---
id: "mistralai/voxtral-mini-transcribe-3-0"
also: ["mistralai/voxtral-mini-transcribe-3-0-20261020"]
card_usd_per_m: "64.1667 in, 0.0 out, at mistral/eu"
cheapest_list_usd_per_m: "58.3333 in, 0.0 out, at mistral/zdr on openrouter"
cheapest_effective_usd_per_m: "5.4421 in, 0.0 out, at mistral/zdr on openrouter"
context: 65536
max_output: 52428
input: ["audio"]
output: ["transcription"]
released: "2026-10-20"
api: ["/api/v1/audio/transcriptions"]
endpoints: 3
gateways: "openrouter (3)"
no_training: 3
trains: 0
retains_prompts: 0
---
# Mistral: Voxtral Mini Transcribe 3

Voxtral Mini Transcribe 3 is Mistral's compact speech-to-text model. It takes audio input and returns a transcript with timestamps and speaker diarization. It also supports context biasing for domain terms....