modelgrep
O

OpenAI: GPT-5 Mini

openai/gpt-5-mini

47th smartest of 180ReasoningToolsJSONVision
Use via OpenRouter ↗
Intelligence
38.9
47th of 180
Design Elo
1199
Game Dev
Speed
72
121st fastest
Latency
2.5s
first token
Input price
$0.250
114th cheapest
Context
400K
128K max out

How it compares

Smarter than74%
of all ranked models
Faster than61%
of all ranked models
Cheaper than62%
of all ranked models

Overview

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....

Benchmarks

independent · via OpenRouter
Artificial Analysis71th percentile
Intelligence Index
38.9
Coding Index
32.8
Agentic Index
40.9
GPQA Diamond
80%
Humanity's Last Exam
15%
SciCode
41%
Tau²-Bench (agentic)
71%
Design Arena · Elo16,874 tournaments
Game Dev
1199
Website
1170
asciiart
1167
codecategories
1166
UI Component
1165
Data Viz
1164
svg
1148
3D
1107

Providers & pricing (3)

ProviderIn $/MOut $/MUptime
OpenAIcache$0.250$2.00100%
Azure$0.250$2.00
Azure$0.250$2.00100%

Specifications

Context window400K
Max output128K
Knowledge cutoffMay 2024
Input modalitiestext, image, file
Output modalitiestext
Prompt cachingSupported
Cache read price$0.025/M
ModeratedYes

GPT-5 Mini FAQ

How much does GPT-5 Mini cost?

GPT-5 Mini costs $0.250 per million input tokens and $2.00 per million output tokens via OpenRouter, making it 114th cheapest of 298 paid models.

How smart is GPT-5 Mini?

GPT-5 Mini scores 38.9 on the Artificial Analysis Intelligence Index, ranking 47th of 180 benchmarked models, with a GPQA Diamond score of 80%.

How fast is GPT-5 Mini?

GPT-5 Mini generates around 72 tokens per second with 2.5s time-to-first-token (p50), the 121st fastest tracked model.

What is GPT-5 Mini's context window?

GPT-5 Mini supports a 400K-token context window and can output up to 128K tokens. It accepts text, image, file input.

Compare head-to-head