OpenAI o3-mini

OpenAI o3-mini is a compact reasoning model for math, science, and coding, with up to 100,000 output tokens.

Reasoning
Vision by description
Tool Calling
Structured Output

Pricing

Auto routing · per 1M tokens

Input: $1.10
Output: $4.40
Cache read: $0.55

Compare provider prices

Specifications

Context window: 200K
Max output: 100K
Avg output (7d): 82 tokens; Longer than 6% of models

Benchmarks

Artificial Analysis

LMArena

Sourced from Artificial Analysis.

Intelligence Index

12.5

Better than 48% of models compared

Agentic work

T²-Bench Telecom (legacy)

Legacy fallback · Conversational AI agents in dual-control scenarios

28.7%

Better than 36% of models compared

Reasoning

HLE

Humanity's Last Exam

7.9%

Better than 45% of models compared

Coding

Terminal-Bench Hard (legacy)

Legacy fallback · Agentic coding and terminal use

6.8%

Better than 37% of models compared

LiveCodeBench

Contamination-free coding benchmark

71.7%

Better than 82% of models compared

Math

AIME

American Invitational Mathematics Examination

77.0%

Better than 86% of models compared

Math-500

Diverse mathematical problem solving benchmark

97.3%

Better than 88% of models compared

Knowledge

MMLU-Pro

Professional and academic subject knowledge

79.1%

Better than 63% of models compared

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

74.8%

Better than 56% of models compared

Last updated Oct 3, 2026