Mistral: Models and Prices
Model lab that also hosts other labs’ open-weight models on its platform.
Mistral served 576B tokens of other labs' open-weight models over Oct 3 to Oct 9, 2026 through a large public LLM router, #20 among providers.
Open-weight models
| Model | Family | Share of model | Tokens, 7d | Input $/M | Output $/M | Tokens/s | Uptime 3d | Context |
|---|---|---|---|---|---|---|---|---|
| GLM 5.3 | GLM | 11.5% | 378B | $1.40 | $4.40 | 108 | 99.5% | 1.05M |
| GLM 5.2 | GLM | 13.0% | 198B | $1.40 | $4.40 | 102 | 100.0% | 1.05M |
| Mistral Small 4 | Mistral | 100.0% | 10B | $0.15 | $0.60 | 146 | 99.7% | 262K |
| Ministral 3 8B 2512 | Mistral | 100.0% | 6B | $0.15 | $0.15 | 79 | 99.9% | 262K |
| Ministral 3 3B 2512 | Mistral | 100.0% | 4B | $0.10 | $0.10 | 170 | 100.0% | 131K |
| Ministral 3 14B 2512 | Mistral | 100.0% | 2B | $0.20 | $0.20 | 67 | 98.2% | 262K |
| Devstral 2 2512 | Mistral | 100.0% | 2B | $0.40 | $2.00 | 53 | 100.0% | 262K |
| Mistral Nemo | Mistral | - | - | $0.15 | $0.15 | 48 | 100.0% | 131K |
| Mistral Small 3.2 24B | Mistral | - | - | $0.10 | $0.30 | 147 | 99.4% | 33K |
| Voxtral Small 24B 2507 | Mistral | - | - | $0.10 | $0.30 | 119 | 96.9% | 33K |
| Mixtral 8x22B Instruct | Mistral | - | - | $2.00 | $6.00 | 97 | 97.1% | 66K |
List prices per million tokens as of October 9, 2026. Share: of all tokens served on that model; a dash where the volume is not reported.
Company
- Website
- mistral.ai
- Headquarters
- Paris, France
- Status page
- status.mistral.ai
Sources: Mistral AI.
Finance your GPUs
Serving tokens on your own GPUs? Tell us the cluster, the models you serve and the contracts behind them, and we will share it with partner funders that fit.
Prefer email? hello@amcompute.com