ModelPickr

Models / Mistral / Ministral 3 3B

Mistral · ministral

Ministral 3 3B

Compact open vision-language model for edge deployment, instruction following, and tool use

$0.10 in · $0.10 out

per 1M tokens · first-party price. Reference price from Mistral, the lab's own listing.

Context
262,144
Max output
262,144
Cache read
$0.01
Cache write
—
Reasoning
No
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
Yes
License
Apache 2.0
Released
Dec 2, 2025
Updated in source
Dec 2, 2025
Knowledge
—
Providers
3

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
Amazon Bedrock$0.10$0.10———
Mistralreference$0.10$0.10$0.01——
LowRouter$0.10$0.10$0.011——