Voxtral Small 24B 2507
unknownMistral AI · voxtral family
Open audio-language model for speech transcription, audio understanding, and voice-driven tool use
Limits
Context32,768
InputUnknown
Output32,768
Modalities
Inputtext, audio
Outputtext
Release info
Release2025-07-15
Last update2025-07-15
Knowledge cutoffUnknown
Provider offerings
Provider-specific prices and limits stay separate from canonical model facts.
| Provider | Provider model ID | Input | Output | Context | Output limit |
|---|---|---|---|---|---|
| No visible provider offerings yet. | |||||
Capabilities
Attachments
Yes
Reasoning
No
Tool calling
Yes
Structured output
Unknown
Temperature
Yes