Gemini Embedding 001 via the Tokenator API

Q: What is the API ID of Gemini Embedding 001?

gemini-embedding-001 — put this into the model field of your request.

Q: How do I call this model?

Through /v1/embeddings only: the chat endpoints refuse such a model. Parameters and examples are in the embeddings documentation .

What the model is for

gemini-embedding-001 provides a unified cutting edge experience across domains, including science, legal, finance, and coding. This embedding model has consistently held a top spot on the Massive Text Embedding Benchmark (MTEB) Multilingual leaderboard since the experimental launch in March.

Specification

Full name	Gemini Embedding 001
API ID	`gemini-embedding-001`
Model vendor	OpenAI
Type	Embeddings (vector representations)
Context window	20K tokens
Tokenator usage multiplier	1.35×
Input modalities	text
Supported API formats	`/v1/embeddings`
Upstream providers	1
Current status	available
Data updated	2026-09-15

Upstream providers

Provider	Multiplier
Unified LLM API	1.35×

A request goes to the first available provider by priority; if it fails, Tokenator switches to the next one.

Example request

curl

curl https://api.tokenator.top/v1/embeddings \
  -H "Authorization: Bearer sk-your-tokenator-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-embedding-001",
    "input": "Hello"
  }'

FAQ about Gemini Embedding 001

What is the API ID of Gemini Embedding 001?

gemini-embedding-001 — put this into the model field of your request.

What context window does Gemini Embedding 001 have?

20K tokens.

How many tokens will a request cost?

input × 1.35× — embeddings have no output, so you pay for the input text only. See the documentation for details.

How do I call this model?

Through /v1/embeddings only: the chat endpoints refuse such a model. Parameters and examples are in the embeddings documentation.