OpenAI · gpt-4o

GPT-4o pricing (November 2026)

OpenAI lists GPT-4o at $2.50 per 1M input tokens and $10.00 per 1M output tokens.

On Crazyrouter the same model is $2.00 / $8.00 — 20% below list price.

That is $0.0025 / $0.01 per 1K tokens. GPT-4o is the #30 cheapest of the 40 chat models we track, by input price. 16.7× the price of GPT-4o mini. Through Crazyrouter you save $0.50 on every 1M input tokens versus list.

Call GPT-4o at $2.00 in / $8.00 out per 1M tokens. Same model, same API, no plan — pay per token.

This page lists token-based pricing for the developer API. Consumer app subscriptions are billed separately.

GPT-4o price by provider

USD per 1M tokens. Cloud prices are the base tier in the default region; the linked source is authoritative.

per 1M tokensInputOutput
  • OpenAI$2.50$10.00
  • Azure$2.50$10.00
  • Crazyrouter$2.00$8.00
ProviderInputCached inputOutputContextSource
OpenAI$2.50$1.25$10.00128KOpenAI
Azure$2.50$1.25$10.00128KAzure OpenAI
Crazyrouter$2.00$1.00$8.00128Kcrazyrouter.com

AWS Bedrock · Google Vertex AI · OpenRouter: No verified quote

per 1M tokens · Snapshot Nov 2, 2026

What GPT-4o costs per month

Three typical workloads, priced on each provider from the table above.

  • Prototype: 10M in / 2M out

    Input 10M · Output 2M

    $36.00

    • OpenAI$45.00
    • Azure$45.00
    • Crazyrouter$36.00
  • Product: 100M in / 20M out

    Input 100M · Output 20M

    $360.00

    • OpenAI$450.00
    • Azure$450.00
    • Crazyrouter$360.00
  • Scale: 1B in / 200M out

    Input 1,000M · Output 200M

    $3,600

    • OpenAI$4,500
    • Azure$4,500
    • Crazyrouter$3,600

Price changes

  • Oct 21, 2026 — Azure: $2.50 / $10.00 → $2.75 / $11.00 per 1M

Alternatives to GPT-4o

Same-family models and cheaper options for similar tasks.

Guides and comparisons

GPT-4o pricing FAQ

How much does GPT-4o cost?

OpenAI charges $2.50 per 1M input tokens and $10.00 per 1M output tokens. Through Crazyrouter the same model is $2.00 / $8.00.

What is cached input pricing?

Tokens that repeat an earlier prompt prefix are billed at the cached rate ($1.25 per 1M when supported) instead of the full input price.

Is there a batch discount?

Yes. OpenAI offers batch pricing at $1.25 in / $5.00 out per 1M tokens for asynchronous jobs.

Is GPT-4o cheaper on Azure, Bedrock or Vertex?

Cloud providers usually match the list price and add regional or provisioned tiers; see the table above for the base rate on each. Crazyrouter applies its discount on top of list.

Sources and method

Provider reference prices use LiteLLM data and maintained entries. Provider links are references, not proof of daily official verification. Snapshot: Nov 2, 2026. Crazyrouter rates come from our billing table; confirm current prices, region and terms with the provider before purchase.

Further reading