Gemini Embedding 2

Embedding Google Verified Released Apr 22, 2026

Gemini Embedding 2 is Google’s first multimodal embedding model, designed to encode varied media in a common vector space for searching across formats, retrieving documents, and powering recommendations. It also accepts mixed media together within one request. Summary written by AI Index from Google’s own pages.

  • In Input modalities: TextImageAudioVideoPDF

Prices

1 offering · prices as listed
Gemini API (opens in a new tab) Official Global · USD gemini-embedding-2
ConditionsInput/ 1M tokensImage/ image
Standard —$0.00012
Text tokens $0.20—
Image tokens $0.45—
Audio tokens $6.50—
Video tokens $12.00—
Batch —$0.00006
Text tokensBatch $0.10—
Image tokensBatch $0.225—
Audio tokensBatch $3.25—
Video tokensBatch $6.00—

Prices from Gemini API pricing (opens in a new tab) (checked Nov 8, 2026)

Standard: the price a request with no conditions pays (the headline price elsewhere on the site).

Details

Shortest vector
128
Languages
100
Model ID

Not stated on Google’s pages: vector types, inputs per request.

Cited scores

From third-party leaderboards, not measured by us

No cited leaderboard covers embedding models yet. MTEB’s results are open (CC0); we will cite them per benchmark, never as a combined score.

  • Nov 6, 2026Retirement Google deprecates Gemini Embedding 2 Preview Effective November 6, 2026, requests to gemini-embedding-2-preview route to gemini-embedding-2 at its rates. The replacement uses the same API schema, pricing, and embedding space.

No changes recorded yet.

Sources

Google’s official policies: data use, privacy, terms →

Google · United States · ai.google.dev

Snapshots, the same family and other models from this provider