---
name: Voxtral-Small-2507
slug: voxtral-small-2507
type: Multimodal
providers:
  - cortecs
description: >-
  Voxtral Small is a multimodal model with audio input, combining advanced
  speech capabilities with strong text performance for transcription,
  translation, and audio understanding.
tags:
  - tool-use
  - multimodal
is_open_source: false
context_window: 32000
max_output: 32000
pricing:
  - image: 0
    input: 0.111
    output: 0.334
    provider: cortecs (Ver 2507)
release_date: '2026-02-02'
capabilities:
  audio: true
  vision: false
  tool_use: true
  citations: false
  reasoning: false
---
Voxtral-Small-2507 is a Multimodal model.
Voxtral Small is a multimodal model with audio input, combining advanced speech capabilities with strong text performance for transcription, translation, and audio understanding.