Skip to content

Amazon · Embedding

Titan Text Embeddings V2

Amazon 🇺🇸EmbeddingTitan familyOne of its sources says the weights aren't publicly available.
From Eurouter's listing:
Amazon Titan Embeddings v2 offers configurable embedding dimensions (256-1024) and improved multilingual support.
Maker's price
$0.02 /1M
Max context
8K
Listings
6
Providers
5

Evidence and sources

All rankings: #442 on OpenRouter this week #462 on OpenRouter today #467 on OpenRouter this monthSources: AWS Bedrock Runtime data, Models.dev data, EURouter dataPrimary data from AWS Bedrock Runtime from Models.dev: weights availability from EURouter: description
Tags from its sources:proprietaryembeddingmultilingualconfigurable-dimensions

Advantages and trade-offs

Compared with 10 representative embedding models

Trade-offs

No open weights

The weights aren't public, so you can't run it yourself.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 3 maker's prices; 5 market median prices.

Input & output

as stated by the model's providers
Text
Embeddings

Listings

 Amazon Web Servicesamazon.titan-embed-text-v2:0Sources: AWS Bedrock Runtime data, LiteLLM data8K$0.02—
 Euroutertitan-embed-text-v2Source: EURouter data8K$0.20—
 Nous Portalamazon/titan-embed-text-v2Source: Nous Portal Inference Gateway data8K$0.02—
 Vercel AI Gatewayvercel_ai_gateway/amazon/titan-embed-text-v2Source: LiteLLM dataNot published by the provider$0.02—

2 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Embedding

Around the web

  • Amazon Titan Text Embeddings V2 now available in Amazon Bedrock - AWS
    dimensions, the model maintains 97% accuracy. Additionally, Titan Text Embeddings V2 includes multilingual support for …dimensions, the model maintains 97% accuracy. Additionally, Titan Text Embeddings V2 includes multilingual support for 100+ languages in pre-training as well as unit vector normalization for improvin…

    aws.amazon.com

  • Titan Text Embeddings V2 - Amazon Bedrock
    Titan Text Embeddings V2 - Amazon Bedrock Titan Text Embeddings V2 is Amazon's second-generation text …Titan Text Embeddings V2 - Amazon Bedrock Titan Text Embeddings V2 is Amazon's second-generation text embeddings model with configurable output dimensions and improved accuracy for retrieval tasks.

    docs.aws.amazon.com

  • Get started with Amazon Titan Text Embeddings V2: A new state-of-the ...
    Get started with Amazon Titan Text Embeddings V2: A new state-of-the ... May 2, 2024 …Get started with Amazon Titan Text Embeddings V2: A new state-of-the ... May 2, 2024 · Amazon Titan Text Embeddings V2 is the second-generation embedding model for Amazon Bedrock, optimized for some …

    aws.amazon.com

  • Amazon Titan Text Embeddings V2 now available in Amazon Bedrock, optimized for improving RAG | AWS News Blog
    Amazon Titan Text Embeddings V2 will soon be the default LLM proposed by Knowledge Bases …Amazon Titan Text Embeddings V2 will soon be the default LLM proposed by Knowledge Bases for Amazon Bedrock. Your existing knowledge bases created with the original Amazon Titan Text Embeddings model…

    aws.amazon.com

  • Amazon Titan Text Embeddings models - Amazon Bedrock
    Amazon Titan Text Embeddings models - Amazon Bedrock Inference types – On-Demand, Provisioned Throughput. Supported …Amazon Titan Text Embeddings models - Amazon Bedrock Inference types – On-Demand, Provisioned Throughput. Supported use cases – RAG, document search, reranking, classification, etc. Note. Titan Text …

    docs.aws.amazon.com

  • Amazon Titan Text Embeddings V2 now available for use with Bedrock Knowledge Bases - AWS
    Embeddings V2, a new embeddings model in the Amazon Titan family of models, is now …Embeddings V2, a new embeddings model in the Amazon Titan family of models, is now available for use with Knowledge Bases for Amazon Bedrock . Using Titan Text Embeddings V2, customers can embed thei…

    aws.amazon.com

  • Introducing Binary Embeddings for Titan Text ...
    Section: > Introducing Binary Embeddings for Titan Text ... Nov 19, 2024 — Amazon Titan …Section: > Introducing Binary Embeddings for Titan Text ... Nov 19, 2024 — Amazon Titan Text Embeddings V2 now supports Binary Embeddings. With Binary Embeddings, customers can reduce the storage cos…

    aws.amazon.com

  • Amazon Titan Text Embeddings - AWS AI Service Cards
    input texts of up to 8192 tokens (roughly 6000-6500 words). Each input is converted into …input texts of up to 8192 tokens (roughly 6000-6500 words). Each input is converted into a vector of 1536 floating point numbers, that is, a 1536-dimensional embedding. Amazon Titan Text Embeddings V…

    docs.aws.amazon.com

  • README.md · amazon/Titan-text-embeddings-v2 at main
    amazon / Titan-text-embeddings-v2 like 17 Follow Amazon 4.26k Feature Extraction Transformers 110 languages sentence-similarity mteb …amazon / Titan-text-embeddings-v2 like 17 Follow Amazon 4.26k Feature Extraction Transformers 110 languages sentence-similarity mteb Eval Results (legacy) License: amazon-service-terms Model card Fil…

    huggingface.co

  • README.md · amazon/Titan-text-embeddings-v2 at 45829398b4a528046ab7379d69de5f303f0235e0
    amazon / Titan-text-embeddings-v2 like 17 Follow Amazon 4.25k Feature Extraction Transformers 110 languages sentence-similarity mteb …amazon / Titan-text-embeddings-v2 like 17 Follow Amazon 4.25k Feature Extraction Transformers 110 languages sentence-similarity mteb Eval Results (legacy) License: amazon-service-terms Model card Fil…

    huggingface.co

Also known as: amazon.titan-embed-text-v2:0, amazon.titan-embed-text-v2:0:8k, amazon/titan-embed-text-v2, bedrock/us-gov-east-1/amazon.titan-embed-text-v2:0, bedrock/us-gov-west-1/amazon.titan-embed-text-v2:0, vercel_ai_gateway/amazon/titan-embed-text-v2

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works