modelgrep
O

OpenAI: GPT-5.1-Codex

openai/gpt-5.1-codex

30th smartest of 180ReasoningToolsJSONVision
Use via OpenRouter ↗
Intelligence
43.1
30th of 180
Design Elo
1218
Data Viz
Speed
55
159th fastest
Latency
2.4s
first token
Input price
$1.25
224th cheapest
Context
400K
128K max out

How it compares

Smarter than83%
of all ranked models
Faster than48%
of all ranked models
Cheaper than25%
of all ranked models

Overview

GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....

Benchmarks

independent · via OpenRouter
Artificial Analysis80th percentile
Intelligence Index
43.1
Coding Index
36.6
Agentic Index
50.7
GPQA Diamond
86%
Humanity's Last Exam
23%
SciCode
40%
Tau²-Bench (agentic)
83%
Design Arena · Elo1,936 tournaments
Data Viz
1218
mobileapps
1211
Game Dev
1208
Website
1206
codecategories
1203
fullstack
1103
webapps
1102

Providers & pricing (2)

ProviderIn $/MOut $/MUptime
Azurecache$1.25$10.00
OpenAIcache$1.25$10.00100%

Specifications

Context window400K
Max output128K
Knowledge cutoff
Input modalitiestext, image
Output modalitiestext
Prompt cachingSupported
Cache read price$0.130/M
ModeratedNo

GPT-5.1-Codex FAQ

How much does GPT-5.1-Codex cost?

GPT-5.1-Codex costs $1.25 per million input tokens and $10.00 per million output tokens via OpenRouter, making it 224th cheapest of 298 paid models.

How smart is GPT-5.1-Codex?

GPT-5.1-Codex scores 43.1 on the Artificial Analysis Intelligence Index, ranking 30th of 180 benchmarked models, with a GPQA Diamond score of 86%.

How fast is GPT-5.1-Codex?

GPT-5.1-Codex generates around 55 tokens per second with 2.4s time-to-first-token (p50), the 159th fastest tracked model.

What is GPT-5.1-Codex's context window?

GPT-5.1-Codex supports a 400K-token context window and can output up to 128K tokens. It accepts text, image input.

Compare head-to-head