Voxtral Small 1.0
Mistral's first model with audio input capabilities for instruct use cases; a 24B enhancement of Mistral Small 3 excelling at speech transcription, translation and audio understanding.
text + audio → text · made by Mistral AI
$0.16→$0.47per Mtok in / out
AWS Bedrock
Sold by 4 ways
| Seller | Lane | Rate |
|---|---|---|
| AWS Bedrock cloud | batch | $0.08per Mtok in$0.23per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| AWS Bedrock cloud | flex | $0.08per Mtok in$0.23per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| AWS Bedrock cloud | standard | $0.16per Mtok in$0.47per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| AWS Bedrock cloud | priority | $0.28per Mtok in$0.82per Mtok outraw.githubusercontent.com · read 2026-10-31 |
About
Voxtral Small 1.0 — a text model from Mistral AI, sold by one company from $0.16 in and $0.47 out per million tokens.
It takes text and audio and returns text, with a context window of 32,000 tokens. It was published in October 2025. Its sellers say it can call a tool. The catalogue files it under transcribe and translate. Only AWS Bedrock sells it, at $0.16 in and $0.47 out per million tokens. Beside the standard rate there are batch, flex and faster lanes.
Every current figure
- Maker
- Mistral AI
- Register
- model
- Takes
- text + audio
- Returns
- text
- Context
- 32,000 tokens
- Longest answer
- 26,214 tokens
- Published
- October 2025
- Licence
- not read
- Sellers
- 1
- Maker's own price
- not read
- Price
- $0.16 in and $0.47 out per million tokens — AWS Bedrock
Known as 1 name
mistral.voxtral-small-24b-2507