GPT 5.3 ChatPricing
- Input Tokens: $1.750 /M tokens
- Output Tokens: $14.000 /M tokens
- Cache Read: $0.175 /M tokens
Input Modalities
- Text
- Vision
Output Modalities
- Text
Context length
- 128K tokens
Max output
- 16.4K tokens
Capabilities
- Thinking
- Streaming
- Tool calling
- Web search
- URL context
- Code interpreter
- Computer use
- File search
- Memory tool
- Structured outputs
- Citations
- Prompt caching
- Background mode
- Server-side sessions
Providers
Performance for gpt-5.3-chat-latest
Uptime is the percentage of requests that succeeded over the past 72 hours. AIHubMix continuously monitors every provider and automatically retries with the next-best provider when one returns an error or responds too slowly; Latency is total round-trip time (lower is better); Throughput is how fast the model writes (tokens per second, higher is better).
Try this model
Frequently asked questions
Compare GPT 5.3 Chat
More models from OpenAI
See all OpenAI models →- Input: $ 4 /M
- Output: $ 20 /M
- Web Search: $0.01/request
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.
- Input: $ 0.2 /M
- Output: $ 1.2 /M
- Web Search: $0.01/request
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.
- Input: $ 4 /M
- Output: $ 20 /M
- Web Search: $0.01/request
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.
- Input: $ 2 /M
- Output: $ 12 /M
- Web Search: $0.01/request
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.
Developed by OpenAI, gpt-oss-20b-free is an open-weight 21B parameter model released under the Apache 2.0 license. This model utilizes a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass. It supports an expansive context window of up to 131,072 tokens, making it well-suited for long-context tasks.
- Input: $ 2.5 /M
- Output: $ 10 /M
- Input Audio: $2.4/M tokens
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.
AIHubMix