AI Models / Compare

o4-mini

Fast, affordable o-series reasoning model for coding and STEM tasks.

Creator: OpenAI
Lifecycle: Active
Context: 200.0K
Max output: 100.0K
Released: Apr 16, 2025
Status: up

Input: $1.10 / 1M tokens
Output: $4.40 / 1M tokens
Cached read: $0.28 / 1M tokens
Cached write: — / 1M tokens
Batch discount: 50%
Source: o4-mini pricing
Verified: Apr 5, 2026 (High)

Capabilities

Modalities: textimage→text
Capabilities: reasoningimageInputbatchSupportpromptCachingfunctionCallingstructuredOutputs
Strengths: Best price/performance for reasoning, Strong coding/math
Tradeoffs: No code execution or web search

Official Links

Intro

https://openai.com/index/introducing-o3-and-o4-mini/

Docs

https://developers.openai.com/api/docs/models

Pricing

https://platform.openai.com/docs/pricing/

Release note

https://help.openai.com/en/articles/9624314-model-release-notes

Benchmark Coverage

Benchmark	Version	Score	Date	Source	Notes
GPQA Diamond	2024	81.4 %	Apr 1, 2025	OpenAI	Vendor-reported
AIME 2025	2025	92.7 %	Apr 1, 2025	OpenAI	Vendor-reported
SWE-bench Verified	2024	68.1 %	Apr 1, 2025	OpenAI	Vendor-reported

Release History

Release	Alias	Lifecycle	Release Date	Deprecation	Shutdown	Summary
o4-mini	o4-mini	Active	Apr 16, 2025	—	—	Current published model family snapshot.

Host Coverage

Host	Type	Context	Pricing Note	Differences
OpenAI API	first-party	200.0K	Reference pricing.	Prompt caching; Batch API

Migration Guidance

Replaced o3-mini; best low-cost reasoning choice.

Change Events

Date	Type	Title	Description	Source
Apr 16, 2025	family_added	o4-mini published	Initial public model family launch.	o4-mini release notes

Other models from OpenAI

GPT-3.5 Turbo, GPT-4.1, GPT-4.1 mini, GPT-4.1 nano, GPT-4o, GPT-4o, GPT-4o mini, GPT-4o mini, GPT-5.4, GPT-5.4 mini, GPT-5.4 nano, o1, o3, o3-mini