Gemini Embedding 001 pricing.

Prices checked

Gemini Embedding 001 costs $0.15 per million input tokens from Google; the cheapest price is $0.15 at Google, checked .

Google's own price

Google

$0.15/M tokens

per million input tokens

50% above the typical price of the 14 embedding models we track.

Cheapest price

Google

$0.15/M tokens

per million input tokens

Nobody sells it for less than Google with a reason we can point at.

embeddings2k contextreleased 20 May 2025

Every provider selling Gemini Embedding 001

  1. 1

    Google

    Maker's price

    per million input tokens

    $0.15/M tokens
  2. 2

    FastRouter

    Same as maker

    per million input tokens

    $0.15/M tokens
  3. 3

    Google Vertex AI

    Same as maker

    per million input tokens

    $0.15/M tokens
  4. 4

    LLM Gateway

    Same as maker

    per million input tokens

    $0.15/M tokens
  5. 5

    Merge Gateway

    Same as maker

    per million input tokens

    $0.15/M tokens
  6. 6

    Nous Portal

    Same as maker

    20k context here

    $0.15/M tokens
  7. 7

    Tempr Gateway

    Same as maker

    per million input tokens

    $0.15/M tokens
  8. 8

    TrustedRouter

    Costs more

    per million input tokens

    $0.16/M tokens
How we count

Prices are per million input tokens; an embedding model writes no output, so there is no blend. A price below Google's own is listed as cheapest only when the provider says why.

Maker's price
What the lab that trained the model charges on its own API. Every other row is measured against it.
Same as maker
Sold by someone else at the price the maker charges.
Costs more
Sold by someone else for more than the maker charges.

Similar models

Embedding models from other labs, nearest in price first. Each percentage is against Gemini Embedding 001's cheapest price, $0.15 per million input tokens.

Frequently asked

Who sells Gemini Embedding 001 cheapest?
Google, at $0.15 per million input tokens, checked 21 Oct 2026. What the lab that trained the model charges on its own API. Every other row is measured against it.
Why is Gemini Embedding 001 priced on input alone?
An embedding model reads text and returns a vector, so there are no output tokens to bill. The price is per million tokens sent, which is why it is never compared with a chat model's blended price.
Is Gemini Embedding 001 open weights?
No. Google keeps the weights, so every price on this page is Google's own or a resale of it.
How does Gemini Embedding 001 compare with other embedding models?
At $0.15 per million input tokens, Google's own price is 50% above the typical $0.10 across the 14 embedding models we track.

More from Google

See also