LLM ReferenceLLM Reference

GPT-5.1 Codex Max

ProprietaryMultimodal

About

OpenAI's GPT-5.1-Codex-Max is a code-specialized model released November 19, 2025, optimized for agentic coding tasks including project-scale refactors, debugging, and multi-file edits. Uses context compaction to handle long-running tasks beyond a single context window. 30% more token-efficient than previous Codex on SWE-bench. Supports an extra-high reasoning effort option.

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

Providers(1)

ProviderInput (per 1M)Output (per 1M)Type
OpenRouter$1.25$10Serverless

Rankings

Specifications

FamilyGPT-5.1
Released2025-11-19
Specializationcoding

Created by

Cutting-edge research and development.

San Francisco, California, United States
Founded 2015
Website

Providers(1)