Voxtral Small 24B 2507

by Mistral AIChat

Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding.

Context
32.8K tokens
Max output
26,214 tokens
Parameters
24.3B total
Released
2025-07-15
Weights
Open
Licence
apache-2.0

FeedWeights on Hugging Face

mistral/voxtral-small-24b-2507 · also seen as mistralai/Voxtral-Small-24B-2507, amazon/mistral.voxtral-small-24b-2507, amazon/mistral.voxtral-small-24b-2507@us

Specifications

Full facts as recorded, incl. what is unknown.

Released
2025-07-15
Weights
Opennot gated
License
apache-2.0
Input
Text, Audio
Output
Text
Context window
32,768 max across endpoints
Max output
26,214
Providers
5 + 3 gateways, not counted as providers
Epoch Capabilities Index
not evaluated
Direct price range
$0.100–$0.228 in · $0.300–$0.513 out per 1M tokens · 4 of 5 providers have a comparable price
More details
Last updated
2025-07-15
Knowledge cutoff
2025-07
Weights link
Hugging Face · mistralai/Voxtral-Small-24B-2507
Parameters
24.3B total
Base model
mistralai/Mistral-Small-24B-Base-2501

Capabilities

Across all endpoints: supported if any endpoint supports it.

  • Tool calling
  • Parallel toolsunknown
  • Structured output
  • Reasoning
  • Image input
  • PDF input
  • Audio input
  • Audio outputunknown
  • Video input
  • Prompt caching
  • Web searchunknown
  • Computer useunknown
  • System messages
  • Assistant prefillunknown
  • Temperature
  • Streamingunknown
  • Attachments

Endpoints

One row per provider and variant; gateways are listed separately.

Loading endpoints…

Price history

Atom feed

No change since 19 Oct 2026. The cheapest direct price has been $0.10 in / $0.30 out per 1M tokens at Mistral on every data refresh since then.

Tracked from 19 Oct 2026. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON

Cost calculator

Loading endpoints…

Similarly priced models

Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).

ModelBlended/1MIn/1MOut/1MContextvs Voxtral Small 24B 2507
Gemma 4 31B Split-UntiedGoogle$0.133$0.10$0.30262K+0%
Manta Pro 1.0MegaNova AI$0.133$0.06$0.5065.5K+0%
Devstral Small 2Mistral AI$0.133$0.10$0.30256K+0%
Mistral Small 3.1 24BMistral AI$0.133$0.10$0.30131K+0%
Voxtral SmallMistral AI$0.133$0.10$0.3032.8K+0%
Step 3.5 Flash 2603StepFun$0.133$0.10$0.30256K+0%
MiMo-V2.5Xiaomi$0.133$0.08$0.401.05M+0%
MiMo-V2-FlashXiaomi$0.133$0.10$0.30262K+0%

More from Mistral AI

Newest Mistral AI models in the catalogue. All Mistral AI models

ModelReleasedContextListed price
Mistral Large 42026-10-061.05Mfrom $0.68
Voxtral Small 24B 2507 STT2026-08-13—unpriced
Leanstral 1.52026-06-30262Kunpriced
Mistral Code Latest2026-06-02128Kfrom $0.30
Mistral Code Agent Latest2026-06-02256Kfrom $0.40
Voxtral Mini Transcribe2026-05-1516.4Kunpriced
Mistral Medium 3.52026-04-30262Kfrom $1.50
Mistral Medium 3.52026-04-29262Kfrom $1.50
Heads up: prices are indicative list rates scraped from provider pricing pages; verify with the provider before relying on them. Report incorrect data for this model