modelbenchmark.io

Voxtral Mini 3B

Mistral · voxtral-mini-3b

Compare

Speech-to-text model for audio transcription, translation, and audio understanding

Specification

most-agreed values

Context
32K
Max output
32K
Released
2025-07
Knowledge cutoff
Retires
Open weights
yes
Input
audio
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.0046
Output
free

Available from 4 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
privatemode-ai$0.0046free32K32K
amazon-bedrock$0.04$0.0433K4K
bedrock_converse$0.04$0.04128K8K
edenai$0.04$0.04128K33K

More from Mistral

most-hosted first