Skip to content
Sovyron

Devstral 2

devstral262k context262k max outputreleased Dec 9, 2025Open weightsTool calling

As of Nov 22, 2026, the cheapest Devstral 2 API price is $0.4 per 1M input tokens (Eden AI) and $2 per 1M output tokens (Eden AI). Devstral 2 is offered by 6 providers in the devstral family, open weights.

Cheapest input
$0.4
Cheapest output
$2
Official
—
output per 1M tokens
Providers
6
offering this model
Spread
1.2×
max / min output
Free offers
0
free-tier offers

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.

Devstral 2 API prices by provider in USD per 1M tokens, updated Nov 22, 2026
Eden AIopenmistral/devstral-2512Cheapest$0.4Cheapest$2$0.04—262k
Eden AIopenmistral/devstral-medium-latest$0.4$2——262k
Kilo Gatewayopenmistralai/devstral-2512$0.4$2$0.04—262k
LLM Gatewayopenmistral/devstral-2512$0.4$2——262k
Merge Gatewayopenmistral/devstral-2512$0.4$2$0.04—256k
OpenRouteropenmistralai/devstral-2512$0.4$2$0.04—262k
Eden AIeuopenmistral/devstral-2512@eu$0.44$2.2$0.044—262k
Eden AIopenmistral/devstral-medium-latest@eu$0.44$2.2——262k
Cortecsopendevstral-2512$0.478$2.392$0.045—256k

Devstral 2 pricing FAQ

What is the cheapest Devstral 2 API?

As of Nov 22, 2026, Eden AI has the lowest Devstral 2 output price at $2 per 1M tokens, and Eden AI 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 many providers offer Devstral 2?

6 providers list Devstral 2 on Sovyron; 9 of them sell it at a metered per-token price.

Is Devstral 2 free?

No provider in the Sovyron catalog lists a free tier for Devstral 2.

What is the context window of Devstral 2?

Devstral 2 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

—