modelgrep
O

OpenAI: o4 Mini

openai/o4-mini

67th smartest of 178ReasoningToolsJSONVision
Use via OpenRouter ↗
Intelligence
33.1
67th of 178
Design Elo
1072
Game Dev
Speed
122
45th fastest
Latency
4.5s
first token
Input price
$1.10
213th cheapest
Context
200K
100K max out

How it compares

Smarter than62%
of all ranked models
Faster than85%
of all ranked models
Cheaper than29%
of all ranked models

Overview

OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...

Benchmarks

independent · via OpenRouter
Artificial Analysis60th percentile
Intelligence Index
33.1
Coding Index
25.6
Agentic Index
36.1
GPQA Diamond
78%
Humanity's Last Exam
18%
SciCode
47%
Tau²-Bench (agentic)
56%
Design Arena · Elo886 tournaments
Game Dev
1072
UI Component
1041
Data Viz
1035
Website
1030
codecategories
1028
3D
934

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
OpenAI$1.10$4.40100%

Specifications

Context window200K
Max output100K
Knowledge cutoffJun 2024
Input modalitiesimage, text, file
Output modalitiestext
Prompt caching
Cache read price$0.275/M
ModeratedYes

o4 Mini FAQ

How much does o4 Mini cost?

o4 Mini costs $1.10 per million input tokens and $4.40 per million output tokens via OpenRouter, making it 213th cheapest of 298 paid models.

How smart is o4 Mini?

o4 Mini scores 33.1 on the Artificial Analysis Intelligence Index, ranking 67th of 178 benchmarked models, with a GPQA Diamond score of 78%.

How fast is o4 Mini?

o4 Mini generates around 122 tokens per second with 4.5s time-to-first-token (p50), the 45th fastest tracked model.

What is o4 Mini's context window?

o4 Mini supports a 200K-token context window and can output up to 100K tokens. It accepts image, text, file input.

Compare head-to-head