Pass IndexThe State of AISign in

Gemini Embedding

State-of-the-art embedding model with excellent performance across English, multilingual and code tasks.

text → embedding · made by Google

$0.15per Mtok in
ElectronHub · 4 sellers

Sold by 7 ways

SellerLaneRate
Google 0 ways$0.075
Google apinot on the seller's list todaybatch$0.075per Mtok inai.google.dev · read 2026-08-24
Google Vertex AI 0 ways$0.12
Google Vertex AI cloudnot on the seller's list todaybatch$0.12per Mtok incloud.google.com · read 2026-08-24
Google 0 ways$0.15
Google apinot on the seller's list todaystandard$0.15per Mtok inai.google.dev · read 2026-08-24
Google Vertex AI cloudstandard$0.15per Mtok incloud.google.com · read 2026-08-24
ElectronHub aggregatorstandard$0.15per Mtok inapi.electronhub.ai · read 2026-09-16
Nous Research aggregatorstandard$0.15per Mtok ininference-api.nousresearch.com · read 2026-09-12
Vercel AI Gateway aggregatorstandard$0.15per Mtok inai-gateway.vercel.sh · read 2026-08-25

Measured 3 standings

PlaceBoardMetricScore
9thof 183MTEB · English (MTEB(eng, v2))meanTask (mean score, 0-1)0.733
9thof 238MTEB · English — Reranking task-type splitscoresByTaskType.Reranking (0-1)0.4859
9thof 86MTEB · Multilingual (MTEB(Multilingual, v2))meanTask (mean score, 0-1)0.6837

About

Gemini Embedding — a vectors model from Google, sold by 4 companies from $0.15 per Mtok in, placed 9th of 238 on MTEB · English — Reranking task-type split.

It takes text and returns vectors, with a context window of 20,000 tokens. It was published in May 2025, trained on material up to May 2025. The catalogue files it under embedding. Four companies sell it. The cheapest is $0.15 per Mtok in at ElectronHub. It has been measured on 3 boards, and stands best at 9th of 238 on MTEB · English — Reranking task-type split.

Every current figure

Maker
Google
Register
model
Takes
text
Returns
embedding
Context
20,000 tokens
Longest answer
4,096 tokens
Published
May 2025
Knowledge to
May 2025
Licence
not read
Sellers
4
Price
$0.15 per Mtok in — ElectronHub
Boards
3
Best place
9th of 238 — MTEB · English — Reranking task-type split

Known as 2 names

google/gemini-embedding-001gemini-embedding-001