Mistral: Voxtral Small 24B 2507
Mistral AI · Text
Open audio-language model for speech transcription, audio understanding, and voice-driven tool use
Model ID mistralai/voxtral-small-24b-2507Updated Jul 15, 2025
Pricing & billing
Billing unit: 1M tokens. Vendor reference price; conversion is approximate.
ItemUSD referenceList price (USD)
Input$0.10$0.10
Output$0.30$0.30
Cache read—No public pricing—No public pricing
Cache write—No public pricing—No public pricing
Specifications
- Form
- Text model
- Input modalities
- Text、Audio、File
- Output modalities
- Text
- Context length
- 33K
- Max output
- 26K
- Weights
- Open weights
- Family
- voxtral
- Released
- Jul 15, 2025
Uses and capabilities
Capabilities Text model、Function calling、Structured output、Open weights
Function calling
Structured output
Reasoning
Prompt caching
Open weights
Sources
Use these links to verify specs and pricing — they may point to the vendor's site or to a third-party catalog.