Open ASR · AMI-Cleaned WER ↗English short-form; normalization unversioned
13.19% WERmistralai/Voxtral-Small-24B-2507
mistralaiListed Jul 19, 2025
Mistral: Voxtral Small 24B 2507
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. Input audio...
Context window32.8K
Max output26.2K
Parameters24B
Provider endpoints6
Benchmark results9
Measured performance
All leaderboards ↗Benchmark results
Word error rate · lower is better
Open ASR · Earnings22-Cleaned-AA-chunked WER ↗English short-form; normalization unversioned
7.07% WERmistralai/Voxtral-Small-24B-2507
Open ASR · Gigaspeech-Cleaned WER ↗English short-form; normalization unversioned
8.33% WERmistralai/Voxtral-Small-24B-2507
Open ASR · LS Clean WER ↗English short-form; normalization unversioned
1.23% WERmistralai/Voxtral-Small-24B-2507
Open ASR · LS Other WER ↗English short-form; normalization unversioned
2.8% WERmistralai/Voxtral-Small-24B-2507
Open ASR · SPGISpeech WER ↗English short-form; normalization unversioned
1.84% WERmistralai/Voxtral-Small-24B-2507
Open ASR · URGENT2024 WER ↗English short-form; normalization unversioned
12.35% WERmistralai/Voxtral-Small-24B-2507
Open ASR · Voice Arena Monsoon WER ↗English short-form; normalization unversioned
3.49% WERmistralai/Voxtral-Small-24B-2507
Open ASR · Voxpopuli-AA-Cleaned WER ↗English short-form; normalization unversioned
2% WERmistralai/Voxtral-Small-24B-2507
Access & cost
6 quotesPrices across providers
Your token mix
USD · listed token ratesOpenRouter
Catalog quote- Input
- $50.00
- Output
- $0.00
OpenRouter
Catalog quote- Input
- $0.10
- Output
- $0.30
- Cached input
- $0.01
DeepInfra
Input audio second
- Rate
- $0.00005
- Input
- $0.10
- Output
- $0.30
- Cached input
- $0.01
Audio input $100/M audio tokens · Cached audio input price unknown · Audio tokens use separate rates from text input
- Input
- $0.10
- Output
- $0.30
- Cached input
- $0.01
Audio input $100/M audio tokens · Cached audio input price unknown · Audio tokens use separate rates from text input
- Input
- $0.11
- Output
- $0.33
- Cached input
- $0.011
Audio input $110/M audio tokens · Cached audio input price unknown · Audio tokens use separate rates from text input
Model specifications
- Developer
- mistralai
- Modality
- Language
- Context
- 32,768 tokens
- Maximum output
- 26,214 tokens
- Weights
- Open weights
- Provider listed
- Jul 19, 2025
- First discovered
- Oct 16, 2026
Exact identities
- openrouter
mistralai/voxtral-small-24b-2507-stt - openrouter
mistralai/voxtral-small-24b-2507 - deepinfra
mistralai/Voxtral-Small-24B-2507 - open-asr
mistralai%2FVoxtral-Small-24B-2507
Sources
Updated Oct 17, 2026
More from mistralai
View all ↗mistralaiListed 11 days ago
Mistral: Mistral Large 4
Open-weight public preview with document Q&A, function calls and JSON schemas; works with Mistral agent APIs.
1M contextImage inputTool callingNo reported score
No reported score
mistralaiListed May 15
Mistral: Voxtral Mini Transcribe
Voxtral Mini Transcribe is Mistral's speech-to-text model, derived from the Voxtral Mini family. It accepts audio input and returns transcribed text via the standard transcription API. Suited for…
16.4K contextAudio inputNo reported score
No reported score
mistralaiListed Apr 30
Mistral: Mistral Medium 3.5
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...
262.1K contextImage inputTool callingNo reported score
No reported score
mistralaiListed Apr 30
Mistral: Mistral Medium 3.5 (batch)
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...
262.1K contextImage inputTool callingNo reported score
No reported score