Voxtral Mini 3B is Mistral AI's speech to text model with a 128K context window and up to 8K output tokens, available from 2 providers, starting at $0.04 / 1M input and $0.04 / 1M output. A compact 3B-parameter audio-language model from Mistral capable of speech transcription and audio understanding in a small footprint.
Specifications
Canonical IDmistral-voxtral-mini
TypeSpeech to Text
StatusDeprecating
CreatorMistral AIMistral AI
Providers
Context Window128K tokens
Max Output8K tokens
Input ModalitiesAudioText
Output ModalitiesText
Release Date · 11 months ago
Deprecation Date

Capabilities

Input2/5
Text✓
Image·
Audio✓
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities1/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandardFlexFastBatch
Input
$ / 1M
Output
$ / 1M
Audio In
$ / sec
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Amazon Bedrock logo
Amazon Bedrock
mistral.voxtral-mini-3b-2507
$0.04$0.04N/A$0.02$0.02$0.07$0.07$0.02$0.02
Mistral AI logo
Mistral AI
mistral/voxtral-mini-2602
N/AN/A$0.000050——————

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Voxtral Mini 3B128K$0.040$0.040Current
Voxtral Mini Realtime————Available
Voxtral Mini Transcribe Realtime————Available
Voxtral Mini TTS————Available

Other Models

ModelTierReleasedContextInput / 1MOutput / 1M
Voxtral Small 24BSmall128K$0.100$0.300
Voxtral Mini 4B Realtime—————
Voxtral TTS—————

Model IDs

mistral-voxtral-mini
mistral.voxtral-mini-3b-2507
mistral/voxtral-mini-2602
mistral/voxtral-mini-latest
mistralai/Voxtral-Mini-3B-2507
voxtral-mini-2507
voxtral-mini-2602
voxtral-mini-latest