VO
Voxtral-Small-24B-2507
Release date: 2025-07-15Updated: 2025-07-16Views: 684
Parameters
24B
Context length
32K
Multilingual
No data
Reasoning ability
2/5
Voxtral-Small-24B-2507 is an AI model published by MistralAI, released on 2025-07-15, for Audio model, with 24B parameters, and 32K context length, requiring about 48.5GB storage.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Voxtral-Small-24B
Model basics
Reasoning traces
No data
Thinking modes
Standard Mode (Default)Thinking Mode
Context length
32K tokens
Max output length
30 tokens
Model type
Audio model
Modality (in / out)
Text, Audio → Text
Release date
2025-07-15
Model file size
48.5GB
MoE architecture
No
Total params / Active params
24B / Not applicable
Knowledge cutoff
No data
Voxtral-Small-24B
Open source & experience
Code license
Weights license
Apache 2.0- Commercial use permitted
GitHub repo
N/A
Hugging Face
Live demo
N/A
Voxtral-Small-24B
Official resources
Paper
DataLearnerAI blog
N/A
Voxtral-Small-24B
API details
API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | - | $0.010/ 1M | $0.300/ 1M |
| Audio | - | $0.0040/ min | — |
“—” means the modality is not billed in that direction, or the vendor has not published a price for it.
Voxtral-Small-24B
Publisher
MistralAI
View publisher details Voxtral-Small-24B-2507
Model Overview
Voxtral-Small-24B-2507 is an AI model published by MistralAI, released on 2025-07-15, for Audio model, with 24B parameters, and 32K context length, requiring about 48.5GB storage.
DataLearner on WeChat
Follow DataLearner on WeChat for AI model updates and research notes.
