Model dossier

Amazon: Titan Multimodal Embeddings G1

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...

ProviderAmazon Start comparison

Context128

Max output115

Pricing viewTVP price

Identity

Amazon: Titan Multimodal Embeddings G1

Model ID: amazon/titan-embed-image-v1
Canonical slug: amazon/titan-embed-image-v1-20261026
Knowledge cutoff: n/a
Created: 10/26/2026

Capabilities

textimageembeddings

Modalities

text+image->embeddingsembeddingstextimage

Capacity

Context128

Max output115

TokenizerOther