# Voxtral Small 24B 2507

> Voxtral Small 24B 2507 is an open-weight language model from Mistral AI, released on 15 Jul 2025. It accepts text, audio and PDFs and generates text, with a 33K-token context window and up to 26K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.10 per million input tokens and $0.30 per million output tokens (Amazon Bedrock), across 2 providers we track.

Source page: https://www.aimodel.directory/models/voxtral-small-24b-2507
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Mistral AI
- **Release date:** 15 Jul 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/mistralai/voxtral-small-24b-2507.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/mistralai/voxtral-small-24b-2507.toml)
- **Weights:** Open weights (source: Hugging Face, https://huggingface.co/mistralai/Voxtral-Small-24B-2507)
- **License:** apache-2.0 (source: Hugging Face, https://huggingface.co/mistralai/Voxtral-Small-24B-2507)
- **Parameters:** 24.3B (source: Hugging Face, https://huggingface.co/mistralai/Voxtral-Small-24B-2507)
- **Context window:** 33K (32,768 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/mistralai/voxtral-small-24b-2507.toml)
- **Max output:** 26K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/mistralai/voxtral-small-24b-2507.toml)
- **Knowledge cutoff:** Jul 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/mistralai/voxtral-small-24b-2507.toml)
- **Input:** Text, audio and PDFs (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/mistralai/voxtral-small-24b-2507.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/mistralai/voxtral-small-24b-2507.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/mistralai/voxtral-small-24b-2507.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/mistralai/voxtral-small-24b-2507.toml)
- **Structured output:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/mistralai/voxtral-small-24b-2507.toml)
- **Hugging Face:** mistralai/Voxtral-Small-24B-2507 (source: Hugging Face, https://huggingface.co/mistralai/Voxtral-Small-24B-2507)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Amazon Bedrock | $0.10 | $0.30 | – | 33K |
| OpenRouter | $0.10 | $0.30 | $0.01 | 33K |

## FAQ

### What is the context window of Voxtral Small 24B 2507?

Voxtral Small 24B 2507 has a context window of 32,768 tokens (33K) and can generate up to 26,214 tokens in a single response, according to models.dev.

### How much does the Voxtral Small 24B 2507 API cost?

Voxtral Small 24B 2507 is listed from $0.10 per million input tokens and $0.30 per million output tokens (Amazon Bedrock). Prices last verified 4 Oct 2026.

### Is Voxtral Small 24B 2507 open source?

Voxtral Small 24B 2507 is an open-weight model: its weights are published on Hugging Face as mistralai/Voxtral-Small-24B-2507 under the apache-2.0 license. Check the license terms before commercial use.

### When was Voxtral Small 24B 2507 released?

Mistral AI released Voxtral Small 24B 2507 on 15 Jul 2025, according to models.dev.

### Which providers offer Voxtral Small 24B 2507?

We track Voxtral Small 24B 2507 on 2 providers: Amazon Bedrock, OpenRouter.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Voxtral Small 24B 2507", https://www.aimodel.directory/models/voxtral-small-24b-2507