Voxtral Mini

Mistral

A mini audio understanding model released in July 2025

Try Now

Capabilities

PDF Input

Technical Specifications

Context Window

32,768 tokens

Max Output

32,768 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input

$0.04

Non-Reasoning Output

$0.04

Legacy

Made legacy on

Reason

Audio/speech model; not applicable for text chat

Recommended Replacement

Mistral Small 4 119B