OpenAI

o3 Mini High

Generally available200K contextReasoning

Summary

o3 Mini High is a language model from OpenAI, released on 12 Feb 2025. It accepts text and files and generates text, with a 200K-token context window and up to 100K output tokens per response.

OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...

Last verified 4 Oct 2026. Every figure on this page links to its source.

Specifications

DeveloperOpenAI
Release date12 Feb 2025 [OpenRouter]
StatusGenerally available
Context window200K (200,000 tokens) [OpenRouter]
Max output100K tokens [OpenRouter]
Knowledge cutoff31 Oct 2023 [OpenRouter]
InputText and files [OpenRouter]
OutputText [OpenRouter]
Reasoning modeYes [OpenRouter]
Tool callingYes [OpenRouter]
Structured outputYes [OpenRouter]

o3 Mini High API pricing by provider

USD per million tokens. Sorted by input price.

We do not currently track a paid API listing for this model.

Frequently asked questions

What is the context window of o3 Mini High?

o3 Mini High has a context window of 200,000 tokens (200K) and can generate up to 100,000 tokens in a single response, according to OpenRouter.

When was o3 Mini High released?

OpenAI released o3 Mini High on 12 Feb 2025, according to OpenRouter.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Claude 3.7 SonnetAnthropic19 Feb 2025200K––Closed
Command ACohere13 Mar 2025256K$2.50$10Open
DeepSeek V3 0324DeepSeek24 Mar 2025164K$0.25$1Open
Phi 4 MultimodalMicrosoft26 Feb 2025128K––Open
Command R7B ArabicCohere27 Feb 2025128K$0.04$0.15Open
Qwen2.5-VL 72B InstructAlibaba (Qwen)26 Jan 2025128K$0.80$1Open

Change history

  • No longer listed on openrouter

Sources