Oo3 Mini (batch)API

OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding.

200KContext window · tokens

$0.55Input price · per M tokens

$2.2Output price · per M tokens

OpenAIProvider

Prices update automatically — checked daily against provider list prices.

$0.96 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
cheaper than 68% of the 192 commercial models tracked here
24 of 88 OpenAI models tracked here, from cheapest

See open-source alternatives → Compare all model prices

Benchmarks & performance

Independent benchmark scores for o3 Mini (batch), measured by Artificial Analysis. Higher is better.

Intelligence index19.2

GPQA74.8%

MMLU-Pro79.1%

Humanity's Last Exam7.9%

LiveCodeBench71.7%

SciCode39.9%

MATH-50097.3%

AIME77%

τ²-Bench28.7%

Terminal-Bench Hard6.8%

💰 Blended price$1.925 / 1M tokens

📈 Value10 intelligence points per $

vs. models measured heretop 67%

Scores higher than 33% of the 273 models measured by Artificial Analysis and tracked here.
Models at this level cost $0.91 per 1M tokens (median of 21) — this one costs $0.96.
Cheaper and better on this index: GLM 5.3 Flash · Gemini 3.7 Flash · Gemini 3.7 Flash (batch) and 67 more

Benchmark data by Artificial Analysis

About this model

o3 Mini (batch) is a commercial AI model by OpenAI. The specifications below are tracked automatically: pricing is refreshed daily from public list prices, so the numbers on this page reflect the current cost of using the model through its API.

Frequently asked questions

What is o3 Mini (batch)?

o3 Mini (batch) is an AI language model from OpenAI. It is a proprietary model, available through an API. It scores 19.2 on the Artificial Analysis intelligence index.

Is o3 Mini (batch) free?

o3 Mini (batch) is not free: it costs $0.55 per million input tokens and $2.2 per million output tokens. Open-weight alternatives can be self-hosted at no per-token cost.

What is o3 Mini (batch) good at?

Independent benchmarks from Artificial Analysis give it GPQA 74.8%, MMLU-Pro 79.1%, Humanity's Last Exam 7.9%, LiveCodeBench 71.7%, SciCode 39.9%, MATH-500 97.3%, AIME 77%, τ²-Bench 28.7%, Terminal-Bench Hard 6.8%.