DataLearner logo
VO

Voxtral-Mini-3B

Audio modelVoxtral

Voxtral-Mini-3B-2507

Release date: 2025-07-15Updated: 2025-07-16 15:07:49739
Live demoGitHubHugging FaceCompare
Parameters
3B
Context length
32K
Chinese support
Not supported
Reasoning ability

Voxtral-Mini-3B-2507 is an AI model published by MistralAI, released on 2025-07-15, for Audio model, with 3B parameters, and 32K context length, requiring about 9.35 GB storage.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Voxtral-Mini-3B

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
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
9.35 GB
MoE architecture
No
Total params / Active params
3B / N/A
Knowledge cutoff
No data
Voxtral-Mini-3B

Open source & experience

Code license
Weights license
Apache 2.0- Commercial use permitted
GitHub repo
GitHub link unavailable
Live demo
No live demo
Voxtral-Mini-3B

Official resources

Paper
DataLearnerAI blog
No blog post yet
Voxtral-Mini-3B

API details

API speed
4/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-$0.040/ 1M$0.040/ 1M
Audio-$0.0010/ min-
Voxtral-Mini-3B

Benchmark Results

No benchmark data to show.

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

Voxtral-Mini-3B

Publisher

Voxtral-Mini-3B-2507

Model Overview

Voxtral-Mini-3B-2507 is an AI model published by MistralAI, released on 2025-07-15, for Audio model, with 3B parameters, and 32K context length, requiring about 9.35 GB storage.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code