Pass IndexThe State of AISign in

Voxtral Small 24B 2507

Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance.

text + audio + file → text · made by Mistral AI

$0.1$0.3per Mtok in / out
AWS Bedrock · 4 sellers

Sold by 5 ways

SellerLaneRate
AWS Bedrock cloudstandard$0.1per Mtok in$0.3per Mtok outmodels.dev · read 2026-09-16
Nous Research aggregatorstandard$0.1per Mtok in$0.3per Mtok out$0.01per Mtok cachedinference-api.nousresearch.com · read 2026-09-12
OpenRouter 2 ways$0.1per Mtok in$0.3per Mtok out$0.01per Mtok cached
OpenRouter aggregatorstandard$0.1per Mtok in$0.3per Mtok out$0.01per Mtok cachedopenrouter.ai · read 2026-08-24
OpenRouter aggregatormistral/eu$0.11per Mtok in$0.33per Mtok out$0.011per Mtok cachedopenrouter.ai · read 2026-08-29
DeepInfra aggregatorstandard$0.003per minuteapi.deepinfra.com · read 2026-08-25

About

Voxtral Small 24B 2507 — a text model from Mistral AI, sold by 4 companies from $0.1 in and $0.3 out per million tokens.

It takes text, audio and files and returns text, with a context window of 32,768 tokens. It was published in July 2025, trained on material up to July 2025. Its sellers say it can call a tool. The catalogue files it under transcribe and translate. Four companies sell it. The cheapest is $0.1 in and $0.3 out per million tokens at AWS Bedrock. Beside the standard rate there is a regional lane.

Every current figure

Maker
Mistral AI
Register
model
Takes
text + audio + file
Returns
text
Context
32,768 tokens
Longest answer
32,000 tokens
Published
July 2025
Knowledge to
July 2025
Parameters
24 billion
Licence
not read
Sellers
4
Maker's own price
not read
Price
$0.1 in and $0.3 out per million tokens — AWS Bedrock

Known as 1 name

mistralai/Voxtral-Small-24B-2507