Head to head

Devstral Small 2 vs Qwen3.5 9B

On a blended workload of one million input tokens and three million output tokens, Qwen3.5 9B is 1.1× cheaper than Devstral Small 2.

Devstral Small 2Qwen3.5 9B
Provider Mistral Together AI
Input / MTok $0.1 $0.17
Output / MTok $0.3 $0.25
Cache read / MTok
Context window 262,144
Blended 1M in + 3M out $1.00 $0.92
Status ga ga

Devstral Small 2 detail   Qwen3.5 9B detail