Voxtral Small 24B 2507: API pricing, providers and specs
Voxtral Small 24B 2507 is a text model by Mistral. 3 providers serve it, from $0.30 to $0.369 /1M; the lowest price is at OpenRouter.
How Voxtral Small 24B 2507 compares
Against the 737 text models on the site priced the same way.
- Cheap for its class: at $0.30 /1M, its lowest price undercuts 76% of comparable models (median $1.10).
- Its 33K-token context window is larger than 6% of them (median 262K), about 50 pages of text.
- 3 providers serve it; 52% of comparable models have fewer.
- Its weights are open under the Apache 2.0 license: commercial use allowed.
Voxtral Small 24B 2507 prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
| Provider | Input | Output | Prompt caching | Context |
|---|---|---|---|---|
| OpenRouter | $0.10/1M | From$0.30/1M | $0.01/1M | 33K |
| AI/ML API | $0.106/1M | $0.317/1M | $0.011/1M | — |
Cortecs | $0.123/1M | $0.369/1M | $0.012/1M | — |
- OpenRouterFrom$0.30
- AI/ML API$0.317
- Cortecs$0.369
Specs
- Type
- Text
- Maker
- Mistral
- Inputs
- Audio, Text
- Outputs
- Text
- Context
- 33K≈ 50 pages of text
- Max output
- 26K
- Capabilities
- Prompt caching, JSON, Tool calling
- Released
- Jul 1, 2025
- License
- Apache 2.0commercial use allowed
- Open weights
- Yes, downloadable
- Parameters
- 24B
Alternatives to Voxtral Small 24B 2507
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| $0.30/1M | 33K | — | 3 | |
| $0.20/1M | 1.05M | 1608 | 45 | |
| $0.50/1M | 262K | 1591 | 33 | |
| GPT-6 Luna | $0.40/1M | 1.05M | 1578 | 28 |
| Claude Haiku 5.5 | $0.30/1M | 1M | 1585 | 27 |
| $0.696/1M | 1.05M | 1625 | 21 | |
| $0.376/1M | 262K | 1628 | 5 | |
| $0.17/1M | 1.05M | — | 26 | |
| $0.294/1M | 1.05M | — | 26 |
More from Mistral
Voxtral Small 24B 2507 FAQ
The lowest price for Voxtral Small 24B 2507 is $0.30 /1M, at OpenRouter.
OpenRouter, at $0.30 /1M. 3 providers serve Voxtral Small 24B 2507; the table above lists every one with its price.
Voxtral Small 24B 2507 reads up to 33K tokens per request and writes up to 26K.
Yes. Voxtral Small 24B 2507's weights can be downloaded from its maker's Hugging Face page, under the Apache 2.0 license.
About 24B, as the safetensors metadata of its official Hugging Face repo states.
3 API providers serve Voxtral Small 24B 2507. Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us
