OpenAI

o4 Mini High

Generally available200K contextReasoning

Summary

o4 Mini High is a language model from OpenAI, released on 16 Apr 2025. It accepts images, text and files and generates text, with a 200K-token context window and up to 100K output tokens per response.

OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...

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

Specifications

DeveloperOpenAI
Release date16 Apr 2025 [OpenRouter]
StatusGenerally available
Context window200K (200,000 tokens) [OpenRouter]
Max output100K tokens [OpenRouter]
Knowledge cutoff30 Jun 2024 [OpenRouter]
InputImages, text and files [OpenRouter]
OutputText [OpenRouter]
Reasoning modeYes [OpenRouter]
Tool callingYes [OpenRouter]
Structured outputYes [OpenRouter]

o4 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 o4 Mini High?

o4 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 o4 Mini High released?

OpenAI released o4 Mini High on 16 Apr 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 Opus 4Anthropic22 May 2025200K––Closed
Claude Sonnet 4Anthropic22 May 2025200K––Closed
Llama Guard 4 12BMeta29 Apr 2025164K$0.18$0.18Open
DeepSeek V3 0324DeepSeek24 Mar 2025164K$0.25$1Open
DeepSeek-R1-0528DeepSeek28 May 2025164K$0.50$2.15Open
Command ACohere13 Mar 2025256K$2.50$10Open

Change history

  • No longer listed on openrouter

Sources