Mistral · open weights · medium
Mistral: Mistral Small 3.2 24B
Open weights, so you can run it locally. The published id includes 24B. That label is copied from the id, not measured here. Size class is this site's filter bucket, not a benchmark.
API price, in pounds
- Input, per million
- £0.0745
- Output, per million
- £0.224
OpenRouter lists $0.1000 in and $0.3000 out per million tokens. Converted at 0.74501 on 2026-11-10. Fetched 2026-11-11. Context length listed as 256,000 tokens.
Sourced local speeds
No sourced tokens-per-second figure for this model. A speed is not invented. You can type one in the calculator if you have measured it.
Comparisons
- Mistral: Mistral Small 3.2 24B on GeForce RTX 5090
- Mistral: Mistral Small 3.2 24B on GeForce RTX 3090
- Mistral: Mistral Small 3.2 24B on GeForce RTX 4090
- Mistral: Mistral Small 3.2 24B on GeForce RTX 4070 Ti SUPER
- Mistral: Mistral Small 3.2 24B on GeForce RTX 4080 SUPER
- Mistral: Mistral Small 3.2 24B on GeForce RTX 5070 Ti