Models / Mistral / Pixtral 12B

Mistral · pixtral

Pixtral 12B

Mistral vision-language model for image understanding and multimodal chat

$0.15 in · $0.15 out

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

Provider input prices run from $0.15 to $0.29 per 1M tokens. Output prices run from $0.15 to $0.29.

Context
128,000
Max output
128,000
Cache read
—
Cache write
—
Reasoning
No
Tool calls
Yes
Structured output
Unknown
Vision
Yes
Open weights
Yes
License
—
Released
Sep 1, 2024
Updated in source
Sep 1, 2024
Knowledge
2024-09
Providers
4

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

Pixtral 12B

$1.13

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. One row per provider.
ProviderInputOutputCache readCache writeStatus
Mistralreference$0.15$0.15——deprecated
Pioneer$0.15$0.15$0.15$0.15—
Scaleway$0.20$0.20———
GreenPT$0.29$0.29———