ModelPickr

Models / Mistral / Magistral Small

Mistral · magistral

Magistral Small

Open Mistral reasoning model for transparent step-by-step problem solving

$0.50 in · $1.50 out

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

Context
131,072
Max output
8,192
Cache read
$0.50
Cache write
$0.50
Reasoning
Yes
Tool calls
Yes
Structured output
Unknown
Vision
No
Open weights
Yes
License
Apache 2.0
Released
Jun 10, 2025
Updated in source
Jun 10, 2025
Knowledge
—
Providers
1

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.

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. One row per provider.
ProviderInputOutputCache readCache writeStatus
Pioneerreference$0.50$1.50$0.50$0.50—