Pixtral 12B
Mistral vision-language model for image understanding and multimodal chat
Context
128,000
Max output
128,000
Input / 1M
$0.15
Output / 1M
$0.15
Providers
1
01Profile
Profile
Released
2024-09-01
Last updated
2024-09-01
Knowledge cutoff
2024-09
Weights
Open
02Capabilities
Capabilities
Input
text · image
Output
text
Reasoning
No
Tool calling
Yes
Structured output
No
Attachments
Yes
Cache read
Not listed
Cache write
Not listed
03Pricing
Pricing across 1 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
4+ recent events since 2024-09-01
2026-09-15Removedvercelofferingremoved→ new
2026-05-18Addedverceloffering→ new
2025-06-10ContextmistralMax output4,096→ 128,000
2025-06-10Addedmistraloffering→ new