Head to head
GPT-4.1 nano vs Devstral Small 2
On a blended workload of one million input tokens and three million output tokens, Devstral Small 2 is 1.3× cheaper than GPT-4.1 nano.
| GPT-4.1 nano | Devstral Small 2 | |
|---|---|---|
| Provider | OpenAI | Mistral |
| Input / MTok | $0.1 | $0.1 |
| Output / MTok | $0.4 | $0.3 |
| Cache read / MTok | $0.025 | — |
| Context window | 1,047,576 | — |
| Blended 1M in + 3M out | $1.30 | $1.00 |
| Status | ga | ga |