gpt-5.1-codex

GPT-5.1 Codex is a specialized version optimized for long-term, agent-enabled coding tasks, built on the foundation of GPT-5.1.It responds to simple tasks up to twice as fast as GPT-5,making it ideal for continuous conversations and autonomous engineering workflows in Codex or similar environments, offering 400,000 tokens in its context window and supporting a maximum output limit of 128,000 tokens.In the SWE-bench Verified benchmark test, GPT-5.1 Codex improved its score from 72.8% with GPT-5 to 76.3%;this model focuses specifically on software engineering tasks, such as translating requirements into code, feature development, debugging, refactoring, and code review,and provides eight distinct dialogue styles—default, professional, friendly, and others—to accommodate a wide range of scenarios, from rigorous code reviews to creative programming. Users can also fine-tune parameters like "simplicity" and "enthusiasm" to tailor the model into a personalized programming assistant.Compared to general-purpose models, it offers greater adaptability and better alignment with developer instructions, making it well-suited for long-term use within IDE/CLI and the Codex toolchain. It’s particularly effective for ongoing development of large-scale codebases, cross-file refactoring, long-form conversational pair programming, and engineering tasks requiring advanced tool or agent orchestration.

Official guide:https://cookbook.openai.com/examples/gpt-5-codex_prompting_guide