GPT-4o pricing
OpenAI · list prices as of 2026-09-29
| Input | $2.50 per 1M tokens |
|---|---|
| Output | $10 per 1M tokens |
| Cached input (read) | $1.25 per 1M tokens |
| Batch / async | 50% off |
| Context window | 128K tokens |
| Longest answer | 16K tokens |
What a call costs
| Typical call | Input tokens | Output tokens | Per call | Per month at 1,000 a day |
|---|---|---|---|---|
| Chat reply | 1,000 | 300 | $0.0055 | $165.00 |
| Document summary | 6,000 | 400 | $0.0190 | $570.00 |
| Code change | 3,000 | 1,200 | $0.0195 | $585.00 |
No caching or batch discount. Your own prompt will differ: count it exactly below.
Price your own prompt on GPT-4oSimilarly priced models
- Command A (Cohere): about the same
- Gemini 3.1 Pro (preview) (Google): about the same
- GPT-5.2 (OpenAI): 1.1× more
- Claude Sonnet 5 (Anthropic): 1.1× cheaper
- Claude Sonnet 5.5 (Anthropic): 1.1× cheaper
Questions
How much does GPT-4o cost?
GPT-4o costs $2.50 per million input tokens and $10 per million output tokens, as of 2026-09-29.
How much is one GPT-4o call?
A call with 1,000 input tokens and a 300-token answer costs about $0.0055, or $165.00 a month at 1,000 calls a day.
How big is the GPT-4o context window?
128,000 tokens.