Providers / Mistral
Mistral API Pricing
Mistral prices its API on a per-million-token Standard schedule. Mistral Large 4 is the current flagship at $1.36 / $4.18 per million tokens with cached input at $0.14, and Mistral Medium 3.5 is the mid-tier multimodal option at $1.50 / $7.50 with cached input at $0.15. Large 4 carries a 1M-token context window; Medium 3.5 is 256k.
This page tracks Mistral’s own Standard list prices only. Batch and Priority columns exist on the official pricing page and are not folded into the calculator rows below. Third-party gateways that resell Mistral models use their own rates and are never mixed into this table.
Figures below are official USD rates from docs.mistral.ai inference pricing, each stamped with a verification date. Le Chat / Vibe consumer subscriptions are separate products.
Mistral models and prices
USD per 1M tokens, official API list prices.
| Model | Input | Output | Cached | Batch | Verified |
|---|---|---|---|---|---|
| Mistral Large 4 | $1.36 | $4.18 | $0.14 | — | 2026-10-27 |
| Mistral Medium 3.5 | $1.5 | $7.5 | $0.15 | — | 2026-10-27 |
Frequently asked questions
What is the cheapest Mistral API model?
Mistral Large 4, at $1.36 per 1M input tokens and $4.18 per 1M output tokens (verified 2026-10-27). Its cost calculator shows worked examples at realistic volumes.
Are these Mistral's official prices?
Yes — this page tracks official API list prices only, each cross-checked and stamped with a verification date. Gateway resellers and consumer subscriptions use different schedules and are not mixed in.
How do I estimate my Mistral bill?
Open any model above and use its calculator: enter your input, output and cached token counts plus your call volume, and it computes the per-call and monthly cost from the same verified prices. The homepage calculator also compares models across providers side by side.