GPT-5.1-Codex-Max
GPT-5.1-Codex-Max is an agentic coding model developed by OpenAI, released on December 4, 2025. It is designed for complex software development tasks, featuring a 400,000 token context window and built-in reasoning and tool-calling capabilities.
GPT-5.1-Codex-Max specs and pricing
- Provider: OpenAI
- Released: December 4, 2025
- Context window: 400K tokens
- Max output: 128K tokens
- Input: text, images
- Output: text
- Price: $1.25 input / $10 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What GPT-5.1-Codex-Max is good at
- Managing large-scale software development projects
- Analyzing extensive codebases with visual documentation
- Automating complex, multi-step programming tasks
To-dos to try with GPT-5.1-Codex-Max
- Analyze this entire repository and identify potential security vulnerabilities in the authentication module.
- Review these architectural diagrams and generate the corresponding boilerplate code for the backend API.
- Refactor this legacy codebase to support the new database schema while maintaining existing functionality.
FAQ
- What is the primary focus of GPT-5.1-Codex-Max? It is specifically designed for agentic, long-running software development and programming tasks.
- Can this model process visual information? Yes, the model accepts both text and images as input.
- How much does GPT-5.1-Codex-Max cost? GPT-5.1-Codex-Max costs $1.25 per million input tokens and $10 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 4.9 credits ($1 = 100 credits).
- What is the context window of GPT-5.1-Codex-Max? GPT-5.1-Codex-Max can read up to 400K tokens at once and write up to 128K tokens in one reply.
- Can I use GPT-5.1-Codex-Max without coding? Yes. In todo.is you pick GPT-5.1-Codex-Max as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.