Skip to content

Model detail

gpt-5.1-codex-max

Provided by OpenAI
Pay-as-you-go

GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic workflows spanning software engineering, mathematics, and research. GPT-5.1-Codex-Max delivers faster performance, improved reasoning, and higher token efficiency across the development lifecycle.

Model specs

Context length
400K
Max output
128K
I/O modalities
Text / Image
Released
2025-12

02

API endpoints

One MixRoute gateway, OpenAI-compatible

  • OpenAI-compatible /v1/chat/completions POST

03

Pricing

Flat rate, unit: /1M Tokens

Input

$1.2500 /1M Tokens

Completion

$10.0000 /1M Tokens

05

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

Long-running, high-context software development workflows

Use gpt-5.1-codex-max for extended agentic work across software engineering, mathematics, and research-oriented development tasks.

What should you check before using it?

Constrain long-running execution before scaling

Set clear task boundaries, tool permissions, time limits, and review checkpoints, then assess token efficiency and completion quality.

How should you start?

Use gpt-5.1-codex-max on a supervised long task

Begin with model ID gpt-5.1-codex-max in a sandboxed workflow where intermediate changes and final output can be reviewed.

08

Token cost estimator

Live estimate from this page's pricing, not an actual bill

This model has no cache-read price; caching is not counted

09

FAQ

gpt-5.1-codex-max is intended for long-running, high-context software development work across engineering, mathematics, and research-oriented workflows.

One endpoint, a testable decision

Test this model and alternate routes with the same request format

Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.