Voxtral Mini 1.0
A mini (3B) version of Mistral's first audio-input model, an enhancement of Ministral 3B that excels at speech transcription, translation and audio understanding while retaining text performance.
text + audio → text · made by Mistral AI
$0.06→$0.06per Mtok in / out
AWS Bedrock
Sold by 4 ways
| Seller | Lane | Rate |
|---|---|---|
| AWS Bedrock cloud | batch | $0.03per Mtok in$0.03per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| AWS Bedrock cloud | flex | $0.03per Mtok in$0.03per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| AWS Bedrock cloud | standard | $0.06per Mtok in$0.06per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| AWS Bedrock cloud | priority | $0.11per Mtok in$0.11per Mtok outraw.githubusercontent.com · read 2026-10-31 |
About
Voxtral Mini 1.0 — a text model from Mistral AI, sold by one company from $0.06 in and $0.06 out per million tokens.
It takes text and audio and returns text, with a context window of 32,000 tokens. The catalogue files it under transcribe and translate. Only AWS Bedrock sells it, at $0.06 in and $0.06 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
- Sellers
- 1
- Maker's own price
- not read
- Price
- $0.06 in and $0.06 out per million tokens — AWS Bedrock
Known as 1 name
mistral.voxtral-mini-3b-2507