Voxtral Small

Our first model with audio input capabilities for instruct use cases.

mistral/voxtral-small-2507

Our first model with audio input capabilities for instruct use cases.

Specifications & capabilities

Input
audio, text
Output
text
Context window · tokens
32000
Published model ID
voxtral-small-2507
Capabilities
audioInput, batch, multimodal, streaming, structuredOutputs, toolCalling

Published prices

1–5 / 5

voxtral-small-2507 ↗

$0.0040

Inference provider
mistral
Platform
Mistral
Unit
audio_minute
Currency
USD
Billing conditions
Billing label
Per input audio minute

voxtral-small-2507 ↗

$0.10

Inference provider
mistral
Platform
Mistral
Unit
input_tokens_per_million
Currency
USD
Billing conditions
Billing label
input / 1M tokens

voxtral-small-2507 ↗

$0.05

Inference provider
mistral
Platform
Mistral
Unit
input_tokens_per_million
Currency
USD
Billing conditions
inference_type
Batch API
Billing label
input / 1M tokens

voxtral-small-2507 ↗

$0.40

Inference provider
mistral
Platform
Mistral
Unit
output_tokens_per_million
Currency
USD
Billing conditions
Billing label
output / 1M tokens

voxtral-small-2507 ↗

$0.20

Inference provider
mistral
Platform
Mistral
Unit
output_tokens_per_million
Currency
USD
Billing conditions
inference_type
Batch API
Billing label
output / 1M tokens

Provider specifications & access

1–1 / 1

Voxtral Small ↗

source model id
voxtral-small-2507
hosting
mistral-hosted
platforms
  • Mistral
context length
32000
architecture
input_modalities
  • audio
  • text
output_modalities
  • text
capabilities
  • batch
  • streaming
  • structuredOutputs
  • toolCalling

Safety assessments

1–1 / 1

Foundation Model Transparency Index 2025 ↗

18 / 100

source id
stanfordFMTI
canonical model id
mistral/voxtral-small-2507
taxonomy
transparency
hazard category
transparency
hazard name
Organization transparency
policy area
Mistral
assessment type
organization-level disclosure
metric
disclosure_score
result label
18 / 100
sample size
100
updated at
2026-11-09T18:08:05.227Z

Source specification observations

1–1 / 1

mistral ↗

field
context_length
value
32000
normalized value
32000
scope
source-model
source id
mistral
confidence
1

Original sources

1–10 / 10

Mistral AI · blog ↗

Hugging Face · Weights ↗

Mistral AI · Model documentation ↗

arXiv · Model reference ↗

arXiv · paper ↗

Mistral AI · legal ↗

www.apache.org · Weights ↗

Epoch AI · Catalog ↗

GitHub · Catalog ↗

Mistral AI · Catalog ↗

Source links

1–3 / 3

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace