OpenAI
GPT-4o API Pricing
Legacy flagship, superseded by the GPT-5.x family but still listed as active/available on the model page (current snapshot gpt-4o-2024-11-20; earlier snapshot gpt-4o-2024-08-06 is deprecated).
Verified against OpenAI’s pricing page on 2026-07-02.
View source ↗Facts
Specs
- FamilyGPT-4o
- API IDgpt-4o
- ModalityMultimodal
- Context window128K tokens
- Max output—
- Release dateNot published
Pricing (per 1M tokens)
- Input$2.50 / 1M tokens
- Output$10.00 / 1M tokens
- Cached input$1.25 / 1M tokens
- Cache write—
- Batch discount—
Capabilities
vision, tool-use, function-calling, structured-outputs
Notes
Legacy flagship, superseded by the GPT-5.x family but still listed as active/available on the model page (current snapshot gpt-4o-2024-11-20; earlier snapshot gpt-4o-2024-08-06 is deprecated).
Worked cost examples
Estimated monthly cost on three common usage shapes
| Workload | Est. monthly cost |
|---|---|
Chatbot 800 input / 200 output tokens per request, 100,000 requests/month | $400.00 |
RAG pipeline 6,000 input / 700 output tokens per request, 30,000 requests/month | $660.00 |
Batch summarization 20,000 input / 1,500 output tokens per request, 5,000 requests/month | $325.00 |
Price history
Changes we have documented since we began tracking
No price changes recorded since we began tracking.
GPT-4o pricing FAQ
- How much does GPT-4o cost per 1M tokens?
- GPT-4o costs $2.50 per 1M input tokens and $10.00 per 1M output tokens.
- How much does GPT-4o cost per request?
- A typical request of 800 input and 200 output tokens costs about $0.004 on GPT-4o.
- Is GPT-4o cheaper than GPT-4o mini?
- GPT-4o is more expensive than GPT-4o mini on input tokens, by about 1567%.
- Does GPT-4o have cache pricing?
- Yes — cached input reads cost $1.25 per 1M tokens.