GPT-5.2-Codex
GPT-5.2-Codex is an AI model developed by OpenAI specifically for software engineering and coding workflows. It supports both text and image inputs and is designed to handle complex engineering tasks through reasoning and tool-calling capabilities.
GPT-5.2-Codex specs and pricing
- Provider: OpenAI
- Released: January 14, 2026
- Context window: 400K tokens
- Max output: 128K tokens
- Input: text, images
- Output: text
- Price: $1.75 input / $14 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What GPT-5.2-Codex is good at
- Complex software engineering tasks
- Interactive development sessions
- Long-form code execution and analysis
To-dos to try with GPT-5.2-Codex
- Analyze this architectural diagram and identify potential security vulnerabilities in the proposed data flow.
- Review this entire codebase and suggest refactoring strategies to improve modularity.
- Execute a series of unit tests across these multiple files and summarize the failure points.
FAQ
- What is the primary focus of GPT-5.2-Codex? This model is optimized specifically for software engineering and coding workflows, supporting both interactive development and independent task execution.
- Can this model process visual information? Yes, GPT-5.2-Codex accepts both text and image inputs.
- How much does GPT-5.2-Codex cost? GPT-5.2-Codex costs $1.75 per million input tokens and $14 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 6.86 credits ($1 = 100 credits).
- What is the context window of GPT-5.2-Codex? GPT-5.2-Codex can read up to 400K tokens at once and write up to 128K tokens in one reply.
- Can I use GPT-5.2-Codex without coding? Yes. In todo.is you pick GPT-5.2-Codex 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.