← Back to catalog

Llama 3.2 90B Instruct

Bedrock · Meta · Premium

Approved GA

Meta's 90-billion-parameter multimodal model that processes text and images for visual reasoning and document understanding.

Context window

128K

Max output

N/A

Latency

Medium

Cost / 1K tokens

Variable

Available on

Platform	Model ID	Cost / 1K	Approval
Bedrock Primary	llama-3-2-90b	Variable	Approved

Modalities

Text Image Multimodal

Common use cases

Visual reasoning Document understanding Multimodal chat Image Q&A