks, Step3 consistently outperforms other open‑source models.","pricing":{"input":1.1,"output":2.75},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"text-embedding-v4","model_name":"Text Embedding V4","developer_id":13,"desc":"This is the Tongyi Laboratory's multilingual unified text vector model trained based on Qwen3, which significantly improves performance in text retrieval, clustering, and classification compared to version V3; it achieves a 15% to 40% improvement on evaluation tasks such as MTEB multilingual, Chinese-English, and code retrieval; supports user-defined vector dimensions ranging from 64 to 2048.","pricing":{"input":0.08,"output":0.08},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-turbo-latest","model_name":"Qwen Turbo","developer_id":13,"desc":"The Qwen series model with the fastest speed and lowest cost, suitable for simple tasks. This model is a dynamically updated version, and updates will not be announced in advance. The model's overall Chinese and English abilities have been significantly improved, human preference alignment has been greatly enhanced, inference capability and complex instruction understanding have been substantially strengthened, performance on difficult tasks is better, and mathematics and coding skills have been significantly improved. The current version is qwen-turbo-2025-04-28.","pricing":{"cache_read":0.0092,"input":0.046,"output":0.092},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"AiHubmix-Phi-4-mini-reasoning","model_name":"Aihubmix Phi 4 Mini (reasoning)","developer_id":3,"desc":"Phi-4-mini-reasoning is a lightweight open model designed for advanced mathematical reasoning and logic-intensive problem-solving. It is particularly well-suited for tasks such as formal proofs, symbolic computation, and solving multi-step word problems. With its efficient architecture, the model balances high-quality reasoning performance with cost-effective deployment, making it ideal for educational applications, embedded tutoring, and lightweight edge or mobile systems.\n\nPhi-4-mini-reasoning supports a 128K token context length, enabling it to process and reason over long mathematical problems and proofs. Built on synthetic and high-quality math datasets, the model leverages advanced fine-tuning techniques such as supervised fine-tuning and preference modeling to enhance reasoning capabilities. Its training incorporates safety and alignment protocols, ensuring robust and reliable performance across supported use cases.","pricing":{"input":0.12,"output":0.12},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":4000,"context_length":128000,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"aihub-Phi-4-multimodal-instruct","model_name":"Aihub Phi 4 Multimodal Instruct","developer_id":3,"desc":"Microsoft's latest model","pricing":{"input":0.12,"output":0.48},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image,audio","endpoints":"","max_output":4000,"context_length":128000,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-30b-a3b","model_name":"Qwen3 30B A3B","developer_id":13,"desc":"Achieves effective integration of thinking and non-thinking modes, allowing mode switching during conversations. Its reasoning ability matches that of QwQ-32B with a smaller parameter size, and its general capability significantly surpasses Qwen2.5-14B, reaching state-of-the-art (SOTA) levels among industry models of the same scale.","pricing":{"input":0.12,"output":1.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-04-28","last_updated":"2025-04-28","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"aihub-Phi-4-mini-instruct","model_name":"Aihub Phi 4 Mini Instruct","developer_id":3,"desc":"Microsoft's latest model","pricing":{"input":0.12,"output":0.48},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":4000,"context_length":128000,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"grok-3","model_name":"Grok 3","developer_id":9,"desc":"Grok's latest model","pricing":{"input":3,"output":15},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-06-01","last_updated":"2024-06-01","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"grok-3-beta","model_name":"Grok 3 Beta","developer_id":9,"desc":"Grok's latest model\nThis model ID with beta has been officially taken offline. Using this model grok-3-beta will automatically point to grok-3.","pricing":{"input":3,"output":15},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-14b","model_name":"Qwen3 14B","developer_id":13,"desc":"Achieves effective integration of thinking and non-thinking modes, enabling mode switching during conversations. Its reasoning ability reaches state-of-the-art (SOTA) levels among models of the same scale, and its general capability significantly surpasses Qwen2.5-14B.","pricing":{"input":0.16,"output":1.6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-04","last_updated":"2025-04","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-embedding-text-240715","model_name":"Doubao Embedding Text 240715","developer_id":4,"desc":"doubao-embedding-text-240715\nDoubao Embedding is a semantic vectorization model developed by ByteDance, primarily designed for vector search scenarios. It supports both Chinese and English languages and has a maximum context length of approximately 4K tokens.","pricing":{"input":0.7,"output":0.7},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-07-15","last_updated":"2024-07-15","schema_checked":false,"retire_stage":"active"},{"model_id":"aihub-Phi-4","model_name":"Aihub Phi 4","developer_id":3,"desc":"Phi-4 is a state-of-the-art open model based on a combination of synthetic datasets, curated public domain website data, and acquired academic books and QA datasets. The approach aims to ensure that small, efficient models are trained using data focused on high quality and advanced reasoning.","pricing":{"input":0.12,"output":0.48},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":16400,"context_length":16400,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"claude-3-opus-20240229","model_name":"Claude 3 Opus 20240229","developer_id":2,"desc":"Claude’s previous generation strongest model","pricing":{"input":16.5,"output":82.5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"dall-e-3","model_name":"Dall E 3","developer_id":12,"desc":"dall-e-3 is an AI image generation model that converts natural language prompts into realistic visuals and artistic content. It delivers accurate semantic understanding, supports customizable output resolutions, and produces high-quality images across a wide range of styles, making it well-suited for concept design, creative prototyping, and professional content workflows.","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"image","cost_usd":0.04,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2023-11-06","last_updated":"2023-11-06","output_modalities":"image","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-8b","model_name":"Qwen3 8B","developer_id":13,"desc":"Achieves effective integration of thinking and non-thinking modes, enabling mode switching during conversations. Its reasoning ability reaches state-of-the-art (SOTA) levels among models of the same scale, and its general capability significantly surpasses Qwen2.5-7B.","pricing":{"input":0.08,"output":0.8},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-04","last_updated":"2025-04","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"grok-3-fast","model_name":"Grok 3 Fast","developer_id":9,"desc":"","pricing":{"input":5.5,"output":27.5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"grok-3-fast-beta","model_name":"Grok 3 Fast Beta","developer_id":9,"desc":"","pricing":{"input":5.5,"output":27.5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"grok-3-mini","model_name":"Grok 3 Mini","developer_id":9,"desc":"","pricing":{"input":0.3,"output":0.501},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-06-01","last_updated":"2024-06-01","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-4b","model_name":"Qwen3 4B","developer_id":13,"desc":"Achieves effective integration of thinking and non-thinking modes, allowing mode switching during conversations. Its reasoning ability reaches state-of-the-art (SOTA) levels among models of the same scale, with significantly enhanced human preference alignment. There are notable improvements in creative writing, role-playing, multi-turn dialogue, and instruction following, resulting in a noticeably better user experience.","pricing":{"input":0.046,"output":0.46},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-ai/DeepSeek-R1-Zero","model_name":"DeepSeek R1 Zero","developer_id":7,"desc":"Openly deployed by chutes.ai; inference with FP8; zero is the initial preliminary version of R1 without optimizations and is not recommended for use unless for research purposes.","pricing":{"input":2.2,"output":2.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"grok-3-mini-beta","model_name":"Grok 3 Mini Beta","developer_id":9,"desc":"This model ID with beta has been officially taken offline. Using this model grok-3-mini-beta will automatically point to grok-3-mini.","pricing":{"input":0.33,"output":0.5511},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-1.7b","model_name":"Qwen3 1.7b","developer_id":13,"desc":"Effectively integrates thinking and non-thinking modes, allowing mode switching during conversations. Its general capabilities significantly surpass those of the Qwen2.5 small-scale series, with greatly enhanced human preference alignment. There are notable improvements in creative writing, role-playing, multi-turn dialogue, and instruction following, resulting in a significantly better expected user experience.","pricing":{"input":0.046,"output":0.46},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-0.6b","model_name":"Qwen3 0.6b","developer_id":13,"desc":"Effectively integrates thinking and non-thinking modes, allowing mode switching during conversations. Its general capabilities significantly surpass those of the Qwen2.5 small-scale series.","pricing":{"input":0.046,"output":0.46},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-3-32b","model_name":"Qwen 3 32B","developer_id":13,"desc":"cerebras","pricing":{"input":0.4,"output":1.6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-04-28","last_updated":"2025-04-28","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-turbo-2025-04-28","model_name":"Qwen Turbo 2025 04-28","developer_id":13,"desc":"The Qwen3 series Turbo model effectively integrates thinking and non-thinking modes, allowing seamless switching between modes during conversations. With a smaller parameter size, its reasoning ability rivals that of QwQ-32B, and its general capabilities significantly surpass those of Qwen2.5-Turbo, reaching state-of-the-art (SOTA) levels among models of the same scale. This version is a snapshot model as of April 28, 2025.","pricing":{"input":0.046,"output":0.092},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"alicloud-glm-5","model_name":"Alicloud Glm 5","developer_id":5,"desc":"GLM-5 is an advanced, open-source large language model designed for developers tackling the toughest challenges. It excels at long-context reasoning, multi-step tool orchestration, and complex systems engineering, making it the ideal choice for powering sophisticated agents and applications that require high-level cognitive tasks.","pricing":{"cache_read":0.11268,"input":0.5634,"output":2.5353,"tiers":[{"cache_read":0.16892,"input":0.8446,"output":3.096869,"tier":{"size":32000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.11268,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.16892,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":200000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.5353,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.096869482,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":200000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.5634,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.8446,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":200000}}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"command-a-03-2025","model_name":"Command A 03 2025","developer_id":6,"desc":"Command A is Cohere most performant model to date, excelling at tool use, agents, retrieval augmented generation (RAG), and multilingual use cases. Command A has a context length of 256K, only requires two GPUs to run, and has 150% higher throughput compared to Command R+ 08-2024.","pricing":{"input":2.5,"output":10},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":8000,"context_length":256000,"release_date":"2025-03-13","last_updated":"2025-03-13","output_modalities":"text","vendor":"cohere","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"grok-3-mini-fast-beta","model_name":"Grok 3 Mini Fast Beta","developer_id":9,"desc":"","pricing":{"input":0.33,"output":2.20011},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-plus-2025-04-28","model_name":"Qwen Plus 2025 04-28","developer_id":13,"desc":"The Qwen3 series Plus model effectively integrates thinking and non-thinking modes, allowing for mode switching during conversations. Its reasoning abilities significantly surpass those of QwQ, and its general capabilities are markedly superior to Qwen2.5-Plus, reaching state-of-the-art (SOTA) levels among models of the same scale. This version is a snapshot model as of April 28, 2025.","pricing":{"cache_read":0.02252,"cache_write":0.14075,"input":0.1126,"output":1.126,"tiers":[{"cache_read":0.0676,"cache_write":0.4225,"input":0.338,"output":3.38,"tier":{"size":128000,"type":"context"}},{"cache_read":0.1352,"cache_write":0.845,"input":0.676,"output":9.013311,"tier":{"size":256000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.14075,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":128000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.4225,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.845,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.02252,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0676,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.1352,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.126,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.38,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":9.0133108,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.1126,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.338,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.676,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.000548,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"THUDM/GLM-Z1-32B-0414","model_name":"GLM Z1 32B 0414","developer_id":5,"desc":"GLM-Z1-32B-0414 is a reasoning-focused AI model built on GLM-4-32B-0414. It has been enhanced through cold-start methods and reinforcement learning, with a strong emphasis on math, coding, and logic tasks. Despite having only 32B parameters, it performs comparably to the 671B DeepSeek-R1 on some benchmarks. It excels in complex reasoning tasks, as shown in evaluations like AIME 24/25, LiveCodeBench, and GPQA.","pricing":{"input":0.08,"output":0.08},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Pro/THUDM/GLM-4.1V-9B-Thinking","model_name":"Thudm/glm 4.1 Vision 9B Thinking","developer_id":5,"desc":"GLM-4.1V-9B-Thinking is an open-source Vision Language Model (VLM) jointly released by Zhipu AI and the KEG Laboratory at Tsinghua University, designed specifically for handling complex multimodal cognitive tasks. Based on the GLM-4-9B-0414 foundation model, it significantly enhances cross-modal reasoning ability and stability by introducing the “Chain-of-Thought” reasoning mechanism and using reinforcement learning strategies. As a lightweight model with 9 billion parameters, it strikes a balance between deployment efficiency and performance. In 28 authoritative benchmark evaluations, it matched or even outperformed the 72-billion-parameter Qwen-2.5-VL-72B model in 18 tasks. The model excels not only in image-text understanding, mathematical and scientific reasoning, and video understanding, but also supports images up to 4K resolution and inputs of arbitrary aspect ratios.","pricing":{"input":0.04,"output":0.16},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"THUDM/GLM-4.1V-9B-Thinking","model_name":"GLM 4.1 Vision 9B Thinking","developer_id":5,"desc":"GLM-4.1V-9B-Thinking is an open-source Vision Language Model (VLM) jointly released by Zhipu AI and the KEG Laboratory at Tsinghua University, designed specifically for handling complex multimodal cognitive tasks. Based on the GLM-4-9B-0414 foundation model, it significantly enhances cross-modal reasoning ability and stability by introducing the “Chain-of-Thought” reasoning mechanism and using reinforcement learning strategies. As a lightweight model with 9 billion parameters, it strikes a balance between deployment efficiency and performance. In 28 authoritative benchmark evaluations, it matched or even outperformed the 72-billion-parameter Qwen-2.5-VL-72B model in 18 tasks. The model excels not only in image-text understanding, mathematical and scientific reasoning, and video understanding, but also supports images up to 4K resolution and inputs of arbitrary aspect ratios.","pricing":{"input":0.1,"output":0.1},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"text-embedding-004","model_name":"Text Embedding 004","developer_id":8,"desc":"","pricing":{"input":0.02,"output":0.02},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"THUDM/GLM-4-32B-0414","model_name":"GLM 4 32B 0414","developer_id":5,"desc":"GLM-4-32B-0414 is a next-generation open-source model with 32 billion parameters, delivering performance comparable to OpenAI’s GPT series and DeepSeek V3/R1. It supports smooth local deployment.\n\nThe base model was pre-trained on 15T of high-quality data, including a large amount of reasoning-focused synthetic content, setting the stage for advanced reinforcement learning.\n\nIn the post-training phase, techniques like human preference alignment, rejection sampling, and reinforcement learning were used to improve the model’s ability to follow instructions, generate code, and handle function calls—core skills needed for agent-style tasks.\n\nGLM-4-32B-0414 has shown strong results in engineering code, artifact generation, function calling, search-based QA, and report writing—sometimes matching or even surpassing larger models like GPT-4o and DeepSeek-V3 (671B) on specific benchmarks.","pricing":{"input":0.08,"output":0.08},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"THUDM/GLM-Z1-9B-0414","model_name":"GLM Z1 9B 0414","developer_id":5,"desc":"GLM-Z1-9B-0414 is a small but powerful model in the GLM series, with only 9 billion parameters. Despite its size, it delivers strong performance in math reasoning and general tasks, ranking among the best in its class of open-source models.\n\nTrained with the same techniques as larger models, it strikes an excellent balance between performance and efficiency—making it a great option for low-resource or lightweight deployment scenarios.","pricing":{"input":0.05,"output":0.05},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"THUDM/GLM-4-9B-0414","model_name":"GLM 4 9B 0414","developer_id":5,"desc":"GLM-4-9B-0414 is a lightweight model in the GLM family, with 9 billion parameters. It inherits the core tech from GLM-4-32B and offers an efficient option for deployment on limited resources.\n\nDespite its smaller size, it performs well in tasks like code generation, web design, SVG graphics creation, and search-based writing. It also supports function calling to interact with external tools, enhancing its versatility.\n\nGLM-4-9B-0414 strikes a solid balance between efficiency and performance, making it a strong choice for low-resource environments—while remaining competitive on various benchmarks.","pricing":{"input":0.05,"output":0.05},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"cc-doubao-seed-code-preview-latest","model_name":"CC Doubao Seed Code Preview","developer_id":4,"desc":"claude code ","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-seed-code-preview-latest","model_name":"Doubao Seed Code Preview","developer_id":4,"desc":"chat","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-ai/Janus-Pro-7B","model_name":"Janus Pro 7B","developer_id":7,"desc":"","pricing":{"input":2,"output":2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"image_generation,llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"image,text","schema_checked":false,"retire_stage":"active"},{"model_id":"glm-zero-preview","model_name":"GLM Zero Preview","developer_id":5,"desc":"Simply put, it is the intelligent enhanced version of O1.","pricing":{"input":2,"output":2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-3-235b-a22b-instruct-2507","model_name":"Qwen 3 235B A22B Instruct 2507","developer_id":13,"desc":"cerebras","pricing":{"input":0.28,"output":1.4},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"coding-glm-4.5-air","model_name":"Coding GLM 4.5 Air","developer_id":5,"desc":"","pricing":{"input":0.014,"output":0.084},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-07-28","last_updated":"2025-07-28","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"nvidia-llama-3.1-nemotron-70b-instruct","model_name":"Nvidia Llama 3.1 Nemotron 70B Instruct","developer_id":17,"desc":"","pricing":{"input":1.32,"output":1.32},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"nvidia-llama-3.3-nemotron-super-49b-v1.5","model_name":"Nvidia Llama 3.3 Nemotron Super 49B V1.5","developer_id":17,"desc":"","pricing":{"input":0.11,"output":0.44},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"nvidia-nemotron-3-nano-30b-a3b","model_name":"Nvidia Nemotron 3 Nano 30B A3B","developer_id":17,"desc":"","pricing":{"input":0.066,"output":0.264},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-12-15","last_updated":"2025-12-15","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"nvidia-nemotron-nano-12b-v2-vl","model_name":"Nvidia Nemotron Nano 12B V2 VL","developer_id":17,"desc":"","pricing":{"input":0.22,"output":0.66},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"nvidia-nemotron-nano-9b-v2","model_name":"Nvidia Nemotron Nano 9B V2","developer_id":17,"desc":"","pricing":{"input":0.044,"output":0.176},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-08-18","last_updated":"2025-08-18","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"o1-preview-2024-09-12","model_name":"O1 Preview 2024 09-12","developer_id":12,"desc":"","pricing":{"cache_read":7.5,"input":15,"output":60},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"deepinfra-nvidia-nemotron-3-nano-30b-a3b2","model_name":"Deepinfra Nvidia Nemotron 3 Nano 30B A3b2","developer_id":17,"desc":"","pricing":{"input":0.066,"output":0.264},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"glm-4.5-air","model_name":"GLM 4.5 Air","developer_id":5,"desc":"","pricing":{"input":0.14,"output":0.84},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":98304,"context_length":131072,"release_date":"2025-07-28","last_updated":"2025-07-28","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Qwen/QVQ-72B-Preview","model_name":"Qvq 72B Preview","developer_id":13,"desc":"","pricing":{"input":1.2,"output":1.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Qwen/QwQ-32B-Preview","model_name":"QwQ 32B Preview","developer_id":13,"desc":"","pricing":{"input":0.16,"output":0.16},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"aihubmix-Mistral-Large-2411","model_name":"Aihubmix Mistral Large 2411","developer_id":10,"desc":"The latest Mistral Large 2 model is deployed on Azure.","pricing":{"input":2,"output":6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"aihubmix-Mistral-large-2407","model_name":"Aihubmix Mistral Large 2407","developer_id":10,"desc":"","pricing":{"input":3,"output":9},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"wan2.6-t2i","model_name":"Wan2.6 T2i","developer_id":13,"desc":"","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"image","cost_usd":0.0282,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"image,text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"image","schema_checked":false,"retire_stage":"active"},{"model_id":"grok-2-1212","model_name":"Grok 2 1212","developer_id":9,"desc":"","pricing":{"input":1.8,"output":9},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"llama-3.1-70b","model_name":"Llama 3.1 70B","developer_id":11,"desc":"","pricing":{"input":0.44,"output":0.44},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-07-23","last_updated":"2024-07-23","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-image-test","model_name":"GPT Image Test","developer_id":12,"desc":"","pricing":{"input":5,"output":40},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"image","schema_checked":false,"retire_stage":"active"},{"model_id":"grok-4.20-beta-0309-non-reasoning","model_name":"Grok 4.20 Beta 0309","developer_id":9,"desc":"Grok 4.20 Beta is our latest flagship model, offering industry-leading speed and agent tool-invocation capabilities. It combines the lowest hallucination rate on the market with strict prompt adherence, enabling it to consistently deliver precise and factual responses.","pricing":{"cache_read":1,"input":2,"output":6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs,long_context","input_modalities":"text,image","endpoints":"","max_output":2000000,"context_length":2000000,"output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"grok-4.20-beta-0309-reasoning","model_name":"Grok 4.20 Beta 0309 (reasoning)","developer_id":9,"desc":"Grok 4.20 Beta is our latest flagship model, offering industry-leading speed and agent tool-invocation capabilities. It combines the lowest hallucination rate on the market with strict prompt adherence, enabling it to consistently deliver precise and factual responses.","pricing":{"cache_read":1,"input":2,"output":6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs,long_context","input_modalities":"text,image","endpoints":"","max_output":30000,"context_length":2000000,"release_date":"2026-03-16","last_updated":"2026-03-16","output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"grok-4.20-multi-agent-beta-0309","model_name":"Grok 4.20 Multi Agent Beta 0309","developer_id":9,"desc":"Grok 4.20 Beta is our latest flagship model, offering industry-leading speed and agent tool-invocation capabilities. It combines the lowest hallucination rate on the market with strict prompt adherence, enabling it to consistently deliver precise and factual responses.","pricing":{"cache_read":0.2,"input":2,"output":6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs,long_context","input_modalities":"text,image","endpoints":"","max_output":2000000,"context_length":2000000,"output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"jina-reader","model_name":"Jina Reader","developer_id":22,"desc":"","pricing":{"input":0.05,"output":0.05},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"search","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"jina-search","model_name":"Jina Search","developer_id":22,"desc":"","pricing":{"input":0.05,"output":0.05},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"search","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"llama3.1-8b","model_name":"Llama3.1 8B","developer_id":11,"desc":"cerebras","pricing":{"input":0.3,"output":0.6},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"o1-2024-12-17","model_name":"O1 2024 12-17","developer_id":12,"desc":"","pricing":{"cache_read":7.5,"input":15,"output":60},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","reasoning":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"bai-qwen3-vl-235b-a22b-instruct","model_name":"Bai Qwen3 VL 235B A22B Instruct","developer_id":13,"desc":"The Qwen3 series open-source models include hybrid models, thinking models, and non-thinking models, with both reasoning capabilities and general abilities reaching industry SOTA levels at the same scale.","pricing":{"input":0.274,"output":1.096},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"cc-MiniMax-M2","model_name":"CC MiniMax M2","developer_id":18,"desc":"For Claude Code only","pricing":{"input":0.1,"output":0.1},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"cc-deepseek-v3","model_name":"CC DeepSeek V3","developer_id":7,"desc":"For Claude code only","pricing":{"input":0.3,"output":0.3},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"cc-deepseek-v3.1","model_name":"CC DeepSeek V3.1","developer_id":7,"desc":"For Claude code only","pricing":{"input":0.56,"output":1.68},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"cc-ernie-4.5-300b-a47b","model_name":"CC ERNIE 4.5 300B A47B","developer_id":25,"desc":"For Claude code only","pricing":{"input":0.32,"output":1.28},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"cc-kimi-dev-72b","model_name":"CC Kimi Dev 72B","developer_id":15,"desc":"For Claude code only","pricing":{"input":0.32,"output":1.28},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"cc-kimi-k2-instruct","model_name":"CC Kimi K2 Instruct","developer_id":15,"desc":"For Claude code only","pricing":{"input":1.1,"output":3.3},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"cc-kimi-k2-instruct-0905","model_name":"CC Kimi K2 Instruct 0905","developer_id":15,"desc":"For Claude code only","pricing":{"input":1.1,"output":3.3},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"tools,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"cc-kimi-k2-thinking","model_name":"CC Kimi K2 Thinking","developer_id":15,"desc":"Dedicated for Claude Code","pricing":{"input":0.548,"output":2.192},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"computer-use-preview","model_name":"Computer Use Preview","developer_id":12,"desc":"","pricing":{"input":3,"output":12},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"sf-kimi-k2-thinking","model_name":"Sf Kimi K2 Thinking","developer_id":15,"desc":"","pricing":{"input":0.548,"output":2.192},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"omni-moderation-latest","model_name":"Omni Moderation","developer_id":12,"desc":"","pricing":{"input":0.02,"output":0.02},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"moderation","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-flash","model_name":"Qwen Flash","developer_id":13,"desc":"The model adopts tiered pricing.","pricing":{"input":0.02,"output":0.2,"tiers":[{"input":0.082192,"output":0.82192,"tier":{"size":128000,"type":"context"}},{"input":0.164382,"output":1.64382,"tier":{"size":256000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":1000000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.20546,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.82192,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.64382,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":1000000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.020546,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.082192,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.164382,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":1000000}}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-07-28","last_updated":"2025-07-28","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-flash-2025-07-28","model_name":"Qwen Flash 2025 07-28","developer_id":13,"desc":"The model adopts tiered pricing.","pricing":{"input":0.02,"output":0.2,"tiers":[{"input":0.08219,"output":0.8219,"tier":{"size":128000,"type":"context"}},{"input":0.164382,"output":1.64382,"tier":{"size":256000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":1000000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.20546,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.8219,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.64382,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":1000000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.020546,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.08219,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.164382,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":1000000}}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-long","model_name":"Qwen Long","developer_id":13,"desc":"","pricing":{"input":0.1,"output":0.4},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-08-01","last_updated":"2024-08-01","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-max","model_name":"Qwen Max","developer_id":13,"desc":"","pricing":{"input":0.38,"output":1.52},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-04-03","last_updated":"2024-04-03","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-max-longcontext","model_name":"Qwen Max Longcontext","developer_id":13,"desc":"","pricing":{"input":7,"output":21},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-plus","model_name":"Qwen Plus","developer_id":13,"desc":"","pricing":{"cache_read":0.02252,"cache_write":0.14075,"input":0.1126,"output":1.126,"tiers":[{"cache_read":0.0676,"cache_write":0.4225,"input":0.338,"output":3.38,"tier":{"size":128000,"type":"context"}},{"cache_read":0.1352,"cache_write":0.845,"input":0.676,"output":9.013311,"tier":{"size":256000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.14075,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":128000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.4225,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.845,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.02252,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":128000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0676,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.1352,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.126,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":128000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":3.38,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":9.0133108,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.1126,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":1,"max_tokens":128000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.338,"source":"billing_config","tier":{"name":"tier2","min_tokens":128001,"max_tokens":256000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.676,"source":"billing_config","tier":{"name":"tier3","min_tokens":256001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.000548,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-01-25","last_updated":"2024-01-25","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-turbo","model_name":"Qwen Turbo","developer_id":13,"desc":"","pricing":{"cache_read":0.0092,"input":0.046,"output":0.092},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"long_context","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-11-01","last_updated":"2024-11-01","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen-turbo-2024-11-01","model_name":"Qwen Turbo 2024 11-01","developer_id":13,"desc":"","pricing":{"input":0.046,"output":0.092},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"long_context","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen2.5-14b-instruct","model_name":"Qwen2.5 14B Instruct","developer_id":13,"desc":"","pricing":{"input":0.4,"output":1.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen2.5-32b-instruct","model_name":"Qwen2.5 32B Instruct","developer_id":13,"desc":"","pricing":{"input":0.6,"output":1.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen2.5-3b-instruct","model_name":"Qwen2.5 3B Instruct","developer_id":13,"desc":"","pricing":{"input":0.4,"output":0.8},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen2.5-72b-instruct","model_name":"Qwen2.5 72B Instruct","developer_id":13,"desc":"","pricing":{"input":0.8,"output":2.4},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-09-18","last_updated":"2024-09-18","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen2.5-7b-instruct","model_name":"Qwen2.5 7B Instruct","developer_id":13,"desc":"","pricing":{"input":0.4,"output":0.8},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-09-18","last_updated":"2024-09-18","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen2.5-coder-1.5b-instruct","model_name":"Qwen2.5 Coder 1.5b Instruct","developer_id":13,"desc":"","pricing":{"input":0.2,"output":0.4},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen2.5-coder-7b-instruct","model_name":"Qwen2.5 Coder 7B Instruct","developer_id":13,"desc":"","pricing":{"input":0.2,"output":0.4},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen2.5-math-1.5b-instruct","model_name":"Qwen2.5 Math 1.5b Instruct","developer_id":13,"desc":"","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen2.5-math-72b-instruct","model_name":"Qwen2.5 Math 72B Instruct","developer_id":13,"desc":"","pricing":{"input":0.8,"output":2.4},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen2.5-math-7b-instruct","model_name":"Qwen2.5 Math 7B Instruct","developer_id":13,"desc":"","pricing":{"input":0.2,"output":0.4},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3-235b-a22b-2507","model_name":"Qwen3 235B A22B 2507","developer_id":13,"desc":"qwen3-235b-a22b-2507 is Qwen's multilingual, instruction-tuned mixture-of-experts language model, designed for general-purpose text generation and instruction following. Built on the Qwen3-235B architecture, it utilizes 22B active parameters per forward pass and features an extensive context window of 262,144 tokens.","pricing":{"cache_read":0.07,"input":0.35,"output":1.4},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":262144,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qwen3.8-27b","model_name":"Qwen3.8 27B","developer_id":13,"desc":"qwen3.8-27b is Qwen's open-weight dense vision-language model, designed for coding, professional workflows, research, multimodal interaction, and long-running agent tasks. It supports text and image inputs with an extensive 1,000,000-token context length and flexible thinking capabilities.","pricing":{"cache_read":0.05,"input":0.2,"output":2.5},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"","input_modalities":"text,image,video","endpoints":"","max_output":131072,"context_length":1000000,"output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"],"default":"xhigh"},{"type":"budget_tokens"}],"interleaved":{"anthropic.messages":true,"openai.chat_completions":{"field":"reasoning_content"},"openai.responses":true},"vendor":"alibaba","open_weights":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"solar-pro4","model_name":"Solar Pro4","developer_id":44,"desc":"","pricing":{"cache_read":0.06,"input":0.3,"output":1.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"long_context","input_modalities":"text","endpoints":"","max_output":131072,"context_length":524288,"release_date":"2026-08-06","last_updated":"2026-08-06","output_modalities":"text","reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"],"default":"medium"}],"interleaved":{"openai.chat_completions":true},"vendor":"upstage","schema_checked":false,"promotion":{"name":"OpenRouter discount","off_percent":75,"time_type":"daily","daily":{"ranges":["00:00-23:59"]}},"retire_stage":"active"},{"model_id":"step-2-16k","model_name":"Step 2 16K","developer_id":16,"desc":"","pricing":{"input":2,"output":2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-01-01","last_updated":"2025-01-01","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"text-ada-001","model_name":"Text Ada 001","developer_id":12,"desc":"","pricing":{"input":0.4,"output":0.4},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"text-babbage-001","model_name":"Text Babbage 001","developer_id":12,"desc":"","pricing":{"input":0.5,"output":0.5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"text-curie-001","model_name":"Text Curie 001","developer_id":12,"desc":"","pricing":{"input":2,"output":2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"text-davinci-002","model_name":"Text Davinci 002","developer_id":12,"desc":"","pricing":{"input":20,"output":20},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"text-davinci-003","model_name":"Text Davinci 003","developer_id":12,"desc":"","pricing":{"input":20,"output":20},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"text-davinci-edit-001","model_name":"Text Davinci Edit 001","developer_id":12,"desc":"","pricing":{"input":20,"output":20},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"text-embedding-3-large","model_name":"Text Embedding 3 Large","developer_id":12,"desc":"","pricing":{"input":0.13,"output":0.13},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-01-25","last_updated":"2024-01-25","schema_checked":false,"retire_stage":"active"},{"model_id":"text-embedding-3-small","model_name":"Text Embedding 3 Small","developer_id":12,"desc":"","pricing":{"input":0.02,"output":0.02},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-01-25","last_updated":"2024-01-25","schema_checked":false,"retire_stage":"active"},{"model_id":"text-embedding-ada-002","model_name":"Text Embedding Ada 002","developer_id":12,"desc":"","pricing":{"input":0.1,"output":0.1},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2022-12-15","last_updated":"2022-12-15","schema_checked":false,"retire_stage":"active"},{"model_id":"text-embedding-v1","model_name":"Text Embedding V1","developer_id":12,"desc":"","pricing":{"input":0.1,"output":0.1},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"text-moderation-007","model_name":"Text Moderation 007","developer_id":12,"desc":"","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"moderation","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"text-moderation-latest","model_name":"Text Moderation","developer_id":12,"desc":"","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"moderation","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"text-moderation-stable","model_name":"Text Moderation Stable","developer_id":12,"desc":"","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"moderation","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"text-search-ada-doc-001","model_name":"Text Search Ada Doc 001","developer_id":12,"desc":"","pricing":{"input":20,"output":20},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"tts-1","model_name":"Tts 1","developer_id":12,"desc":"","pricing_source":"model_ratio","pricing_lines":[{"billable":"input_characters","unit":"character","cost_usd":0.000015,"source":"model_ratio"}],"has_zdr_provider":false,"types":"tts","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2023-11-06","last_updated":"2023-11-06","output_modalities":"audio","vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"tts-1-1106","model_name":"Tts 1 1106","developer_id":12,"desc":"","pricing_source":"model_ratio","pricing_lines":[{"billable":"input_characters","unit":"character","cost_usd":0.000015,"source":"model_ratio"}],"has_zdr_provider":false,"types":"tts","features":"","input_modalities":"audio","endpoints":"","max_output":0,"context_length":0,"output_modalities":"audio","schema_checked":false,"retire_stage":"active"},{"model_id":"tts-1-hd","model_name":"Tts 1 Hd","developer_id":12,"desc":"","pricing_source":"model_ratio","pricing_lines":[{"billable":"input_characters","unit":"character","cost_usd":0.00003,"source":"model_ratio"}],"has_zdr_provider":false,"types":"tts","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2023-11-06","last_updated":"2023-11-06","output_modalities":"audio","vendor":"openai","open_weights":false,"schema_checked":false,"retire_stage":"active"},{"model_id":"tts-1-hd-1106","model_name":"Tts 1 Hd 1106","developer_id":12,"desc":"","pricing_source":"model_ratio","pricing_lines":[{"billable":"input_characters","unit":"character","cost_usd":0.00003,"source":"model_ratio"}],"has_zdr_provider":false,"types":"tts","features":"","input_modalities":"audio","endpoints":"","max_output":0,"context_length":0,"output_modalities":"audio","schema_checked":false,"retire_stage":"active"},{"model_id":"whisper-1","model_name":"Whisper 1","developer_id":12,"desc":"Ignore the displayed price on the page; the actual charge for this model request is consistent with the official, so you can use it with confidence.","pricing_source":"model_ratio","pricing_lines":[{"billable":"audio_input_seconds","unit":"second","cost_usd":0.0001,"source":"model_ratio"}],"has_zdr_provider":false,"types":"stt","features":"","input_modalities":"audio","endpoints":"","max_output":0,"context_length":0,"release_date":"2022-09-21","last_updated":"2022-09-21","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"whisper-large-v3","model_name":"Whisper Large V3","developer_id":12,"desc":"","pricing_source":"model_ratio","pricing_lines":[{"billable":"audio_input_seconds","unit":"second","cost_usd":0.000030834,"source":"model_ratio"}],"has_zdr_provider":false,"types":"stt","features":"","input_modalities":"audio","endpoints":"","max_output":0,"context_length":0,"release_date":"2023-09-01","last_updated":"2023-09-01","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"whisper-large-v3-turbo","model_name":"Whisper Large V3 Turbo","developer_id":12,"desc":"","pricing_source":"model_ratio","pricing_lines":[{"billable":"audio_input_seconds","unit":"second","cost_usd":0.000012222,"source":"model_ratio"}],"has_zdr_provider":false,"types":"stt","features":"","input_modalities":"audio","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-10-01","last_updated":"2024-10-01","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-5.6-sol-pro","model_name":"GPT 5.6 Sol Pro","developer_id":12,"desc":"gpt-5.6-sol-pro is OpenAI's multimodal model, designed for complex reasoning and generation tasks. It supports text and image inputs alongside an extensive 1,050,000-token context window. Compared with GPT-5.6 Sol, it is served with reasoning.mode set to pro for higher-quality responses on complex tasks.","pricing":{"cache_read":0.8,"input":8,"output":40},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":1050000,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-oss-20b","model_name":"gpt-oss-20b","developer_id":12,"desc":"gpt-oss-20b is a 21-billion parameter open-weight model released by OpenAI under the Apache 2.0 license. Its core feature is a Mixture-of-Experts (MoE) architecture that uses only 3.6B active parameters, enabling low-latency inference and deployment on consumer GPUs. The model also supports fine-tuning, function calling, tool use, and structured outputs.","pricing":{"input":0.11,"output":0.55},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"thinking,function_calling,structured_outputs","input_modalities":"text","endpoints":"","max_output":32768,"context_length":128000,"release_date":"2025-08-05","last_updated":"2025-08-05","output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"grok-2-vision-1212","model_name":"Grok 2 Vision 1212","developer_id":9,"desc":"grok-2-vision-1212 is the latest vision model in the Grok family, delivering outstanding performance on vision-based tasks and achieving state-of-the-art results in visual mathematical reasoning and document-based question answering. It supports a wide range of visual inputs, including documents, charts, screenshots, and real-world images, making it well-suited for advanced visual understanding and reasoning use cases.\n\nThe price of calling this model in AIhubMix is ​​10% lower than on the official website.","pricing":{"input":1.8,"output":9},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"grok-vision-beta","model_name":"Grok Vision Beta","developer_id":9,"desc":"","pricing":{"input":5.6,"output":16.8},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"groq-llama-3.1-8b-instant","model_name":"Groq Llama 3.1 8B Instant","developer_id":11,"desc":"","pricing":{"input":0.055,"output":0.088},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"groq-llama-3.3-70b-versatile","model_name":"Groq Llama 3.3 70B Versatile","developer_id":11,"desc":"","pricing":{"input":0.649,"output":0.869011},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"groq-llama-4-maverick-17b-128e-instruct","model_name":"Groq Llama 4 Maverick 17B 128e Instruct","developer_id":11,"desc":"","pricing":{"input":0.22,"output":0.66},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-04-05","last_updated":"2025-04-05","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"groq-llama-4-scout-17b-16e-instruct","model_name":"Groq Llama 4 Scout 17B 16e Instruct","developer_id":11,"desc":"","pricing":{"input":0.122,"output":0.366},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"jina-embeddings-v2-base-code","model_name":"Jina Embeddings V2 Base Code","developer_id":22,"desc":"Model optimized for code and document search, 768-dimensional, 137M parameters.","pricing":{"input":0.05,"output":0.05},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"laguna-s-2.1","model_name":"Laguna S 2.1","developer_id":35,"desc":"laguna-s-2.1 is Poolside's coding agent model, designed for programming and developer agent workflows. It offers a massive 1,048,576-token context window, a 118B total parameter architecture with 8B active parameters, and cost-effective text processing with prompt caching.","pricing":{"cache_read":0.01,"input":0.1,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":1048576,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"laguna-xs-2.1","model_name":"Laguna Xs 2.1","developer_id":35,"desc":"laguna-xs-2.1 is Poolside's coding agent model, designed for coding and text generation tasks. It features a 262,144-token context window with cost-effective pricing across input, output, and prompt caching. Compared with Laguna XS.2, it represents Poolside's latest step forward in the 33B-A3B category.","pricing":{"cache_read":0.05,"input":0.1,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":262144,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"learnlm-1.5-pro-experimental","model_name":"Learnlm 1.5 Pro Experimental","developer_id":8,"desc":"","pricing":{"input":1.25,"output":5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"ling-3.0-flash","model_name":"Ling 3.0 Flash","developer_id":29,"desc":"ling-3.0-flash is Inclusionai's 124B Mixture-of-Experts (MoE) text model, designed for production-scale agentic inference and token-efficient text generation. Activating approximately 5.1B parameters per token, it offers an extensive 262,144-token context window alongside cost-effective pricing at $0.06 per 1M input, $0.18 per 1M output, and $0.01 per 1M cache tokens.","pricing":{"cache_read":0.012,"input":0.06,"output":0.18},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":262144,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"llama-3.1-405b-instruct","model_name":"Llama 3.1 405B Instruct","developer_id":11,"desc":"","pricing":{"input":4,"output":4},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-07-23","last_updated":"2024-07-23","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"llama-3.1-405b-reasoning","model_name":"Llama 3.1 405B (reasoning)","developer_id":11,"desc":"","pricing":{"input":4,"output":4},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"llama-3.1-70b-versatile","model_name":"Llama 3.1 70B Versatile","developer_id":11,"desc":"","pricing":{"input":0.6,"output":0.6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"llama-3.1-8b-instant","model_name":"Llama 3.1 8B Instant","developer_id":11,"desc":"","pricing":{"input":0.3,"output":0.6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-07-01","last_updated":"2024-07-01","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"llama-3.2-11b-vision-preview","model_name":"Llama 3.2 11B Vision Preview","developer_id":11,"desc":"","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"llama-3.2-1b-preview","model_name":"Llama 3.2 1B Preview","developer_id":11,"desc":"","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"llama-3.2-3b-preview","model_name":"Llama 3.2 3B Preview","developer_id":11,"desc":"","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"llama-3.2-90b-vision-preview","model_name":"Llama 3.2 90B Vision Preview","developer_id":11,"desc":"","pricing":{"input":2.4,"output":2.4},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"llama-3.3-70b-instruct","model_name":"Llama 3.3 70B Instruct","developer_id":11,"desc":"","pricing":{"input":0.6,"output":1.2},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"long_context","input_modalities":"text","endpoints":"","max_output":0,"context_length":131072,"release_date":"2024-12-06","last_updated":"2024-12-06","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"llama2-70b-4096","model_name":"Llama2 70B 4096","developer_id":11,"desc":"","pricing":{"input":0.5,"output":0.5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"llama2-70b-40960","model_name":"Llama2 70B 40960","developer_id":11,"desc":"","pricing":{"input":0.5,"output":0.5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"llama2-7b-2048","model_name":"Llama2 7B 2048","developer_id":11,"desc":"","pricing":{"input":0.1,"output":0.1},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"llama3-70b-8192","model_name":"Llama3 70B 8192","developer_id":11,"desc":"","pricing":{"input":0.7,"output":0.937288},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"llama3-70b-8192(33)","model_name":"Llama3 70B 8192(33)","developer_id":11,"desc":"","pricing":{"input":2.65,"output":2.65},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"llama3-8b-8192","model_name":"Llama3 8B 8192","developer_id":11,"desc":"","pricing":{"input":0.06,"output":0.12},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"llama3-8b-8192(33)","model_name":"Llama3 8B 8192(33)","developer_id":11,"desc":"","pricing":{"input":0.3,"output":0.3},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"llama3-groq-70b-8192-tool-use-preview","model_name":"Llama3 Groq 70B 8192 Tool Use Preview","developer_id":11,"desc":"","pricing":{"input":0.00089,"output":0.00089},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"llama3-groq-8b-8192-tool-use-preview","model_name":"Llama3 Groq 8B 8192 Tool Use Preview","developer_id":11,"desc":"","pricing":{"input":0.00019,"output":0.00019},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"mercury-2.5","model_name":"Mercury 2.5","developer_id":43,"desc":"Mercury 2.5 is Inception's diffusion language model (dLLM), designed for text generation and reasoning tasks. Instead of sequential generation, it produces and refines multiple tokens in parallel to achieve rapid reasoning, supported by an expansive 260,000-token context window.","pricing":{"cache_read":0.02,"input":0.2,"output":0.75},"pricing_source":"legacy_ratio","has_zdr_provider":true,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":260000,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"meta-llama/Llama-3.2-90B-Vision-Instruct","model_name":"Llama 3.2 90B Vision Instruct","developer_id":11,"desc":"","pricing":{"input":0.5,"output":0.5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"meta-llama/llama-3.1-405b-instruct:free","model_name":"Llama 3.1 405B Instruct (free)","developer_id":11,"desc":"","pricing":{"input":0.02,"output":0.02},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"meta-llama/llama-3.1-70b-instruct:free","model_name":"Llama 3.1 70B Instruct (free)","developer_id":11,"desc":"","pricing":{"input":0.02,"output":0.02},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"meta-llama/llama-3.1-8b-instruct:free","model_name":"Llama 3.1 8B Instruct (free)","developer_id":11,"desc":"","pricing":{"input":0.02,"output":0.02},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"meta-llama/llama-3.2-11b-vision-instruct:free","model_name":"Llama 3.2 11B Vision Instruct (free)","developer_id":11,"desc":"","pricing":{"input":0.02,"output":0.02},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"meta-llama/llama-3.2-3b-instruct:free","model_name":"Llama 3.2 3B Instruct (free)","developer_id":11,"desc":"","pricing":{"input":0.02,"output":0.02},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"meta/llama-3.1-405b-instruct","model_name":"Llama 3.1 405B Instruct","developer_id":11,"desc":"","pricing":{"input":5,"output":5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"meta/llama3-8B-chat","model_name":"Llama3 8B Chat","developer_id":11,"desc":"","pricing":{"input":0.3,"output":0.3},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"mistralai/mistral-7b-instruct:free","model_name":"Mistral 7B Instruct (free)","developer_id":10,"desc":"","pricing":{"input":0.002,"output":0.002},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"moonshot-v1-128k","model_name":"Moonshot V1 128K","developer_id":15,"desc":"","pricing":{"input":10,"output":10},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"moonshot-v1-128k-vision-preview","model_name":"Moonshot V1 128K Vision Preview","developer_id":15,"desc":"","pricing":{"input":10,"output":10},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"moonshot-v1-32k","model_name":"Moonshot V1 32K","developer_id":15,"desc":"","pricing":{"input":4,"output":4},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"moonshot-v1-32k-vision-preview","model_name":"Moonshot V1 32K Vision Preview","developer_id":15,"desc":"","pricing":{"input":4,"output":4},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"moonshot-v1-8k","model_name":"Moonshot V1 8K","developer_id":15,"desc":"","pricing":{"input":2,"output":2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"moonshot-v1-8k-vision-preview","model_name":"Moonshot V1 8K Vision Preview","developer_id":15,"desc":"","pricing":{"input":2,"output":2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"nvidia/Llama-3_1-Nemotron-Ultra-253B-v1","model_name":"Llama 3_1 Nemotron Ultra 253B V1","developer_id":17,"desc":"Llama-3.1-Nemotron-Ultra-253B is a 253 billion parameter reasoning-focused language model optimized for efficiency that excels at math, coding, and general instruction-following tasks while running on a single 8xH100 node.","pricing":{"input":0.5,"output":0.5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"o1-mini-2024-09-12","model_name":"O1 Mini 2024 09-12","developer_id":12,"desc":"","pricing":{"cache_read":1.5,"input":3,"output":12},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"deepinfra-llama-4-maverick-17b-128e-instruct","model_name":"Deepinfra Llama 4 Maverick 17B 128e Instruct","developer_id":11,"desc":"","pricing":{"input":0.33,"output":1.32},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"deepinfra-llama-4-scout-17b-16e-instruct","model_name":"Deepinfra Llama 4 Scout 17B 16e Instruct","developer_id":11,"desc":"","pricing":{"input":0.088,"output":0.33},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-ai/DeepSeek-Coder-V2-Instruct","model_name":"DeepSeek Coder V2 Instruct","developer_id":7,"desc":"","pricing":{"input":0.16,"output":0.32},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-ai/DeepSeek-R1-Distill-Llama-70B","model_name":"DeepSeek R1 Distill Llama 70B","developer_id":7,"desc":"","pricing":{"input":0.6,"output":0.6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-ai/DeepSeek-R1-Distill-Llama-8B","model_name":"DeepSeek R1 Distill Llama 8B","developer_id":7,"desc":"","pricing":{"input":0.01,"output":0.01},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","model_name":"DeepSeek R1 Distill Qwen 1.5b","developer_id":7,"desc":"","pricing":{"input":0.01,"output":0.01},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","model_name":"DeepSeek R1 Distill Qwen 14B","developer_id":7,"desc":"Open source deployment from SiliconFlow, the model itself is obtained through knowledge distillation.","pricing":{"input":0.1,"output":0.1},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","model_name":"DeepSeek R1 Distill Qwen 32B","developer_id":7,"desc":"Open source deployment from SiliconFlow, the model itself is obtained through knowledge distillation.","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","model_name":"DeepSeek R1 Distill Qwen 7B","developer_id":7,"desc":"Open source deployment from SiliconFlow, the model itself is obtained through knowledge distillation.","pricing":{"input":0.01,"output":0.01},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-ai/DeepSeek-V2-Chat","model_name":"DeepSeek V2 Chat","developer_id":7,"desc":"","pricing":{"input":0.16,"output":0.32},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-ai/DeepSeek-V2.5","model_name":"DeepSeek V2.5","developer_id":7,"desc":"","pricing":{"input":0.16,"output":0.32},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-ai/deepseek-llm-67b-chat","model_name":"DeepSeek Llm 67B Chat","developer_id":7,"desc":"","pricing":{"input":0.16,"output":0.16},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-ai/deepseek-vl2","model_name":"DeepSeek Vl2","developer_id":7,"desc":"","pricing":{"input":0.16,"output":0.16},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"distil-whisper-large-v3-en","model_name":"Distil Whisper Large V3 En","developer_id":12,"desc":"","pricing_source":"model_ratio","pricing_lines":[{"billable":"audio_input_seconds","unit":"second","cost_usd":0.000005556,"source":"model_ratio"}],"has_zdr_provider":false,"types":"stt","features":"","input_modalities":"audio","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-1-5-thinking-vision-pro-250428","model_name":"Doubao 1.5 Thinking Vision Pro 250428","developer_id":4,"desc":"Deep Thinking  \nImage Understanding  \nVisual Localization  \nVideo Understanding  \nTool Invocation  \nStructured Output","pricing":{"input":2,"output":2},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":9,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":3,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-04-28","last_updated":"2025-04-28","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"fx-flux-2-pro","model_name":"Fx Flux 2 Pro","developer_id":27,"desc":"","pricing_source":"img_price_config","pricing_lines":[{"billable":"generate","unit":"image","cost_usd":0.09,"source":"img_price_config","variant":{"quality":"standard","size":"standard"}}],"has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"image","schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-2.5-pro-exp-03-25","model_name":"Gemini 2.5 Pro","developer_id":8,"desc":"Google’s latest experimental model, highly unstable, for experience only.\nIt boasts strong reasoning and coding capabilities, able to \"think\" before responding, enhancing performance and accuracy in complex tasks. It supports multimodal inputs (text, audio, images, video) and a 1 million token context window, suitable for advanced programming, math, and science tasks.\n\nThis means Gemini 2.5 can handle more complex problems in coding, science and math, and support more context-aware agents.","pricing":{"cache_read":0.125,"input":1.25,"output":5,"tiers":[{"cache_read":0.25,"input":2.5,"output":15,"tier":{"size":200000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":4.5,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.125,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.25,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":15,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":1.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":200000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":2.5,"source":"billing_config","tier":{"name":"tier2","min_tokens":200001,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.035,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"structured_outputs,tools,long_context","input_modalities":"text,image,audio,video","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-03-25","last_updated":"2025-03-25","output_modalities":"text","tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-embedding-exp-03-07","model_name":"Gemini Embedding","developer_id":8,"desc":"","pricing":{"input":0.02,"output":0.02},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"embedding","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-exp-1114","model_name":"Gemini","developer_id":8,"desc":"","pricing":{"input":1.25,"output":5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-exp-1121","model_name":"Gemini","developer_id":8,"desc":"","pricing":{"input":1.25,"output":5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-pro","model_name":"Gemini Pro","developer_id":8,"desc":"","pricing":{"input":0.2,"output":0.6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gemini-pro-vision","model_name":"Gemini Pro Vision","developer_id":8,"desc":"","pricing":{"input":1,"output":1},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gemma-7b-it","model_name":"Gemma 7B It","developer_id":8,"desc":"","pricing":{"input":0.1,"output":0.1},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"glm-3-turbo","model_name":"GLM 3 Turbo","developer_id":5,"desc":"","pricing":{"input":0.71,"output":0.71},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"glm-4","model_name":"GLM 4","developer_id":5,"desc":"","pricing":{"input":14.2,"output":14.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"glm-4-flash","model_name":"GLM 4 Flash","developer_id":5,"desc":"","pricing":{"input":0.1,"output":0.1},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"glm-4-plus","model_name":"GLM 4 Plus","developer_id":5,"desc":"","pricing":{"input":8,"output":8},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"glm-4.5-airx","model_name":"GLM 4.5 Airx","developer_id":5,"desc":"GLM-4.5-AirX is the high-speed version of GLM-4.5-Air, with faster response times, specifically designed for large-scale high-speed demands.","pricing":{"cache_read":0.22,"input":1.1,"output":4.51},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-07-28","last_updated":"2025-07-28","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"glm-4v","model_name":"GLM 4 Vision","developer_id":5,"desc":"","pricing":{"input":14.2,"output":14.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"glm-4v-plus","model_name":"GLM 4 Vision Plus","developer_id":5,"desc":"","pricing":{"input":2,"output":2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"google-gemma-3-12b-it","model_name":"Google Gemma 3 12B It","developer_id":8,"desc":"","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"google-gemma-3-27b-it","model_name":"Google Gemma 3 27B It","developer_id":8,"desc":"","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-11-04","last_updated":"2025-11-04","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"google-gemma-3-4b-it","model_name":"Google Gemma 3 4B It","developer_id":8,"desc":"","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"google/gemini-exp-1114","model_name":"Gemini","developer_id":8,"desc":"","pricing":{"input":1.25,"output":5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"google/gemma-2-27b-it","model_name":"Gemma 2 27B It","developer_id":8,"desc":"","pricing":{"input":0.8,"output":0.8},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-3.5-turbo","model_name":"GPT 3.5 Turbo","developer_id":12,"desc":"Since the GPT-3.5-turbo model has been officially deprecated, all requests targeting this model will be automatically routed to GPT-40-mini. We recommend using GPT-40-mini directly as a replacement.","pricing":{"input":0.5,"output":1.5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2023-03-01","last_updated":"2023-03-01","output_modalities":"text","schema_checked":false,"retire_stage":"deprecated","deprecated_at":"2026-09-02T00:00:00Z","retired_at":"2026-10-23T00:00:00Z","successor_model":"gpt-5.6-terra"},{"model_id":"gpt-3.5-turbo-1106","model_name":"GPT 3.5 Turbo 1106","developer_id":12,"desc":"","pricing":{"input":1,"output":2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2023-11-06","last_updated":"2023-11-06","output_modalities":"text","schema_checked":false,"retire_stage":"deprecated","deprecated_at":"2026-09-02T00:00:00Z","retired_at":"2026-09-28T00:00:00Z","successor_model":"gpt-5.6-terra"},{"model_id":"gpt-3.5-turbo-16k","model_name":"GPT 3.5 Turbo 16K","developer_id":12,"desc":"","pricing":{"input":3,"output":4},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2023-08-28","last_updated":"2023-08-28","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-3.5-turbo-instruct","model_name":"GPT 3.5 Turbo Instruct","developer_id":12,"desc":"","pricing":{"input":1.5,"output":2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2023-09-21","last_updated":"2023-09-21","output_modalities":"text","schema_checked":false,"retire_stage":"deprecated","deprecated_at":"2026-09-02T00:00:00Z","retired_at":"2026-09-28T00:00:00Z","successor_model":"gpt-5.6-terra"},{"model_id":"gpt-4","model_name":"GPT 4","developer_id":12,"desc":"","pricing":{"input":30,"output":60},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2023-11-06","last_updated":"2023-11-06","output_modalities":"text","schema_checked":false,"retire_stage":"deprecated","deprecated_at":"2026-09-02T00:00:00Z","retired_at":"2026-10-23T00:00:00Z","successor_model":"gpt-5.6-sol"},{"model_id":"gpt-4-0613","model_name":"GPT 4 0613","developer_id":12,"desc":"","pricing":{"input":30,"output":60},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"deprecated","deprecated_at":"2026-09-02T00:00:00Z","retired_at":"2026-10-23T00:00:00Z","successor_model":"gpt-5.6-sol"},{"model_id":"gpt-4-1106-preview","model_name":"GPT 4 1106 Preview","developer_id":12,"desc":"","pricing":{"input":10,"output":30},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"deprecated","deprecated_at":"2026-09-02T00:00:00Z","retired_at":"2026-10-23T00:00:00Z","successor_model":"gpt-5.6-sol"},{"model_id":"gpt-4-turbo","model_name":"GPT 4 Turbo","developer_id":12,"desc":"","pricing":{"input":10,"output":30},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2023-11-06","last_updated":"2023-11-06","output_modalities":"text","schema_checked":false,"retire_stage":"deprecated","deprecated_at":"2026-09-02T00:00:00Z","retired_at":"2026-10-23T00:00:00Z","successor_model":"gpt-5.6-sol"},{"model_id":"gpt-4-turbo-2024-04-09","model_name":"GPT 4 Turbo 2024 04-09","developer_id":12,"desc":"","pricing":{"input":10,"output":30},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"deprecated","deprecated_at":"2026-09-02T00:00:00Z","retired_at":"2026-10-23T00:00:00Z","successor_model":"gpt-5.6-sol"},{"model_id":"gpt-4o-2024-05-13","model_name":"GPT 4o 2024 05-13","developer_id":12,"desc":"","pricing":{"cache_read":5,"input":5,"output":15},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":15,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"image_generation","unit":"image","cost_usd":0,"source":"billing_config"},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.025,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":4096,"context_length":128000,"release_date":"2024-05-13","last_updated":"2024-05-13","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-4o-mini-2024-07-18","model_name":"GPT 4o Mini 2024 07-18","developer_id":12,"desc":"","pricing":{"cache_read":0.075,"input":0.15,"output":0.6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-07-18","last_updated":"2024-07-18","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Doubao-1.5-lite-32k","model_name":"Doubao 1.5 Lite 32K","developer_id":4,"desc":"Doubao-1.5-lite, a brand-new generation of lightweight model, offers exceptional response speed with both performance and latency reaching world-class levels. It supports a 32k context window and an output length of up to 12k tokens.","pricing":{"cache_read":0.01,"input":0.05,"output":0.1},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":0.002329,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0082192,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.082192,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.041096,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Doubao-1.5-pro-256k","model_name":"Doubao 1.5 Pro 256K","developer_id":4,"desc":"Doubao-1.5-pro-256k, a fully upgraded version based on Doubao-1.5-Pro, delivers an overall performance improvement of 10%. It supports inference with a 256k context window and an output length of up to 12k tokens. With higher performance, larger window size, and exceptional cost-effectiveness, it is suitable for a wider range of application scenarios.","pricing":{"input":0.8,"output":1.44},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.2328776,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.684932,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-03-12","last_updated":"2025-03-12","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Doubao-1.5-pro-32k","model_name":"Doubao 1.5 Pro 32K","developer_id":4,"desc":"Doubao-1.5-pro, a brand-new generation of flagship model, features comprehensive performance upgrades and excels in knowledge, coding, reasoning, and other aspects. It supports a 32k context window and an output length of up to 12k tokens.","pricing":{"cache_read":0.0268,"input":0.134,"output":0.335},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":0.002329,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.021918,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.273975,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.10959,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-11-20","last_updated":"2024-11-20","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Doubao-1.5-vision-pro-32k","model_name":"Doubao 1.5 Vision Pro 32K","developer_id":4,"desc":"Doubao-1.5-vision-pro is a newly upgraded multimodal large model that supports image recognition at any resolution and extreme aspect ratios. It enhances visual reasoning, document recognition, detailed information understanding, and instruction-following capabilities. It supports a 32k context window and an output length of up to 12k tokens.","pricing":{"input":0.46,"output":1.38},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-11-20","last_updated":"2024-11-20","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Doubao-lite-128k","model_name":"Doubao Lite 128K","developer_id":4,"desc":"","pricing":{"input":0.14,"output":0.28},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.1369875,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.10959,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Doubao-lite-32k","model_name":"Doubao Lite 32K","developer_id":4,"desc":"","pricing":{"cache_read":0.012,"input":0.06,"output":0.12},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":0.002329,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0082192,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.082192,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.041096,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Doubao-lite-4k","model_name":"Doubao Lite 4K","developer_id":4,"desc":"","pricing":{"input":0.06,"output":0.12},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.082192,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.041096,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Doubao-pro-128k","model_name":"Doubao Pro 128K","developer_id":4,"desc":"","pricing":{"input":0.8,"output":1.44},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Doubao-pro-256k","model_name":"Doubao Pro 256K","developer_id":4,"desc":"","pricing":{"input":0.8,"output":1.44},"pricing_source":"billing_config","pricing_lines":[{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.2328776,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.684932,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Doubao-pro-32k","model_name":"Doubao Pro 32K","developer_id":4,"desc":"","pricing":{"cache_read":0.028,"input":0.14,"output":0.35},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_storage_hours","unit":"million_tokens_hour","cost_usd":0.002329,"source":"billing_config"},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.021918,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.273975,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.10959,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Doubao-pro-4k","model_name":"Doubao Pro 4K","developer_id":4,"desc":"","pricing":{"input":0.14,"output":0.35},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"GPT-OSS-20B","model_name":"gpt-oss-20b","developer_id":12,"desc":"","pricing":{"input":0.11,"output":0.55},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-08-05","last_updated":"2025-08-05","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Gryphe/MythoMax-L2-13b","model_name":"Mythomax L2 13B","developer_id":11,"desc":"","pricing":{"input":0.4,"output":0.4},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"MiniMax-Text-01","model_name":"MiniMax Text 01","developer_id":18,"desc":"","pricing":{"input":0.14,"output":1.12},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"long_context","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-01-15","last_updated":"2025-01-15","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Mistral-large-2407","model_name":"Mistral Large 2407","developer_id":10,"desc":"","pricing":{"input":3,"output":9},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-11-19","last_updated":"2024-11-19","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Qwen/Qwen2-1.5B-Instruct","model_name":"Qwen2 1.5b Instruct","developer_id":13,"desc":"","pricing":{"input":0.2,"output":0.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Qwen/Qwen2-57B-A14B-Instruct","model_name":"Qwen2 57B A14B Instruct","developer_id":13,"desc":"","pricing":{"input":0.24,"output":0.24},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Qwen/Qwen2-72B-Instruct","model_name":"Qwen2 72B Instruct","developer_id":13,"desc":"","pricing":{"input":0.8,"output":0.8},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Qwen/Qwen2-7B-Instruct","model_name":"Qwen2 7B Instruct","developer_id":13,"desc":"","pricing":{"input":0.08,"output":0.08},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Qwen/Qwen2.5-32B-Instruct","model_name":"Qwen2.5 32B Instruct","developer_id":13,"desc":"","pricing":{"input":0.6,"output":0.6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Qwen/Qwen2.5-72B-Instruct","model_name":"Qwen2.5 72B Instruct","developer_id":13,"desc":"","pricing":{"input":0.8,"output":0.8},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Qwen/Qwen2.5-72B-Instruct-128K","model_name":"Qwen2.5 72B Instruct 128K","developer_id":13,"desc":"","pricing":{"input":0.8,"output":0.8},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Qwen/Qwen2.5-7B-Instruct","model_name":"Qwen2.5 7B Instruct","developer_id":13,"desc":"","pricing":{"input":0.4,"output":0.4},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Qwen/Qwen2.5-Coder-32B-Instruct","model_name":"Qwen2.5 Coder 32B Instruct","developer_id":13,"desc":"","pricing":{"input":0.16,"output":0.16},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"Qwen3-235B-A22B-Thinking-2507","model_name":"Qwen3 235B A22B Thinking 2507","developer_id":13,"desc":"","pricing":{"input":0.28,"output":2.8},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-07-25","last_updated":"2025-07-25","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"WizardLM/WizardCoder-Python-34B-V1.0","model_name":"Wizardcoder Python 34B V1.0","developer_id":11,"desc":"","pricing":{"input":0.9,"output":0.9},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"ahm-Phi-3-5-MoE-instruct","model_name":"Ahm Phi 3.5 Moe Instruct","developer_id":3,"desc":"","pricing":{"input":0.4,"output":1.6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"ahm-Phi-3-5-mini-instruct","model_name":"Ahm Phi 3.5 Mini Instruct","developer_id":3,"desc":"Phi-3.5-mini is a lightweight, state-of-the-art open model built upon the dataset used for Phi-3—which includes synthetic data and carefully curated publicly available websites—focusing on very high-quality, reasoning-intensive data. This model is part of the Phi-3 model family and supports a context length of 128K tokens.","pricing":{"input":1,"output":3},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"ahm-Phi-3-5-vision-instruct","model_name":"Ahm Phi 3.5 Vision Instruct","developer_id":3,"desc":"","pricing":{"input":0.4,"output":1.6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"ahm-Phi-3-medium-128k","model_name":"Ahm Phi 3 Medium 128K","developer_id":3,"desc":"","pricing":{"input":6,"output":18},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"ahm-Phi-3-medium-4k","model_name":"Ahm Phi 3 Medium 4K","developer_id":3,"desc":"","pricing":{"input":1,"output":3},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"ahm-Phi-3-small-128k","model_name":"Ahm Phi 3 Small 128K","developer_id":3,"desc":"","pricing":{"input":1,"output":3},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"aihubmix-Codestral-2501","model_name":"Aihubmix Codestral 2501","developer_id":10,"desc":"","pricing":{"input":0.4,"output":1.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"aihubmix-Cohere-command-r","model_name":"Aihubmix Cohere Command R","developer_id":6,"desc":"","pricing":{"input":0.64,"output":1.92},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"aihubmix-Jamba-1-5-Large","model_name":"Aihubmix Jamba 1.5 Large","developer_id":1,"desc":"","pricing":{"input":2.2,"output":8.8},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"aihubmix-Llama-3-1-405B-Instruct","model_name":"Aihubmix Llama 3.1 405B Instruct","developer_id":11,"desc":"","pricing":{"input":5,"output":15},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"aihubmix-Llama-3-1-70B-Instruct","model_name":"Aihubmix Llama 3.1 70B Instruct","developer_id":11,"desc":"","pricing":{"input":0.6,"output":0.78},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"aihubmix-Llama-3-1-8B-Instruct","model_name":"Aihubmix Llama 3.1 8B Instruct","developer_id":11,"desc":"","pricing":{"input":0.3,"output":0.6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"aihubmix-Llama-3-2-11B-Vision","model_name":"Aihubmix Llama 3.2 11B Vision","developer_id":11,"desc":"","pricing":{"input":0.4,"output":0.4},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"aihubmix-Llama-3-2-90B-Vision","model_name":"Aihubmix Llama 3.2 90B Vision","developer_id":11,"desc":"","pricing":{"input":2.4,"output":2.4},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"aihubmix-Llama-3-70B-Instruct","model_name":"Aihubmix Llama 3 70B Instruct","developer_id":11,"desc":"","pricing":{"input":0.7,"output":0.7},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"aihubmix-Mistral-large","model_name":"Aihubmix Mistral Large","developer_id":10,"desc":"","pricing":{"input":4,"output":12},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"aihubmix-command-r-08-2024","model_name":"Aihubmix Command R 08 2024","developer_id":6,"desc":"","pricing":{"input":0.2,"output":0.8},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"aihubmix-command-r-plus","model_name":"Aihubmix Command R Plus","developer_id":6,"desc":"","pricing":{"input":3.84,"output":19.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"aihubmix-command-r-plus-08-2024","model_name":"Aihubmix Command R Plus 08 2024","developer_id":6,"desc":"","pricing":{"input":2.8,"output":11.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"alicloud-deepseek-v3.2","model_name":"Alicloud Deepseek V3.2","developer_id":7,"desc":"","pricing":{"cache_read":0.0548,"cache_write":0.3425,"input":0.274,"output":0.411},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":0.3425,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.0548,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":0.411,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.274,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.000548,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"alicloud-glm-4.7","model_name":"Alicloud Glm 4.7","developer_id":5,"desc":"","pricing":{"cache_read":0.41096,"input":0.41096,"output":1.917786,"tiers":[{"cache_read":0.547946,"input":0.547946,"output":2.191784,"tier":{"size":32000,"type":"context"}}]},"pricing_source":"billing_config","pricing_lines":[{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.41096,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.547946,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":200000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":1.917785936,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":2.191784,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":200000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.41096,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":32000}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":0.547946,"source":"billing_config","tier":{"name":"tier2","min_tokens":32001,"max_tokens":200000}}],"has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"alicloud-kimi-k2-thinking","model_name":"Alicloud Kimi K2 Thinking","developer_id":15,"desc":"","pricing":{"input":0.548,"output":2.192},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"alicloud-minimax-m2.5","model_name":"Alicloud Minimax M2.5","developer_id":18,"desc":"","pricing":{"cache_read":0.05752,"input":0.2876,"output":1.1504},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"anthropic-opus-4-6","model_name":"Anthropic Opus 4.6","developer_id":2,"desc":"Claude Opus 4.6 is Anthropic’s latest state-of-the-art reasoning model. It features an adaptive “thinking” mode that dynamically decides when to think and how much to think. At the default effort level (high), Claude will almost always engage in thinking. At lower effort levels, it may skip thinking for simple problems.\n ⚠️ The minimum cache token for claude-opus-4-6 has been increased from 1,024 to 4,096 tokens.","pricing":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"pricing_source":"billing_config","pricing_lines":[{"billable":"cache_write_1_hour_tokens","unit":"million_tokens","cost_usd":10,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_5_minutes_tokens","unit":"million_tokens","cost_usd":6.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cache_write_tokens","unit":"million_tokens","cost_usd":6.25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"cached_tokens","unit":"million_tokens","cost_usd":0.5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"completion_tokens","unit":"million_tokens","cost_usd":25,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"prompt_tokens","unit":"million_tokens","cost_usd":5,"source":"billing_config","tier":{"name":"tier1","default":true,"min_tokens":0,"max_tokens":-1}},{"billable":"web_search_requests","unit":"request","cost_usd":0.01,"source":"billing_config"}],"has_zdr_provider":false,"types":"llm","features":"thinking,tools,function_calling,structured_outputs","input_modalities":"text,image","endpoints":"","max_output":32000,"context_length":200000,"output_modalities":"text","reasoning":true,"tool_call":true,"schema_checked":false,"retire_stage":"active"},{"model_id":"azure-deepseek-v3.2","model_name":"Azure Deepseek V3.2","developer_id":7,"desc":"","pricing":{"input":0.58,"output":1.680028},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"azure-deepseek-v3.2-speciale","model_name":"Azure Deepseek V3.2 Speciale","developer_id":7,"desc":"","pricing":{"input":0.58,"output":1.680028},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"cbs-glm-4.7","model_name":"Cbs Glm 4.7","developer_id":5,"desc":"","pricing":{"input":2.25,"output":2.749995},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"cerebras-llama-3.3-70b","model_name":"Cerebras Llama 3.3 70B","developer_id":11,"desc":"","pricing":{"input":0.6,"output":0.6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"chatglm_lite","model_name":"Chatglm_lite","developer_id":5,"desc":"","pricing":{"input":0.2858,"output":0.2858},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"chatglm_pro","model_name":"Chatglm_pro","developer_id":5,"desc":"","pricing":{"input":1.4286,"output":1.4286},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"chatglm_std","model_name":"Chatglm_std","developer_id":5,"desc":"","pricing":{"input":0.7144,"output":0.7144},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"chatglm_turbo","model_name":"Chatglm_turbo","developer_id":5,"desc":"","pricing":{"input":0.7144,"output":0.7144},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"claude-2","model_name":"Claude 2","developer_id":2,"desc":"","pricing":{"input":8.8,"output":8.8},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"claude-2.0","model_name":"Claude 2.0","developer_id":2,"desc":"","pricing":{"input":8.8,"output":39.6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"claude-2.1","model_name":"Claude 2.1","developer_id":2,"desc":"","pricing":{"input":8.8,"output":39.6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"claude-3-haiku-20240229","model_name":"Claude 3 Haiku 20240229","developer_id":2,"desc":"","pricing":{"input":0.275,"output":0.275},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"claude-3-haiku-20240307","model_name":"Claude 3 Haiku 20240307","developer_id":2,"desc":"","pricing":{"input":0.275,"output":1.375},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-03-07","last_updated":"2024-03-07","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"claude-3-haiku@20240307","model_name":"Claude 3 Haiku@20240307","developer_id":2,"desc":"","pricing":{"input":0.275,"output":1.375},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"claude-3-opus@20240229","model_name":"Claude 3 Opus@20240229","developer_id":2,"desc":"","pricing":{"input":16.5,"output":82.5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"claude-3-sonnet-20240229","model_name":"Claude 3 Sonnet 20240229","developer_id":2,"desc":"","pricing":{"input":3.3,"output":16.5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text,image","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"claude-instant-1","model_name":"Claude Instant 1","developer_id":2,"desc":"","pricing":{"input":1.793,"output":1.793},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"claude-instant-1.2","model_name":"Claude Instant 1.2","developer_id":2,"desc":"","pricing":{"input":0.88,"output":3.96},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"code-davinci-edit-001","model_name":"Code Davinci Edit 001","developer_id":5,"desc":"","pricing":{"input":20,"output":20},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"cogview-3","model_name":"Cogview 3","developer_id":5,"desc":"","pricing":{"input":35.5,"output":35.5},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"image","schema_checked":false,"retire_stage":"active"},{"model_id":"cogview-3-plus","model_name":"Cogview 3 Plus","developer_id":5,"desc":"","pricing":{"input":10,"output":10},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"image_generation","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"image","schema_checked":false,"retire_stage":"active"},{"model_id":"command","model_name":"Command","developer_id":6,"desc":"","pricing":{"input":1,"output":2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"command-light","model_name":"Command Light","developer_id":6,"desc":"","pricing":{"input":1,"output":2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"command-light-nightly","model_name":"Command Light Nightly","developer_id":6,"desc":"","pricing":{"input":1,"output":2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"command-nightly","model_name":"Command Nightly","developer_id":6,"desc":"","pricing":{"input":1,"output":2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"command-r","model_name":"Command R","developer_id":6,"desc":"","pricing":{"input":0.64,"output":1.92},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"command-r-08-2024","model_name":"Command R 08 2024","developer_id":6,"desc":"","pricing":{"input":0.2,"output":0.8},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-08-30","last_updated":"2024-08-30","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"command-r-plus","model_name":"Command R Plus","developer_id":6,"desc":"","pricing":{"input":3.84,"output":19.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"command-r-plus-08-2024","model_name":"Command R Plus 08 2024","developer_id":6,"desc":"","pricing":{"input":2.8,"output":11.2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"text","endpoints":"","max_output":0,"context_length":0,"release_date":"2024-08-30","last_updated":"2024-08-30","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"davinci","model_name":"Davinci","developer_id":12,"desc":"","pricing":{"input":20,"output":20},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"davinci-002","model_name":"Davinci 002","developer_id":12,"desc":"","pricing":{"input":2,"output":2},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"deepinfra-llama-3.1-8b-instant","model_name":"Deepinfra Llama 3.1 8B Instant","developer_id":11,"desc":"","pricing":{"input":0.033,"output":0.054978},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"deepinfra-llama-3.3-70b-instant-turbo","model_name":"Deepinfra Llama 3.3 70B Instant Turbo","developer_id":11,"desc":"","pricing":{"input":0.11,"output":0.352},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"o3-pro-global","model_name":"O3 Pro Global","developer_id":12,"desc":"","pricing":{"input":20,"output":80},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qianfan-chinese-llama-2-13b","model_name":"Qianfan Chinese Llama 2 13B","developer_id":11,"desc":"","pricing":{"input":0.822,"output":0.822},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"qianfan-llama-vl-8b","model_name":"Qianfan Llama VL 8B","developer_id":11,"desc":"","pricing":{"input":0.274,"output":0.685},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"deepseek-r1-distill-qianfan-llama-8b","model_name":"DeepSeek R1 Distill Qianfan Llama 8B","developer_id":11,"desc":"","pricing":{"input":0.137,"output":0.548},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-1-5-pro-256k-250115","model_name":"Doubao 1.5 Pro 256K 250115","developer_id":5,"desc":"","pricing":{"input":0.684,"output":1.2312},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-01-15","last_updated":"2025-01-15","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"doubao-1-5-pro-32k-250115","model_name":"Doubao 1.5 Pro 32K 250115","developer_id":5,"desc":"","pricing":{"input":0.108,"output":0.27},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"release_date":"2025-01-15","last_updated":"2025-01-15","output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-4o-2024-08-06-global","model_name":"GPT 4o 2024 08-06 Global","developer_id":12,"desc":"","pricing":{"cache_read":1.25,"input":2.5,"output":10},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"gpt-4o-mini-global","model_name":"GPT 4o Mini Global","developer_id":12,"desc":"","pricing":{"cache_read":0.075,"input":0.15,"output":0.6},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"meta-llama-3-70b","model_name":"Meta Llama 3 70B","developer_id":11,"desc":"","pricing":{"input":4.795,"output":4.795},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"meta-llama-3-8b","model_name":"Meta Llama 3 8B","developer_id":11,"desc":"","pricing":{"input":0.548,"output":0.548},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"o3-global","model_name":"O3 Global","developer_id":12,"desc":"","pricing":{"cache_read":0.5,"input":2,"output":8},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"},{"model_id":"o3-mini-global","model_name":"O3 Mini Global","developer_id":12,"desc":"","pricing":{"cache_read":0.55,"input":1.1,"output":4.4},"pricing_source":"legacy_ratio","has_zdr_provider":false,"types":"llm","features":"","input_modalities":"","endpoints":"","max_output":0,"context_length":0,"output_modalities":"text","schema_checked":false,"retire_stage":"active"}],"message":"","success":true}