OpenAI
Reasoning

o3-mini

Reasoning

Cheaper reasoning model in the o3 generation. Strong on STEM, lower latency than full o3.

o3-mini is a reasoning AI model from OpenAI. It costs $1.10 per million input tokens and $4.40 per million output tokens (blended $2.09/M), with a 200,000-token context window.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$1.10/M
per million input tokens
OUTPUT
$4.40/M
per million output tokens
BLENDED 70/30
$2.09/M
unchanged since 3 May
CONTEXT
200,000
tokens

Hand-maintained from OpenAI's published pricing; no check date on record.

What it is good at
  • Cheap reasoning
  • STEM-tuned
  • Lower latency than o3
Typical use cases
  • Reasoning at scale
  • STEM tutoring
  • Cost-sensitive code review

Benchmarks

vs. best public score
MMLU85.9%
Multitask academic knowledge across 57 subjects. Source: OpenAI (self-reported), MMLU, read 2026-11-10.
Graduate-level science questions, "Google-proof". Source: OpenAI (self-reported), GPQA Diamond, read 2026-11-10.
HumanEval96.3%
Python function synthesis from docstrings. Source: OpenAI (self-reported), HumanEval, read 2026-11-10.
Real GitHub issues solved end-to-end. Source: OpenAI (self-reported), SWE-bench Verified, read 2026-11-10.
LMArena Elo1348 Elo
Crowd-sourced head-to-head preference Elo rating. Source: LMArena (independent), LMArena Text Arena score, read 2026-11-10.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

Also reported by the provider

Results on benchmarks outside the set we compare across models. They are listed for completeness and are deliberately excluded from the bars above and from every ranking on this site, because a score is only comparable against the same benchmark variant. Why benchmark scores do not compare →

  • MATH-50097.3%self-reported by OpenAI · 2025-07 · o3-mini default (medium) effort. simple-evals README, zero-shot chain of thought. Its footnote says models from o1 onward are scored on MATH-500, not the full MATH test set. Not comparable with the MATH column, so shown here and never ranked.

More from OpenAI

See all 28 →

Frequently asked questions

How much does o3-mini cost?

o3-mini costs $1.10 per million input tokens and $4.40 per million output tokens, for a blended reference rate of $2.09 per million tokens.

What is o3-mini's context window?

o3-mini supports up to 200,000 tokens of context in a single request.

What is o3-mini best for?

o3-mini is well suited to Cheap reasoning, STEM-tuned and Lower latency than o3.

Who makes o3-mini?

o3-mini is developed and served by OpenAI. It was released in Jan 2025.

Terms used on this page