prices synced 2026-07-28

Voxtral Small 24B 2507

Mistral · Multimodal · Released Oct 2025

Compare

A 24B multimodal model from Mistral that processes both text and audio inputs, with a 32K token context window.

Strengths
Handles speech transcription, translation, and audio understanding alongside traditional text tasks without significant performance degradation on text.
Best for
Applications that need to process audio content (transcription, translation, or analysis) while maintaining text-based reasoning capabilities.
Limitations
The 32K context window is relatively constrained for handling long documents or extensive conversation history, and audio processing performance may vary depending on audio quality and complexity.

Input / 1M

$0.1

Output / 1M

$0.3

Cached input / 1M

$0.01

Context window

32K

Also billed

Audio input
$100.00 / 1M

Price history

Input (solid)Output (dashed)
Price per 1M tokens over timeOutput went from $0.3 to $0.3; Input went from $0.1 to $0.1 between Jun 2026 and Jun 2026.$0$0.1$0.2$0.3Output on 11 Jun 2026: $0.3Output on 29 Jun 2026: $0.3Out $0.3Input on 11 Jun 2026: $0.1Input on 29 Jun 2026: $0.1In $0.1Jun 2026Jun 2026

Price change

30d
in decreased 0.0% out decreased 0.0%
90d
in decreased 0.0% out decreased 0.0%
1y
in decreased 0.0% out decreased 0.0%
Since launch
in decreased 0.0% out decreased 0.0%

Snapshots

Effective Input Output Cached in Note Source
29 Jun 2026 $0.1 $0.3 $0.01 Imported from OpenRouter openrouter.ai
11 Jun 2026 $0.1 $0.3 $0.01 Imported from OpenRouter openrouter.ai

More from Mistral

Report a problem