Back to Models
mistralai logo
mistralai/voxtral-mini-3b-2507

Voxtral Mini 3B

A 3B-parameter speech-language model built on the Ministral-3B backbone with an audio encoder for state-of-the-art audio understanding. Supports speech transcription, translation, audio Q&A, and voice-to-function calling across 8 languages.

32,768 tokens
Input: ¥5/M
Output: ¥5/M
Specifications

Modalities

Input
audio
text
Output
text
Code Examples
curl https://api.fastmetal.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "mistral-voxtral-mini-3b-2507",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'