Pass IndexThe State of AISign in

GPT-5.1 Codex

GPT-5.1-Codex is a version of GPT-5.1 optimized for agentic coding tasks in Codex or similar environments.

text + image + file → text · made by OpenAI

$1.25$10per Mtok in / out
Microsoft Azure AI · 4 sellers

Sold by 8 ways

SellerLaneRate
Databricks 0 ways$1.25per Mtok in$10per Mtok out$0.13per Mtok cached$1.25per Mtok cache write
Databricks cloudnot on the seller's list todaystandard$1.25per Mtok in$10per Mtok out$0.13per Mtok cached$1.25per Mtok cache writeraw.githubusercontent.com · read 2026-08-30
DigitalOcean 0 ways$1.25per Mtok in$10per Mtok out$0.12per Mtok cached
DigitalOcean cloudnot on the seller's list todaystandard$1.25per Mtok in$10per Mtok out$0.12per Mtok cachedmodels.dev · read 2026-08-27
Microsoft Azure AI cloudstandard$1.25per Mtok in$10per Mtok out$0.12per Mtok cachedmodels.dev · read 2026-09-16
Microsoft Azure AI cloudpriority$2.5per Mtok in$20per Mtok out$0.25per Mtok cachedraw.githubusercontent.com · read 2026-09-16
Nous Research aggregatorstandard$1.25per Mtok in$10per Mtok out$0.13per Mtok cachedinference-api.nousresearch.com · read 2026-09-12
OpenRouter aggregatorstandard$1.25per Mtok in$10per Mtok out$0.13per Mtok cachedopenrouter.ai · read 2026-08-24
Requesty 0 ways$1.25per Mtok in$10per Mtok out$0.12per Mtok cached
Requesty aggregatornot on the seller's list todayopenai-responses$1.25per Mtok in$10per Mtok out$0.12per Mtok cachedrouter.requesty.ai · read 2026-08-28
Vercel AI Gateway aggregatorstandard$1.25per Mtok in$10per Mtok out$0.13per Mtok cachedai-gateway.vercel.sh · read 2026-08-25

Measured 14 standings

PlaceBoardMetricScore
19thof 47SWE-bench Verified (default "Bash Only" view, agent = mini-SWE-agent)% Resolved (medium)66
27thof 112Ale bench — Epoch AIPerformance1244.92
35thof 65Apex agents — Epoch AIPass@1 score0.207
35thof 63Design Arena · mobileapps (agents)Elo1191
46thof 64Design Arena · fullstack (agents)Elo1086
55thof 202Terminalbench — Epoch AIAccuracy mean0.578
58thof 150Design Arena · uicomponent (models)Elo1252
61stof 62Design Arena · webapps (agents)Elo1034
64thof 152Design Arena · dataviz (models)Elo1229
92ndof 155Design Arena · gamedev (models)Elo1161
97thof 156Design Arena · codecategories (models)Elo1168
100thof 121Webdev arena — Epoch AIArena Score1336.28
102ndof 162Design Arena · website (models)Elo1174
102ndof 128LMArena · WebDevScore (Elo)1336

About

GPT-5.1 Codex — a text model from OpenAI, sold by 4 companies from $1.25 in and $10 out per million tokens, placed 27th of 112 on Ale bench — Epoch AI.

It takes text, images and files and returns text, with a context window of 400,000 tokens. It was published in 2025, trained on material up to September 2024. Its sellers say it can reason step by step and call a tool. The catalogue files it under code and agents. Four companies sell it. The cheapest is $1.25 in and $10 out per million tokens at Microsoft Azure AI. Beside the standard rate there is a faster lane. It has been measured on 14 boards, and stands best at 27th of 112 on Ale bench — Epoch AI.

Every current figure

Maker
OpenAI
Register
model
Takes
text + image + file
Returns
text
Context
400,000 tokens
Longest answer
272,000 tokens
Published
2025
Knowledge to
September 2024
Licence
not read
Sellers
4
Maker's own price
not read
Price
$1.25 in and $10 out per million tokens — Microsoft Azure AI
Boards
14
Best place
27th of 112 — Ale bench — Epoch AI

Known as 4 names

GPT 5.1 Codex medium5.1 codexopenai/gpt-5.1-codexopenai-responses/gpt-5.1-codex