GPT-5.1-Codex: pricing, context and benchmarks

What you need to know about GPT-5.1-Codex

OpenAI, based in United States, put GPT-5.1-Codex online on November 13, 2025. It accepts text and images as input and produces text. Its context window reaches 400,000 tokens, larger than 64 % of the models in the registry, and it can write up to 128,000 tokens in one go.

It has been available for about 11 months, long enough for its prices and scores to have settled.

GPT-5.1-Codex pricing

On OpenRouter, GPT-5.1-Codex costs $1.25 per million input tokens and $10 per million output tokens. Counting three tokens read for every token written, its average price is $3.438 per million, more expensive than 80 % of paid models (4.5 times the median of $0.76).

A concrete example: a task that sends 2,000 tokens (about 1,500 words) and receives a 500-token answer costs $0.0075. At 1,000 tasks a day, budget $225 a month. The price calculator redoes this with your own volumes.

Tokens already sent and cached are billed at $0.13 per million.

Performance and benchmarks

Epoch AI does not yet publish a capabilities index for GPT-5.1-Codex. We therefore show no made-up performance rating: only price, context and features count towards its score.

Scores published by Epoch AI on the benchmarks the site tracks:

Features, privacy and local use

• It supports tool calling, so it can drive an AI agent, call APIs or MCP servers.
• It can answer in an enforced JSON format (structured outputs).
• It is a reasoning model: it "thinks" before answering, which helps on hard tasks but uses more output tokens.

Its weights are not published: it can only be used through the OpenAI API or a broker such as OpenRouter, which means sending your data off your machines.

Other OpenAI models