Devstral Medium pricing and specs

deprecatedopen weights

Legacy model retained for compatibility with older integrations

33,8 ₽input / 1M$0.4
169 ₽output / 1M$2
128Kcontexttokens
128Kmax outputtokens

Devstral Medium price per 1M tokens

Type₽ / 1M$ / 1M
Input tokens33,8 ₽$0.4
Output tokens169 ₽$2

Prices in rubles as of 18.09.2026 at the CBR rate: 1 $ = 84.51 ₽.

Devstral Medium specs and limits

Context window
128K
Max output
128K
Input
text
Output
text
Family
devstral
Released
2025-07-10
Updated
2025-07-10
Knowledge cutoff
2025-05
Also known as
mistral devstral medium, mistral ai devstral medium, mistralai devstral medium, le chat devstral medium, mistral api devstral medium, mistral llm devstral medium

What Devstral Medium can do

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments / files
  • Vision (images)
  • Temperature control
  • Open weights

Devstral Medium benchmarks

BenchmarkScoreMetric
SWE-Bench Verified61.6resolved

Frequently asked questions

How much does the Devstral Medium API cost?

Input costs $0.4 per 1M tokens (33.8 ₽) and output costs $2 per 1M (169 ₽). Mistral bills the prompt and the completion separately, so the price of a call depends on how long both are. Ruble figures use the Bank of Russia rate of 84.51 ₽ per dollar for September 2026.

How much do 1,000 Devstral Medium tokens cost?

List prices are quoted per 1M tokens, so 1,000 tokens cost a thousandth of that: divide $0.4 for input and $2 for output by 1,000. The same rates in rubles are 33.8 ₽ and 169 ₽ per 1M tokens. Both prompt tokens and completion tokens are billed.

How many tokens does Devstral Medium hold?

The Devstral Medium context window is 128K tokens (128,000). Everything shares that budget: the system prompt, the dialogue history, attached files and the answer the model writes. The figure comes from the Mistral model card as of September 2026.

What are the Devstral Medium limits?

The context window is 128K tokens (128,000) and a single response is capped at 128K tokens, so longer output has to be generated in parts. Rate limits are set by Mistral per account and depend on your plan rather than on the model, so they are not listed here.

How is the Devstral Medium price in rubles calculated?

Providers quote their tariffs in US dollars, so the ruble amounts here are a conversion at the official Bank of Russia rate of 84.51 ₽ per dollar. For Devstral Medium that gives 33.8 ₽ per 1M input tokens and 169 ₽ per 1M output tokens. When the rate moves, the ruble price moves with it.

How is Devstral Medium different from other Mistral models?

Devstral Medium belongs to the Devstral family at Mistral. Models in the Mistral line differ in context size, price per 1M tokens and supported capabilities, so compare them by the numbers on their cards rather than by the name. Every Mistral model is listed on the provider page.

What capabilities does Devstral Medium support?

The declared capabilities of Devstral Medium are: tool calling. It accepts text as input, and every attachment consumes tokens from the shared context window of 128K tokens. The list comes from the Mistral model card and is refreshed with the catalog as of September 2026.

Does Devstral Medium have open weights?

Yes, Devstral Medium ships with open weights, so it can be downloaded and served on your own hardware instead of being used only through the Mistral API. What you may do with it is set by the license shown on the card. Catalog prices cover hosted API access.

Other Mistral models