Mistral: Models and Prices

Model lab that also hosts other labs’ open-weight models on its platform.

Mistral served 254B tokens of other labs' open-weight models over Nov 2 to Nov 8, 2026 through a large public LLM router, #35 among providers.

Open-weight models

ModelFamilyShare of modelTokens, 7dInput $/MOutput $/MTokens/sUptime 3dContext
DeepSeek V4.1 Flash 1017DeepSeek0.3%155B$0.30$1.205399.8%1.05M
Mistral Large 4Mistral100.0%131B$0.70$2.107799.5%1.05M
GLM 5.3GLM1.5%54B$1.40$4.4053100.0%1.05M
GLM 5.2GLM3.3%26B$1.40$4.406399.9%1.05M
GLM 5.3 FlashGLM0.1%19B$0.15$0.50100100.0%1.05M
Mistral Small 4Mistral100.0%12B$0.15$0.60100100.0%262K
Mistral Small 3.2 24BMistral100.0%9B$0.10$0.3069100.0%33K
Devstral 2 2512Mistral100.0%3B$0.40$2.0097100.0%262K
Ministral 3 3B 2512Mistral100.0%3B$0.10$0.10140100.0%131K
Ministral 3 8B 2512Mistral100.0%818M$0.15$0.1591100.0%262K
Ministral 3 14B 2512Mistral100.0%494M$0.20$0.2065100.0%262K
Mistral NemoMistral--$0.15$0.1593100.0%131K
Mixtral 8x22B InstructMistral--$2.00$6.0076100.0%66K
Voxtral Small 24B 2507Mistral--$0.10$0.3062.5100.0%33K

List prices per million tokens as of November 8, 2026. Share: of all tokens served on that model; a dash where the volume is not reported.

Company

Website
mistral.ai
Headquarters
Paris, France

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