Back to models

o4-mini

Fast, cost-efficient reasoning model, succeeded by GPT-5 mini

Context window128,000 tokens
Max output tokens4,096 tokens

Pricing

TypeInputOutput
Standard$2.00 / 1M tokens$8.00 / 1M tokens
Cached input$0.50 / 1M tokens

Parameters

ParameterDefaultRange
Max stop sequences0

Supported features

Capabilities

  • Streaming
  • Reasoning
  • System Prompt

Endpoints

  • Chat Completions
  • Batch

Use cases

  • text-chat
  • reasoning

Model specifications

Model IDo4-mini
FamilyOther
Access typeClosed
Input modalitiestext
Output modalitiestext
Last updatedJanuary 3, 2026