o4-mini Models by OpenAI

OpenAIProprietary
OpenAI releases · 51 in the last 12 monthsChangelog →
1 model2025Up to 200k ctxFrom $2.00/1M input

Last refreshed 2026-06-04. Next refresh: weekly.

Details

ResearcherOpenAI
LicenseProprietary
Commercial useCommercial use: conditional
Models1
Released2025
Max context200k

Capabilities

VisionAll models
MultimodalAll models
Structured OutputsAll models

About

o4-mini is OpenAI’s small o-series reasoning model in the API, aimed at fast, efficient reasoning with strong coding and visual-task performance. It takes text and image input and returns text, supports reasoning tokens, function calling, structured outputs, streaming, and fine-tuning, and offers a large context window with high max output length. OpenAI documents it as succeeded by GPT-5 Mini.

Decision facts

Best fit
vision and multimodal workstructured outputscoding
Capability starting point
o4 Mini Deep Research with 200k context and structured outputs and multimodal inputs
Lowest tracked input
o4 Mini Deep Research · $2.00/1M · OpenRouter
Closest related family
GPT-5

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

1 in view
o4 Mini Deep ResearchCurrent

Use when the workload needs 200k context, structured outputs, and multimodal inputs.

2025-04200k contextstructured outputsmultimodal inputs

Release Timeline

1 release group
2025-04
1 current
o4 Mini Deep Research
200k contextstructured outputsmultimodal inputs
Current

Specifications(1 models)

o4-mini model specifications comparison
ModelReleasedContextVisionMultimodalStructured Outputs
o4 Mini Deep Research2025-04200kYesYesYes

Available From(2 providers)

OpenAI APIOpenRouter

Pricing

o4-mini model pricing by provider
ModelProviderInput / 1MOutput / 1MType
o4 Mini Deep ResearchOpenRouter$2$8Serverless
o4 Mini Deep ResearchOpenAI API$2$8Serverless