Voxtral Small 24B 2507
Open audio-language model for speech transcription, audio understanding, and voice-driven tool use
- Context
- 33K
- Released
- 1y ago
- Parameters
- 24B
- Input / 1M tokens
- $0.10
- Output / 1M tokens
- $0.30
- Cached input / 1M tokens
- $0.01
Sources:models.devOpenRouter
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
No benchmark results have been matched to this model yet.
Specifications
- Developer
- Mistral AI
- Model family
- Voxtral
- Type
- Language model
- Predecessor
- —
- Successor
- —
- Released
- July 15, 2025
- Model ID
mistralai/voxtral-small-24b-2507- Openness
- Open weights
- License
- Apache 2.0
- Parameters
- 24B
- Input modalities
- text, audio, file
- Output modalities
- text
- Modality
- text+file+audio->text
- Tokenizer
- Mistral
- Max output tokens
- 26K
- Hugging Face
- mistralai/Voxtral-Small-24B-2507
- Source freshness
- Metadata synced Oct 8, 2026, 10:17 PM UTC
Additional source evidence
- Source model
- mistral/voxtral-small-24b-2507
- Source family
- voxtral
- Last updated
- 2025-07-15
- Model context
- 33K
- Model output limit
- 33K
- Open weights
- Yes
- File attachments
- Yes
- Reasoning
- No
- Tool calling
- Yes
- Temperature control
- Yes
Downloadable weights
Complete source record (JSON)
{
"id": "mistral/voxtral-small-24b-2507",
"name": "Voxtral Small 24B 2507",
"description": "Open audio-language model for speech transcription, audio understanding, and voice-driven tool use",
"family": "voxtral",
"last_updated": "2025-07-15",
"attachment": true,
"reasoning": false,
"tool_call": true,
"temperature": true,
"modalities": {
"input": [
"text",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 32768,
"output": 32768
},
"release_date": "2025-07-15",
"open_weights": true,
"license": "Apache 2.0",
"weights": [
{
"label": "Hugging Face",
"url": "https://huggingface.co/mistralai/Voxtral-Small-24B-2507"
}
]
}Infrastructure
Provider availability
| Provider | Endpoint | Context | Input /M tokens | Output /M tokens | Cached input /M tokens | Cache write /M tokens | Uptime 1d | Data handling |
|---|---|---|---|---|---|---|---|---|
| mistral/zdr | 33K | $0.10 | $0.30 | $0.01 | — | 99.76% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| mistral | 33K | $0.10 | $0.30 | $0.01 | — | 99.84% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| mistral/eu | 32K | $0.11 | $0.33 | $0.01 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 |
Provider data:OpenRouter
Deployment graph
Can I run this?
Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.