Mistral: Voxtral Small 24B 2507
Mistral AIID: mistralai/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 is priced at $100 per million seconds.
Pricing per 1M Tokens
| Input (Prompt) | $0.10 |
| Output (Completion) | $0.30 |
| Cache Read | $0.01 |
| Cache Write | Free |
| Image | N/A |
Specifications
| Context Length | 32K |
| Max Output Tokens | N/A |
| Input Modalities | Text + Audio |
| Output Modalities | Text |
| Tokenizer | Mistral |
| Instruct Type | N/A |
| Top Provider Context | 32K |
| Top Provider Max Output | N/A |
| Moderated | No |
Compare this model
See how Mistral: Voxtral Small 24B 2507 stacks up against other models.
More from Mistral AI
Last updated: March 23, 2026
First tracked: March 23, 2026