Meterary
Start free

OpenAI

o4-mini API Pricing

Page notes it has been "succeeded by GPT-5 mini"; snapshot o4-mini-2025-04-16 marked deprecated. Also has separate fine-tuning-tier pricing: standard inference $4.00/$16.00 (cached $1.00) per MTok, batch $2.00/$8.00, training $100/hour.

Verified against OpenAI’s pricing page on 2026-07-02.

View source ↗

Facts

Legacy

Specs

  • Familyo-series
  • API IDo4-mini
  • ModalityText
  • Context window200K tokens
  • Max output—
  • Release dateNot published

Pricing (per 1M tokens)

  • Input$1.10 / 1M tokens
  • Output$4.40 / 1M tokens
  • Cached input$0.275 / 1M tokens
  • Cache write—
  • Batch discount—

Capabilities

reasoning

Notes

Page notes it has been "succeeded by GPT-5 mini"; snapshot o4-mini-2025-04-16 marked deprecated. Also has separate fine-tuning-tier pricing: standard inference $4.00/$16.00 (cached $1.00) per MTok, batch $2.00/$8.00, training $100/hour.

Worked cost examples

Estimated monthly cost on three common usage shapes

WorkloadEst. monthly cost

Chatbot

800 input / 200 output tokens per request, 100,000 requests/month

$176.00

RAG pipeline

6,000 input / 700 output tokens per request, 30,000 requests/month

$290.40

Batch summarization

20,000 input / 1,500 output tokens per request, 5,000 requests/month

$143.00

Price history

Changes we have documented since we began tracking

No price changes recorded since we began tracking.

o4-mini pricing FAQ

How much does o4-mini cost per 1M tokens?
o4-mini costs $1.10 per 1M input tokens and $4.40 per 1M output tokens.
How much does o4-mini cost per request?
A typical request of 800 input and 200 output tokens costs about $0.0018 on o4-mini.
Is o4-mini cheaper than o1?
o4-mini is cheaper than o1 on input tokens, by about 93%.
Does o4-mini have cache pricing?
Yes — cached input reads cost $0.275 per 1M tokens.

Keep exploring

Estimate my usage