GPT-4.1 nano pricing
OpenAI · list prices as of 2026-09-29
| Input | $0.10 per 1M tokens |
|---|---|
| Output | $0.40 per 1M tokens |
| Cached input (read) | $0.025 per 1M tokens |
| Batch / async | 50% off |
| Context window | 1.048M tokens |
| Longest answer | 33K 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 | $0.00022 | $6.60 |
| Document summary | 6,000 | 400 | $0.00076 | $22.80 |
| Code change | 3,000 | 1,200 | $0.00078 | $23.40 |
No caching or batch discount. Your own prompt will differ: count it exactly below.
Price your own prompt on GPT-4.1 nanoSimilarly priced models
- Gemini 2.5 Flash-Lite (Google): about the same
- Mistral Small 3 (Mistral): 1.2× cheaper
- GPT-5 nano (OpenAI): 1.3× cheaper
- GPT-4o mini (OpenAI): 1.5× more
- Llama 4 Scout (Meta): 1.6× more
Questions
How much does GPT-4.1 nano cost?
GPT-4.1 nano costs $0.10 per million input tokens and $0.40 per million output tokens, as of 2026-09-29.
How much is one GPT-4.1 nano call?
A call with 1,000 input tokens and a 300-token answer costs about $0.00022, or $6.60 a month at 1,000 calls a day.
How big is the GPT-4.1 nano context window?
1,047,576 tokens.