o3 Mini

openai/o3-mini-2025-01-31

OpenAI’s o3 Mini model accepts text and file inputs and generates text output. It supports tool use and reasoning, has a context window of up to 200 000 tokens, and is not open weight. Pricing is $1.1 per million input tokens and $4.4 per million output tokens; the model was released on 2023‑10‑01.

  • tool use
  • structured outputs
  • reasoning

At a glance

provideropenai
releasedOct 1, 2023
context200K
input / M$1.10

Specifications

What the API gives you

Context window
200K tokens
Max output
100K tokens
Input price
$1.10 / 1M tokens
Output price
$4.40 / 1M tokens
Cache read
$0.55 / 1M tokens
Modalities
text, file → text
Knowledge cutoff
Oct 31, 2023
Released
Oct 1, 2023

Measured evidence

Public benchmark record

FrontierMath Tiers 1-3 (Epoch AI)‡
10.5% ± 1.82026-08-27medium effort, evaluated 2026-08-27
FrontierMath Tiers 1-3 (Epoch AI)‡
18.6% ± 2.32026-06-11high effort, evaluated 2026-06-11
GPQA Diamond (Epoch AI)‡
68.2% ± 3.32026-07-20low effort, evaluated 2026-07-20
GPQA Diamond (Epoch AI)‡
77% ± 2.62025-02-13high effort, evaluated 2025-02-13
GPQA Diamond (Epoch AI)‡
74.3% ± 2.52025-01-31medium effort, evaluated 2025-01-31
OTIS Mock AIME (Epoch AI)‡
44.4% ± 7.52026-07-20low effort, evaluated 2026-07-20
OTIS Mock AIME (Epoch AI)‡
76.9% ± 5.22025-02-27high effort, evaluated 2025-02-27
OTIS Mock AIME (Epoch AI)‡
63.9% ± 62025-02-25medium effort, evaluated 2025-02-25
SimpleQA Verified (Epoch AI)‡
15.3% ± 1.12026-08-31high effort, evaluated 2026-08-31

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference. ‡ Submitted scaffold plus model result. Compare the harness and effort settings, not only the model name.

Task evidence

How broad is the support?

Each status is exact to this model version and the selected task. Official release claims remain provisional.

  • Best LLM for Competition MathEstablished evidence

    30% of intended weighted task evidence across 2 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • Best LLM for Math & ReasoningEstablished evidence

    24% of intended weighted task evidence across 3 independent sources. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for Logic & Problem SolvingProvisional evidence

    18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Grounded RAGProvisional evidence

    14% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from CRAG or FACTS Grounding. 5 of 7 configured evaluation feeds currently have results.

  • Best LLM for a General AssistantProvisional evidence

    9% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 6 of 6 configured evaluation feeds currently have results.

Recommendation coverage

Where this model appears

Not currently included in a published recommendation. The task evidence panel above says exactly what is confirmed and what is still missing.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.