by Doubao
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.
| Input | $0.48 / 1M tokens |
| Output | $2.41 / 1M tokens |
| Cache read | $0.1 / 1M tokens |
| Context window | 256,000 tokens |
| Modalities | text, image, video |
| Features | thinking, web, tools, function_calling, structured_outputs |
Use doubao-seed-2-0-pro via the AIHubMix unified API — one interface for every major LLM.