Llama 3.2 90B Vision Instruct
Open Llama multimodal model for image understanding and text reasoning
Context
128,000
Max output
8,192
Input / 1M
$0.35
Output / 1M
$0.40
Providers
2
01Profile
Profile
Released
2024-09-25
Last updated
2024-09-25
Knowledge cutoff
2023-12
Weights
Open
02Capabilities
Capabilities
Input
text · image
Output
text
Reasoning
No
Tool calling
Yes
Structured output
No
Attachments
No
Cache read
—
Cache write
—
03Pricing
Pricing across 1 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
12+ recent events since 2024-09-25
2026-08-03Removedgithub-modelsofferingremoved→ new
2026-07-25Removedazureofferingremoved→ new
2026-06-03Removednano-gptofferingremoved→ new
2026-05-03Addednvidiaoffering→ new
2026-02-18Price cutnano-gptinput / 1M$0.90→ $0.90
2026-02-18Price cutnano-gptoutput / 1M$0.90→ $0.90
2026-02-17Addednano-gptoffering→ new
2025-11-29Addedazureoffering→ new
2025-11-29Removedio-intelligenceofferingremoved→ new
2025-11-29Addedio-netoffering→ new
2025-11-26Addedio-intelligenceoffering→ new
2025-08-04Price upgithub-modelsinput / 1M—→ Not listed