OpenAI: gpt-5.2-codex:free

GPT-5.2-Codex is OpenAI's most advanced model optimized for long-horizon, agentic coding tasks. It integrates the professional knowledge of the GPT-5.2 family with specialized capabilities for software engineering, such as repo-aware intelligence and native context compaction. This model features an "agentic execution loop" that allows it to generate, test, and refine code autonomously in sandboxed environments. With its "xhigh" reasoning effort setting, it can work independently for hours on complex refactors, migrations, and cybersecurity audits, maintaining high steerability and temporal consistency across thousands of files.