Meterary
Start free

OpenAI

o1 API Pricing

Reasoning model. Current snapshot o1-2024-12-17 and o1-preview-2024-09-12 both marked deprecated on the model page, though o1 remains listed as "Default" in the model comparison.

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

View source ↗

Facts

Deprecated

Specs

  • Familyo-series
  • API IDo1
  • ModalityText
  • Context window200K tokens
  • Max output100K tokens
  • Release dateNot published

Pricing (per 1M tokens)

  • Input$15.00 / 1M tokens
  • Output$60.00 / 1M tokens
  • Cached input$7.50 / 1M tokens
  • Cache write—
  • Batch discount—

Capabilities

reasoning

Notes

Reasoning model. Current snapshot o1-2024-12-17 and o1-preview-2024-09-12 both marked deprecated on the model page, though o1 remains listed as "Default" in the model comparison.

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

$2,400

RAG pipeline

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

$3,960

Batch summarization

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

$1,950

Price history

Changes we have documented since we began tracking

No price changes recorded since we began tracking.

o1 pricing FAQ

How much does o1 cost per 1M tokens?
o1 costs $15.00 per 1M input tokens and $60.00 per 1M output tokens.
How much does o1 cost per request?
A typical request of 800 input and 200 output tokens costs about $0.024 on o1.
Is o1 cheaper than o3?
o1 is more expensive than o3 on input tokens, by about 650%.
Does o1 have cache pricing?
Yes — cached input reads cost $7.50 per 1M tokens.

Keep exploring

Estimate my usage