Gemini Embedding 2 Preview API

Gemini Embedding 2 Preview is an embedding model by Google, available on the Venice API as gemini-embedding-2-preview. Requests are anonymized, so the provider never sees your identity.

Gemini Embedding 2 Preview API pricing

Model ID	Variant	Privacy	Price
`gemini-embedding-2-preview`	Standard	Anonymized	$0.25 per 1M tokens

Gemini Embedding 2 Preview specifications

Spec	Value
Provider	Google
Released	Apr 17, 2026
Privacy	Anonymized
Dimensions	3,072
Max input	2K tokens

How to use the Gemini Embedding 2 Preview API

Send requests to POST https://api.venice.ai/api/v1/embeddings with "model": "gemini-embedding-2-preview" and your API key.

curl https://api.venice.ai/api/v1/embeddings \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-embedding-2-preview",
    "input": "Private AI for everyone."
  }'

Gemini Embedding 2 Preview API FAQ

How much does the Gemini Embedding 2 Preview API cost?

$0.25 per 1M input tokens. Prices are in USD and can be paid in DIEM at parity.

What is the Gemini Embedding 2 Preview model ID?

Use gemini-embedding-2-preview as the model parameter.

Is the Gemini Embedding 2 Preview API private?

Gemini Embedding 2 Preview is anonymized: Venice forwards requests to the provider without your identity, but the provider may retain prompt data, so use a private model for sensitive work.

How many dimensions do Gemini Embedding 2 Preview embeddings have?

3,072 dimensions, with up to 2K input tokens per item.

Which endpoint does the Gemini Embedding 2 Preview API use?

Call POST /embeddings.

Related models

Text Embedding 3 Large API: $0.16 per 1M tokens
BGE-M3 API: $0.15 per 1M tokens
Text Embedding 3 Small API: $0.03 per 1M tokens
BGE-EN-ICL API: $0.01 per 1M tokens

Explore

By modality