EN / 中文
Model prices / Mistral AI / Mistral Medium (latest)

Mistral Medium (latest)Open weights

Mistral AI · released 2026-04-29

The official API price of Mistral Medium (latest) is $1.5 per 1M input tokens and $7.5 per 1M output tokens (as of 2026-11-12). Context window: 262K tokens, up to 262K output tokens per request. 5 providers sell it. The lowest is Merge Gateway: $0.4 input, $2 output.

Price by providerUSD per 1M tokens

ProviderInputOutputCachedNotes
MistralOfficialmistral-medium-latest
$1.5$7.5$0.15OfficialOfficial docs
MMerge GatewayLowestmistral/mistral-medium-latest
$0.4$2—LowestOfficial docs
RRequestymistral-medium-latest
$0.44$2.2$0.44Official docs
RRequestymistral-medium-latest@eu
$0.44$2.2$0.44Official docs
EEden AImistral/mistral-medium-latest
$1.5$7.5$0.15Official docs
TTempr Gatewaymistral/mistral-medium-latest
$1.5$7.5$0.15Official docs
EEden AImistral/mistral-medium-latest@eu
$1.65$8.25$0.165Official docs

Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.

About

Balanced Mistral model for enterprise assistants, multilingual work, and tools

Description from models.dev.

Specs

Type
Text
Context
262K
Max output
262K
Input
Text, Image, PDF
Output
Text
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
Knowledge cutoff
—
Open weights
Yes
Released
2026-04-29

Source

Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.