modelgrep
O

OpenAI: GPT-5.1-Codex-Mini

openai/gpt-5.1-codex-mini

48th smartest of 180ReasoningToolsJSONVision
Use via OpenRouter ↗
Intelligence
38.6
48th of 180
Design Elo
1162
Game Dev
Speed
126
39th fastest
Latency
2.0s
first token
Input price
$0.250
113th cheapest
Context
400K
100K max out

How it compares

Smarter than73%
of all ranked models
Faster than87%
of all ranked models
Cheaper than62%
of all ranked models

Overview

GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex

Benchmarks

independent · via OpenRouter
Artificial Analysis70th percentile
Intelligence Index
38.6
Coding Index
36.4
Agentic Index
38.7
GPQA Diamond
81%
Humanity's Last Exam
17%
SciCode
43%
Tau²-Bench (agentic)
63%
Design Arena · Elo17,153 tournaments
Game Dev
1162
Website
1155
asciiart
1147
codecategories
1145
Data Viz
1141
UI Component
1136
3D
1070
svg
1034

Providers & pricing (2)

ProviderIn $/MOut $/MUptime
OpenAI$0.250$2.0099.2%
Azurecache$0.250$2.00

Specifications

Context window400K
Max output100K
Knowledge cutoff
Input modalitiesimage, text
Output modalitiestext
Prompt cachingSupported
Cache read price$0.025/M
ModeratedYes

GPT-5.1-Codex-Mini FAQ

How much does GPT-5.1-Codex-Mini cost?

GPT-5.1-Codex-Mini costs $0.250 per million input tokens and $2.00 per million output tokens via OpenRouter, making it 113th cheapest of 298 paid models.

How smart is GPT-5.1-Codex-Mini?

GPT-5.1-Codex-Mini scores 38.6 on the Artificial Analysis Intelligence Index, ranking 48th of 180 benchmarked models, with a GPQA Diamond score of 81%.

How fast is GPT-5.1-Codex-Mini?

GPT-5.1-Codex-Mini generates around 126 tokens per second with 2.0s time-to-first-token (p50), the 39th fastest tracked model.

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

GPT-5.1-Codex-Mini supports a 400K-token context window and can output up to 100K tokens. It accepts image, text input.

Compare head-to-head