Voxtral Small 24B 2507
Voxtral Small 24B 2507 is a large language model made by Mistral, added to the catalog on 30 Oct 2025. It has a context window of 32,768 tokens and costs $0.10 per 1M input tokens and $0.30 per 1M output tokens. It accepts text, files and audio and produces text. Typical uses: transcribe lengthy audio recordings, translate spoken language accurately and understand complex audio data.
Price checked ยท source: OpenRouter
What Voxtral Small 24B 2507 is
Mistral: Voxtral Small 24B 2507, released by mistralai on October 30, 2025, is designed for both text and audio processing. With a context window of 32,000 tokens, it handles text-to-text tasks efficiently while integrating advanced audio input capabilities. This model is particularly adept at speech transcription, translation, and understanding audio inputs. It supports various parameters like frequency penalty and temperature, offering flexibility for different applications. Whether you need to process text or audio, Voxtral Small provides a robust solution.
Key features
- Supports text and audio inputs
- 32,000 token context window
- Excels in speech transcription
- Advanced audio understanding
- Flexible parameter support
Typical uses
- Transcribe lengthy audio recordings
- Translate spoken language accurately
- Understand complex audio data
- Generate text responses from audio input
Voxtral Small 24B 2507 pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.10 |
| Output, per 1M tokens | $0.30 |
| Cached input read, per 1M tokens | $0.01 |
No price change since it was added on 30 Oct 2025.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0001 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0027 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0036 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.015 |
Voxtral Small 24B 2507 specifications
| Model id | mistralai/voxtral-small-24b-2507 |
|---|---|
| Version | voxtral-small-24b-2507 |
| Context window | 32,768 tokensAbout 24,576 English words |
| Max output | 26,214 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 30 Oct 2025 |
| Input types | text, audio, file |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
Write a short essay
RUN20 Nov 2026Write 150 words on how AI might positively upend work, leisure and creativity
AI has the potential to significantly enhance work, leisure, and creativity. In the workplace, AI can automate repetitive tasks, freeing up human time for more strategic and creative work. It can also provide data-driven insights, improving decision-making and productivity. For leisure, AI can personalize entertainment, from recommending movies to creating tailored playlists. It can also facilitate social connections, with AI-driven platforms helping people find like-minded individuals or groups. In terms of creativity, AI can serve as a tool for artists, musicians, and writers, generating ideas, creating drafts, or even collaborating on projects. It can also democratize creativity, making tools and resources more accessible. However, it's crucial to ensure that AI is used ethically and responsibly, with a focus on augmenting human capabilities rather than replacing them.