GPT-5.1 Codex is OpenAI's coding-optimized model built on the GPT-5.1 architecture with dynamic reasoning adjustment. Delivers strong software engineering performance with 2-3x faster speed and extended prompt caching.
- Coding-optimized model built on GPT-5.1 with dynamic reasoning adjustment for development tasks.
- 400,000-token context window with 128,000 max output tokens and configurable reasoning effort.
- 2-3x faster than GPT-5 with ~50% token efficiency for cost-effective coding workflows.
- Extended prompt caching retention up to 24 hours with 90% cheaper cached input tokens.
- Pricing is $1.25 per 1M input tokens and $10 per 1M output tokens.
Model Information
Supported Formats
GPT 5.5OpenAI's most advanced model released April 2026. GPT-5.5 is recommended for most reasoning workloads, combining frontier intelligence with configurable reasoning effort (none → xhigh). Available in API, Codex, and ChatGPT.
GPT 5.5 ProHighest-intelligence API option in the GPT-5.5 family. Use for the most challenging problems that require maximum reasoning depth and can tolerate higher latency. Supports full reasoning effort range from none to xhigh.
GPT 5.4GPT-5.4 is OpenAI's frontier model for complex professional work, designed for agentic, coding, and professional workflows with the highest reasoning capability. Features a 1.05M token context window, native computer use, and built-in support for web search, file search, and MCP.