Voxtral Small 24B 2507
Voxtral Small 24B 2507 is a compact variant, chosen for high throughput and low cost rather than absolute capability. Available via Mistral. 32,768-token context. Budget pricing.
Voxtral Small 24B 2507 is a multimodal AI model from Mistral. It costs $0.100 per million input tokens and $0.300 per million output tokens (blended $0.160/M), with a 32,768-token context window.
- Sub-second latency
- Affordable at scale
- Good for routing & classification
- Multimodal: handles images alongside text
- Routing & classification
- Bulk summarisation
- Realtime chat UX
Benchmarks
More from Mistral
See all 15 →Frequently asked questions
How much does Voxtral Small 24B 2507 cost?
Voxtral Small 24B 2507 costs $0.100 per million input tokens and $0.300 per million output tokens, for a blended reference rate of $0.160 per million tokens.
What is Voxtral Small 24B 2507's context window?
Voxtral Small 24B 2507 supports up to 32,768 tokens of context in a single request.
What is Voxtral Small 24B 2507 best for?
Voxtral Small 24B 2507 is well suited to Sub-second latency, Affordable at scale and Good for routing & classification.
Who makes Voxtral Small 24B 2507?
Voxtral Small 24B 2507 is developed and served by Mistral.