GPT-5.1 Codex Max

At a glance

What GPT-5.1 Codex Max does

Tool use, Compaction across windows, Deep coding reasoning, Long-running tasks, Streaming, Function calling

Best for

Multi-hour, cross-file engineering tasks where context compaction matters; enterprise Codex CLI use

Works well with

Conflicts & caveats

• Trae's built-in model menu may not include GPT-5.1 Codex Max — Trae primarily ships with Claude/GPT/Gemini/DeepSeek.
• Kiro's spec mode is tuned for Claude models — GPT-5.1 Codex Max may work but spec-driven flows are best with Claude.
• Gemini CLI is locked to Google Gemini models — your LLM is GPT-5.1 Codex Max.
• Claude Code only works with Claude models — your LLM is GPT-5.1 Codex Max.
• Devin uses Cognition's proprietary model internally — your selected GPT-5.1 Codex Max will be ignored.
• OpenAI Codex (Cloud) runs GPT-5.1 Codex internally — your selected GPT-5.1 Codex Max will be ignored.
• Jules runs Gemini models internally — your selected GPT-5.1 Codex Max will be ignored.
• The Claude Code SDK is tuned for Claude models — GPT-5.1 Codex Max may work via the model adapter but loses Claude-specific features (thinking, prompt caching, sub-agents).
• Lovable uses a fixed internal model — your selected GPT-5.1 Codex Max will be ignored.
• Replit Agent 3 uses its own model selection internally — your selected GPT-5.1 Codex Max will be ignored.