Amazon Nova Multimodal Embeddings

Bedrock · Amazon · Standard

Approved GA

Amazon's embedding model that converts text, images, and video into vector representations for search and retrieval.

Context window

N/A

Max output

N/A

Latency

Low

Cost / 1K tokens

Variable

Available on

Platform	Model ID	Cost / 1K	Approval
Bedrock Primary	amazon-nova-multimodal-embeddings	Variable	Approved

Embedding Multimodal

Semantic search RAG retrieval Multimodal search Recommendation