For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.0000001 | $0.100 |
| completion | 0.0000004 | $0.400 |
| web_search | 0.01 | $10000 |
| input_cache_read | 0.00000003 | $0.030 |