- Input
- $0.80
- Output
- $0.00
amazonListed Oct 26, 2026
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...
Model brief
AI summary with sourcesLimited evidence · Checked
The provider route states text input is limited to 128 tokens and vectors default to 1,024 dimensions, with 384 and 256 selectable via the dimensions parameter. [1]
Documented caveats
- The provider route states images are sent as base64 up to 25 MB. [1]
We have not found enough specific first-hand reports for this model yet.
Sources and dates1
Measured performance
All leaderboards ↗Benchmark results
No published results in this index yet
Scores appear here when an evaluation matches this exact model.
Access & cost
1 quotePrices across providers
Model specifications
- Developer
- amazon
- Modality
- Embedding
- Context
- 128 tokens
- Maximum output
- 115 tokens
- Weights
- Not reported
- Provider listed
- Oct 26, 2026
- First discovered
- Oct 27, 2026
More from amazon
View all ↗amazonListed Today
Amazon: Titan Embeddings G1 - Text
Amazon Titan Embeddings G1 - Text is the first-generation Titan text embedding model. It accepts up to 8,192 tokens per input and returns fixed 1,536-dimension vectors; the dimensions parameter is...
8.2K contextNo reported score
No reported score
amazonListed Today
Amazon: Titan Text Embeddings V2
Amazon Titan Text Embeddings V2 is a text embedding model for retrieval, search, and clustering. It accepts up to 8,192 tokens per input and returns normalized vectors of 1,024 dimensions...
8.2K contextNo reported score
No reported score