O4 Mini
OpenAI's O4 Mini is a chat model capable of handling various inputs, including images, PDFs, and text, and excels at tasks such as math and coding. It is particularly strong in math-related benchmarks, with top 25% or better scores in Math Index, LiveCodeBench, AIME, and MATH-500. Notably, O4 Mini features an extended context window of 200,000 tokens, allowing it to process and understand lengthy inputs.
Input
Output
Context
200K
Max Output
100K
Parameters
-
Technical Specifications
Model TypeChat
Context Window200,000 tokens
Max Output Tokens100,000 tokens
ParametersNot available
Release DateApr 9, 2025
Training CutoffJun 1, 2024
Licenseproprietary
Open SourceNo
Input Modalities
ImageText
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
17.5%
HLE
94.0%
AIME
78.4%
GPQA
46.5%
SciCode
98.9%
MATH 500
83.2%
MMLU Pro
90.7
Math
25.6
Coding
85.9%
LiveCodeBench
25.6
Intelligence
168
Speed (tok/s)
25.9
TTFA (s)
25.9
TTFT (s)
Resources & Links
proprietary, Proprietary - API access only
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.