Providers

Mistral

Verified

The French frontier lab — open-weight and commercial models served first-party via La Plateforme.

Start building View requests Official status

Models on Mistral

Open in catalog

9 of 9

Codestral 2508Chatcodestral-2508256K contextRouteprimary$0.30 / $0.90per M input / output

GLM 5.2Chatglm-5.2Released June 20261M contextWeights Routeemergency$1.40 / $4.40per M input / output

Ministral 3 14BChatministral-3-14b262K contextRouteprimary$0.20 / $0.20per M input / output

Ministral 3 3BChatministral-3-3b131K contextRouteprimary$0.10 / $0.10per M input / output

Ministral 3 8BChatministral-3-8b262K contextRouteprimary$0.15 / $0.15per M input / output

Mistral LargeChatmistral-large128K contextRouteprimary$2.00 / $6.00per M input / output

Mistral Large 3Chatmistral-large-3Released December 2025262K contextRouteprimary$0.50 / $1.50per M input / output

Mistral Medium 3.5Chatmistral-medium-3.5256K contextRouteprimary$1.50 / $7.50per M input / output

Mistral Small 4Chatmistral-small-4256K contextRouteprimary$0.15 / $0.60per M input / output

Performance

Response latency estimates

Time to first token

Generation speed · tok/s

Request success

Text-model timing and speed, plus API request success. Daily latency percentiles are estimates.

Direct routingCall Mistral explicitly

mistral· routing

# pin every request to Mistral
curl https://www.ninjachat.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $NINJACHAT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "codestral-2508",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "routing": { "providers": { "only": ["mistral"] } }
  }'