text-embedding-004 — reviews, specs & pricing

Google's text embedding model for semantic tasks.

Summary

text-embedding-004 generates vector representations for text used in search, clustering and classification. It's accessible via the Gemini API. It supports task-specific embedding types.

Sample use case

Used for RAG systems and semantic search within Google Cloud/Gemini ecosystem. Also used for recommendation systems.

Specifications

  • Provider: google
  • License: closed
  • Context: 2k tokens
  • Released: 2024-05-14

Pros

  • Integrated with Gemini ecosystem
  • Task-type customization
  • Free tier available

Cons

  • Closed weights
  • Smaller context than newer embedding models
  • Limited to Google infra

Average rating 0.0 from 0 community reviews on Reviuws.

Frequently asked questions

What is text-embedding-004?

text-embedding-004 generates vector representations for text used in search, clustering and classification. It's accessible via the Gemini API. It supports task-specific embedding types.

How much does text-embedding-004 cost?

Pricing for text-embedding-004 is not publicly listed.

Is text-embedding-004 open source?

text-embedding-004 is released under the closed license.