Voxtral Small (latest) pricing and specs

Input costs $0.1 per 1M tokens (8.45 ₽) and output costs $0.3 per 1M (25.35 ₽). 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.

List prices are quoted per 1M tokens, so 1,000 tokens cost a thousandth of that: divide $0.1 for input and $0.3 for output by 1,000. The same rates in rubles are 8.45 ₽ and 25.35 ₽ per 1M tokens. Both prompt tokens and completion tokens are billed.

The Voxtral Small (latest) context window is 32K tokens (32,000). 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.

The context window is 32K tokens (32,000) and a single response is capped at 32K 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.

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 Voxtral Small (latest) that gives 8.45 ₽ per 1M input tokens and 25.35 ₽ per 1M output tokens. When the rate moves, the ruble price moves with it.

The declared capabilities of Voxtral Small (latest) are: tool calling. It accepts text, audio as input, and every attachment consumes tokens from the shared context window of 32K tokens. The list comes from the Mistral model card and is refreshed with the catalog as of September 2026.

Yes, Voxtral Small (latest) 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.