The small, fast Mistral model is Mistral Small 4 — the efficient tier at 110 tokens/sec and $0.150 per million input tokens. It trades a few points of raw intelligence for speed and cost, the right call for high-volume, latency-sensitive work. Mistral Small 3.2 24B (92 t/s) and Mistral Nemo (75 t/s) round out the top three.
Compact, efficient models — the small/mini/flash/haiku tier — ranked by output speed. These trade a little raw intelligence for low cost and high throughput, which is the right tradeoff for chat, classification, extraction and other high-volume work.
The small, fast Mistral model is Mistral Small 4 — the efficient tier at 110 tokens/sec and $0.150 per million input tokens. It trades a few points of raw intelligence for speed and cost, the right call for high-volume, latency-sensitive work. Mistral Small 3.2 24B (92 t/s) and Mistral Nemo (75 t/s) round out the top three.
Mistral Small 3.2 24B (92 t/s) is the closest alternative on this metric, followed by Mistral Nemo (75 t/s). See the full ranking above for the tradeoffs.
modelgrep tracks 19 Mistral models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Mistral Medium 3.5. 10 of them qualify for this ranking.