Skip to content
OmniRail
← All models

Amazon · Embedding model

Titan Multimodal Embeddings G1

amazon/titan-embed-image-v1
  • Embedding
Released Oct 26, 2026

Amazon Titan Multimodal Embeddings G1 embeds text, images, or text and image together into a shared vector space for multimodal search and recommendation. Images are sent as base64 (up to...

Specifications

Input
text, image
Output
vector per input (float array; base64 on request)
Batch
up to 512 inputs per call
Billing
per input token

Use it

POST /api/v1/embeddings · MCP embed · full reference

curl https://omnirail.org/api/v1/embeddings \
  -H "Authorization: Bearer $OMNIRAIL_KEY" -H "Content-Type: application/json" \
  -d '{"model":"amazon/titan-embed-image-v1","input":["brass lever espresso machine","coffee grinder"]}'