Mistral Medium
As of Nov 22, 2026, the cheapest Mistral Medium API price is $0.4 per 1M input tokens (Merge Gateway) and $2 per 1M output tokens (Merge Gateway). Mistral Medium is offered by 5 providers in the mistral-medium family, open weights, reasoning enabled. Mistral's own rate is $7.5 per 1M output tokens.
API pricing by provider
Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked. Seeing a wide range? Why the same LLM costs different amounts.
| Merge Gatewayopenmistral/mistral-medium-latest | Cheapest$0.4 | Cheapest$2 | — | — | 262k |
| Requestyopenmistral-medium-latest | $0.44 | $2.2 | $0.44 | — | 131k |
| Requestyopenmistral-medium-latest@eu | $0.44 | $2.2 | $0.44 | — | 131k |
| Eden AIopenmistral/mistral-medium-latest | $1.5 | $7.5 | $0.15 | — | 262k |
| Mistralopenmistral-medium-latest | $1.5 | $7.5 | $0.15 | — | 262k |
| Vercel AI Gatewaymistral/mistral-medium-3.5 | $1.5 | $7.5 | $0.15 | — | 262k |
| Eden AIopenmistral/mistral-medium-latest@eu | $1.65 | $8.25 | $0.165 | — | 262k |
Mistral Medium pricing FAQ
What is the cheapest Mistral Medium API?
As of Nov 22, 2026, Merge Gateway has the lowest Mistral Medium output price at $2 per 1M tokens, and Merge Gateway has the lowest input price at $0.4 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.
How much does Mistral Medium cost on Mistral?
Mistral charges $1.5 per 1M input tokens and $7.5 per 1M output tokens for Mistral Medium.
How many providers offer Mistral Medium?
5 providers list Mistral Medium on Sovyron; 7 of them sell it at a metered per-token price.
Is Mistral Medium free?
No provider in the Sovyron catalog lists a free tier for Mistral Medium.
What is the context window of Mistral Medium?
Mistral Medium supports a 262k-token context window and up to 262k output tokens.
Token cost calculator
What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.
Estimated
—