o4 Mini
by OpenAItext+image+file->text1 endpoint
Neura Intelligence Index
57.1/ 100
Rank
#155—
Confidence
highBenchmarks
8(21% coverage)
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...
Capabilities
Text generation
Image understanding
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
File input
Deterministic seed
Modalities
Input
ImageTextFile
Output
Text
Technical Specifications
Context Window
200K tokens
Max Output
100K tokens
Knowledge Cutoff
2024-06-30
Tokenizer
GPT
Content Moderation
Enabled
Uptime (24h)
10000.0%
Country
🇺🇸US
Release Date
April 16, 20251y
Supported Parameters
include_reasoningmax_tokensreasoningresponse_formatseedstructured_outputstool_choicetools
Benchmark Performance
coding
| Benchmark | Score | Source |
|---|---|---|
| SWE-bench Verified | 68.1 | verified |
math
| Benchmark | Score | Source |
|---|---|---|
| AIME 2025 | 92.7 | verified |
reasoning
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 81.4 | verified |
| Humanity's Last Exam | 14.7 | verified |
multimodal
| Benchmark | Score | Source |
|---|---|---|
| MMMU | 81.6 | verified |
| CharXiv Reasoning | 72 | verified |
agent
| Benchmark | Score | Source |
|---|---|---|
| TAU-Bench Retail | 71.8 | verified |
| BrowseComp | 51.5 | verified |
Performance Over Time
Pricing
Per 1M tokens
Input$1.10
Output$4.40
Cache read$0.28
Added
April 16, 2025
Last synced 9/19/2026