Skip to main content
Watch: I Built an AI App Without Leaving Databricks

Amazon - API - verified

Amazon Titan Multimodal Embeddings G1 embeddings

Amazon Titan Multimodal Embeddings G1 is a current embedding model from Amazon, called by API as amazon.titan-embed-image-v1. It returns 1,024-dimension vectors by default and accepts up to 256 input tokens, for text and image input. No per-1M-token list price is stated for it. No row for this model appeared on the Amazon Bedrock pricing page read today.

CurrentModel id: amazon.titan-embed-image-v1

Default dims
1,024
Max input
256 tok
Price / 1M
Not stated
Inputs
Text, Image

Dimensions

Flexible output size
  • 1,024default
  • 384
  • 256

Default output: 1,024 dimensions.

Listed sizes: 1,024, 384 and 256.

Amazon documents shorter output vectors for this model (Matryoshka-style), so you can store smaller embeddings by asking for fewer dimensions instead of re-embedding with another model.

Pricing

Per 1M input tokens
Not stated
Batch, per 1M
Not stated

No row for this model appeared on the Amazon Bedrock pricing page read today.

Source: aws.amazon.com/bedrock/pricing

Usage

Copied verbatim from the page linked below. Placeholders such as project ids and API keys are the source's own.

Python
import json
import boto3

client = boto3.client('bedrock-runtime', region_name='us-east-1')
response = client.invoke_model(
    modelId='amazon.titan-embed-image-v1',
    body=json.dumps({
            'inputText': 'What are the different services that you offer?',
            'embeddingConfig': {
                'outputEmbeddingLength': 1024
            }
    })
)
print(json.loads(response['body'].read()))

Source: docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-titan-multimodal-embeddings-g1.html

Worth knowing

Embeds English text, images up to 25 MB and 2048 x 2048 pixels, or both into a shared space for image search and recommendation, and supports fine-tuning on image-text pairs.

Released . Multilingual: no.

FAQ

How many dimensions does Amazon Titan Multimodal Embeddings G1 output?

Default output: 1,024 dimensions. Listed sizes: 1,024, 384 and 256. Amazon documents shorter output vectors for this model (Matryoshka-style), so you can store smaller embeddings by asking for fewer dimensions instead of re-embedding with another model.

What is the max input length of Amazon Titan Multimodal Embeddings G1?

256 tokens per input, per Amazon's documentation. Longer text has to be chunked before you embed it.

How much does Amazon Titan Multimodal Embeddings G1 cost?

No per-1M-token list price is stated for it. No row for this model appeared on the Amazon Bedrock pricing page read today. Source: https://aws.amazon.com/bedrock/pricing/.

What can Amazon Titan Multimodal Embeddings G1 embed?

Text and image input, per the provider. It is not documented as multilingual.

Sources

Last verified from the pages below.

More Amazon embedding models

Default dimensions, max input tokens and list price per 1M tokens.

Amazon API modelsPrices per 1M tokens, context windows and specs for every Amazon model in the API registry.

All embedding models

Newsletter

New models, every week

One email per week. New model releases, embedding and retrieval updates and what they mean for what you build.

Keep exploring

Model API pricing and specs

First-party prices per 1M tokens for chat and reasoning models.

Local models

Open-weight LLMs you can download and run, with sizes and licenses.

What is RAG?

Where embeddings fit in a retrieval pipeline, end to end.

Vector databases compared

Where the vectors go once you have picked a model.