Gemini Embedding 2

google/gemini-embedding-2

An embedding model with a 131K-token context window, at $0.21 per million tokens.

Details

Maker: google
Kind: Embeddings
Context window: 131,072 tokens
Input: $0.21 per million tokens
Capabilities: None listed
Takes: Text
Returns: Text
Zero data retention: Not on every provider
No training on requests: Yes, on every provider
Released: 2026-03-10

Description

Google’s first fully multimodal Embedding model that is capable of mapping text, image, video, audio, and PDFs and their interleaved combinations thereof into a single, unified vector space. Built on the Gemini architecture, it supports 100+ languages.

Call it

curl

curl https://phantom.codes/v1/embeddings \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-embedding-2",
    "input": "The quick brown fox"
  }'

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model