ModelPickr

Models / Mistral / Voxtral Small 24B 2507

Mistral · voxtral

Voxtral Small 24B 2507

Open audio-language model for speech transcription, audio understanding, and voice-driven tool use

$0.10 in · $0.30 out

per 1M tokens · provider rate closest to the median. No first-party Mistral price was listed. The reference price is Amazon Bedrock's rate, the provider closest to the median.

Provider input prices run from $0.10 to $0.14 per 1M tokens. Output prices run from $0.30 to $0.41.

Context
32,768
Max output
32,768
Cache read
—
Cache write
—
Reasoning
No
Tool calls
Yes
Structured output
Unknown
Vision
No
Open weights
Yes
License
Apache 2.0
Released
Jul 15, 2025
Updated in source
Jul 15, 2025
Knowledge
—
Providers
5

Hugging Face weights

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

Estimated monthly cost

Voxtral Small 24B 2507

$1.05

Cache hit is ignored because this model has no cache-read price.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. Where a provider lists the model more than once, the row is the listing whose id is closest to the canonical model id.
ProviderInputOutputCache readCache writeStatus
Amazon Bedrockreference$0.10$0.30———
Eden AI$0.10$0.30———
Kilo Gateway$0.10$0.30$0.01——
OpenRouter$0.10$0.30$0.01——
AI/ML API$0.14$0.41$0.014——

Jobs this model qualifies for