Skip to content

Google · Embedding

Text Embedding 004

Google 🇺🇸EmbeddingGoogle Embeddings familyThe maker currently plans to deprecate it within the next 180 days (1 Apr 2027). Plans can change.
From Llmgateway's listing:
Vertex AI text embedding model. Returns 768-dimensional vectors; supports the `dimensions` parameter (1–768) and native batching (up to 250 inputs per request).
llminfo IQ
111.4
Maker's price
$0.10 /1M
Max context
2K
Listings
3

Evidence and sources

llminfo IQ 111.4, ranked among embedding models. From 43 benchmarks. Plenty of data behind it.How llminfo IQ is computedReleased 9 Apr 2024Maker HQ: US (according to Google's own website)
Sources: LiteLLM data, LLMGateway data, llminfo researchPrimary data from LiteLLM from LLMGateway: name, description from llminfo research: release date

Advantages and trade-offs

Compared with 10 embedding models, picked mainly by popularity and IQ

Trade-offs

Deprecation scheduled

The maker plans to deprecate it on 1 Apr 2027, within the next 180 days.

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 7 maker's prices; 4 market median prices.

Input & output

as stated by the model's providers
Text
Embeddings

Capabilities

Supported operations and provider-stated features

Function calling

Listings

 Googletext-embedding-004Source: LiteLLM data2K$0.10—
 LlmgatewayInference by Googletext-embedding-004Sources: LiteLLM data, LLMGateway dataNot published by the provider$0.025—
 Llmgatewaytext-embedding-004Sources: LiteLLM data, LLMGateway data2K$0.025—

Benchmarks

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

Embedding

Around the web

  • Embeddings  |  Gemini API  |  Google AI for Developers
    Python Node.js Go Shell More from google import genai from google.genai import types client = …Python Node.js Go Shell More from google import genai from google.genai import types client = genai . Client () text = "Hello World!" result = client . models . embed_content ( model = "gemini-embedd…

    ai.google.dev

  • Embeddings  |  Machine Learning  |  Google for Developers
    If you're hoping to run your ML model on local devices (as opposed to serving …If you're hoping to run your ML model on local devices (as opposed to serving them), you'll need to be focused on making your model smaller, and will want to decrease the number of weights. In this m…

    developers.google.com

  • Embeddings APIs overview  |  Generative AI on Vertex AI  |  Google Cloud Documentation
    part of Gemini Enterprise Agent Platform. See the most up-to-date information in the Agent Platform …part of Gemini Enterprise Agent Platform. See the most up-to-date information in the Agent Platform documentation . Home Documentation AI and ML Vertex AI Generative AI on Vertex AI Guides Send feedb…

    docs.cloud.google.com

  • Get text embeddings  |  Generative AI on Vertex AI  |  Google Cloud Documentation
    previously specialized models like text-embedding-005 and text-multilingual-embedding-002 and achieves better performance in their respective domains. …previously specialized models like text-embedding-005 and text-multilingual-embedding-002 and achieves better performance in their respective domains. Read our Tech Report for more detail. · up to 30…

    docs.cloud.google.com

  • Multimodal embeddings API  |  Generative AI on Vertex AI  |  Google Cloud Documentation
    Multimodal embeddings API The Multimodal embeddings API generates vectors based on the input you provide, …Multimodal embeddings API The Multimodal embeddings API generates vectors based on the input you provide, which can include a combination of image, text, and video data. The embedding vectors can the…

    docs.cloud.google.com

  • Embeddings - Google AI for Developers
    Storing embeddings As you take embeddings to production, it is common to use vector databases …Storing embeddings As you take embeddings to production, it is common to use vector databases to efficiently store, index, and retrieve high-dimensional embeddings. Google Cloud offers managed data s…

    ai.google.dev

  • Embeddings: Obtaining embeddings  |  Machine Learning  |  Google for Developers
    Embeddings can be created using dimensionality reduction techniques like PCA or by training them as …Embeddings can be created using dimensionality reduction techniques like PCA or by training them as part of a neural network. Training an embedding within a neural network allows customization for sp…

    developers.google.com

  • Choose an embeddings task type  |  Generative AI on Vertex AI  |  Google Cloud Documentation
    Skip to main content Vertex AI is transitioning to become part of Gemini Enterprise Agent …Skip to main content Vertex AI is transitioning to become part of Gemini Enterprise Agent Platform. See the most up-to-date information in the Agent Platform documentation . Home Documentation AI and…

    docs.cloud.google.com

  • Generate embeddings for Images, Videos and Text  |  Generative AI on Vertex AI  |  Google Cloud Documentation
    embeddings = model . get_embeddings ( image = image , video = video , video_segment_config …embeddings = model . get_embeddings ( image = image , video = video , video_segment_config = VideoSegmentConfig ( end_offset_sec = 1 ), contextual_text = "Cars on Highway" , ) print ( f "Image Embedd…

    docs.cloud.google.com

  • Text embeddings overview  |  Google Distributed Cloud air-gapped  |  Google Cloud Documentation
    gapped 1.15.3 (Latest) Send feedback Text embeddings overview Important: This content applies to version 1.14.4 …gapped 1.15.3 (Latest) Send feedback Text embeddings overview Important: This content applies to version 1.14.4 and later. Embeddings are numerical representations of text, images, or videos that cap…

    docs.cloud.google.com

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