Mistral AI — Open-Source LLM Platform
Workload Suitability Matrix: Multi-Node Training: Mistral AI provides open-weight models with competitive performance. Spot Inference Prototyping: La Plateforme offers documented free tier with phone ...
Hosted Models & Token Rates
| MODEL | TOKENS/SEC | INPUT /1M | OUTPUT /1M | FREE TIER | CONTEXT |
|---|---|---|---|---|---|
Mistral Small v2409 24B | 70 tok/s | $0.10 | $0.10 | — | 128K |
Codestral 22B | 55 tok/s | $0.30 | $0.90 | — | 32K |
Codestral 22B | 1 tok/s | $0.00 | $0.00 | 128K |
Competitor Comparison
| PROVIDER | MIN PRICE / HR | AVG TOKEN RATE | FREE TIER | BILLING | KEY ADVANTAGE |
|---|---|---|---|---|---|
| Mistral AI | — | $0.00/1M | 1 RPS (60 RPM) free tier; phon... | per-token | ★ You are here |
| Groq | — | $0.00/1M | 30 requests per minute (RPM) f... | per-token | LPU Inference Engine |
| Cerebras | — | $0.00/1M | Limited free tier available; c... | per-token | Wafer-Scale AI Inference |
| DeepInfra | — | $0.00/1M | Generous free tier with rate l... | per-token | Serverless Open-Source Inference |
Technical Nuances & Editorial Analysis
Workload Suitability Matrix: Multi-Node Training: Mistral AI provides open-weight models with competitive performance. Spot Inference Prototyping: La Plateforme offers documented free tier with phone verification; 128k context windows; multilingual support. Persistent Production API: Enterprise plans available; Mistral NeMo 12B and Mistral Large provide production-grade inference; strong multilingual and reasoning capabilities.
Billing Granularity
per-token
How charges are calculated
Hidden Costs
Phone verification required for free tier
Watch out for these fees
Free Tier
1 RPS (60 RPM) free tier; phone verification required via La Plateforme
Credit requirements and caps
Best Use Case
Best for API-based LLM inference
Ideal workload profile