Gemini Embedding 001

Gemini Embedding 001: a gemini model from Google, ~2K context, knowledge cutoff 2025-05

Published
scheduleReleasedMay 20, 2025

Gemini Embedding 001 is a gemini model from Google (~2K context, input around $0.15/1M tokens). Suitable for assistants, content generation, knowledge Q&A and business automation

paymentsContext and pricing

Context limit2,048
Max output1
Knowledge cutoff2025-05
Input price$0.15/ 1M tokens
Output price$0/ 1M tokens

descriptionOverview

Overview

Gemini Embedding 001 is provided by Google, model ID gemini-embedding-001

Key specs

  • Context: 2K tokens
  • Max output: 1 tokens
  • Knowledge cutoff: 2025-05
  • Input price: $0.15/1M
  • Output price: $0/1M

Best for

Consider Gemini Embedding 001 when comparing context length, pricing, multimodal support and relay availability

lightbulbUse cases

  • Assistants and customer support
  • Content generation and rewriting
  • Knowledge Q&A and summarization
  • Structured extraction

thumb_upStrengths

  • Priced and relay availability tracked here for easy side-by-side comparison

infoLimitations

  • Knowledge cutoff 2025-05; newer facts need external retrieval
  • Relatively short context (~2K); long inputs need chunking
  • Low single-response output limit
  • Pricing and availability vary by upstream and relay; verify with official docs and tests

linkReferences

This content is compiled from official documentation and public sources. Always refer to official documentation for final details