Head to head
Devstral Small 2 vs Qwen2.5 7B Instruct Turbo
On a blended workload of one million input tokens and three million output tokens, Devstral Small 2 is 1.2× cheaper than Qwen2.5 7B Instruct Turbo.
| Devstral Small 2 | Qwen2.5 7B Instruct Turbo | |
|---|---|---|
| Provider | Mistral | Together AI |
| Input / MTok | $0.1 | $0.3 |
| Output / MTok | $0.3 | $0.3 |
| Cache read / MTok | — | — |
| Context window | — | 32,768 |
| Blended 1M in + 3M out | $1.00 | $1.20 |
| Status | ga | ga |