EU-based; Mistral Small / Codestral with experimental free tier
Mistral La Plateforme — EU-based; Mistral Small / Codestral with experimental free tier. Free tier: Experimental free tier — 1 RPS, 500k tokens/min, 1B tokens/month. Best free-tier limits in the EU.
mistral-large-latestmistral-small-latestcodestral-latestministral-8b-latestministral-3b-latestMistral Small $0.20/1M input tokens, Mistral Large $2/1M input. Codestral $0.30/1M.
Self-hosted (on-prem) and dedicated cloud deployments.
https://api.mistral.ai/v1
Custom SDK / API shape.
curl https://api.mistral.ai/v1/chat/completions \
-H "Authorization: Bearer $MISTRAL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistral-small-latest",
"messages": [{"role": "user", "content": "Hello in 5 words"}]
}'
EU data-residency requirements, Codestral for code generation, Ministral for cost-sensitive edge use.
Latency-critical UX — Mistral inference is slower than Groq/Cerebras on the same models.
Experimental free tier — 1 RPS, 500k tokens/min, 1B tokens/month. Best free-tier limits in the EU. No credit card is required to sign up.
Most commonly used: mistral-large-latest, mistral-small-latest, codestral-latest, ministral-8b-latest. The full current list is on Mistral La Plateforme's docs page.
No — Mistral La Plateforme ships its own SDK. Code samples for Python, Node, and cURL are above.
Mistral Small $0.20/1M input tokens, Mistral Large $2/1M input. Codestral $0.30/1M. If your traffic is bursty or seasonal, the free tier may be enough; if you need a guaranteed SLA, upgrade.