Google

Gemini Embedding 001 API Pricing

Text-only embedding model, superseded by Gemini Embedding 2. Batch rate $0.075/M.

Verified against Google’s pricing page on 2026-07-02.

View source ↗

Facts

Legacy

Specs

  • FamilyGemini Embedding
  • API IDgemini-embedding-001
  • ModalityEmbedding
  • Context window
  • Max output
  • Release dateNot published

Pricing (per 1M tokens)

  • Input$0.15 / 1M tokens
  • Output
  • Cached input
  • Cache write
  • Batch discount50%

Capabilities

embedding

Notes

Text-only embedding model, superseded by Gemini Embedding 2. Batch rate $0.075/M.

Worked cost examples

Estimated monthly cost on three common usage shapes

WorkloadEst. monthly cost

Chatbot

800 input / 200 output tokens per request, 100,000 requests/month

$12.00

RAG pipeline

6,000 input / 700 output tokens per request, 30,000 requests/month

$27.00

Batch summarization

20,000 input / 1,500 output tokens per request, 5,000 requests/month

$15.00

Price history

Changes we have documented since we began tracking

No price changes recorded since we began tracking.

Gemini Embedding 001 pricing FAQ

How much does Gemini Embedding 001 cost per 1M tokens?
Gemini Embedding 001 costs $0.15 per 1M input tokens.
How much does Gemini Embedding 001 cost per request?
We can't compute an exact per-request cost for Gemini Embedding 001 — some price fields aren't published.
Is Gemini Embedding 001 cheaper than Gemini Embedding 2?
Gemini Embedding 001 is cheaper than Gemini Embedding 2 on input tokens, by about 25%.
Does Gemini Embedding 001 have cache pricing?
No cache discount is documented for Gemini Embedding 001 on the provider's pricing page.