LiteLLMModels

Gemini Embedding 001 API Pricing

As of October 10, 2026, Gemini Embedding 001 costs $0.15 per 1M input tokens on Google AI Studio. It has a 2,048-token context window.

By GoogleModel ID gemini/gemini-embedding-001Prices updated Checked
Scheduled for deprecation: Google AI Studio lists May 14, 2028 as the deprecation date for gemini/gemini-embedding-001.
Input
$0.15 / 1M tokens
Output
$0 / 1M tokens
Context window
2,048 tokens
Providers
3
Added to LiteLLM
June 2025

Gemini Embedding 001 pricing by provider

3 listings across 3 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputBatch inContext
Google AI Studiogemini/gemini-embedding-001$0.15$0–2K
Google Vertex AIvertex_ai/gemini-embedding-001$0.15$0$0.122K
Vercel AI Gatewayvercel_ai_gateway/google/gemini-embedding-001$0.15$0––

What Gemini Embedding 001 costs in practice

Embedding 10,000 documents of 500 tokens each

Google AI Studio$0.75
Google Vertex AI$0.75
Vercel AI Gateway$0.75

Use Gemini Embedding 001 with LiteLLM

Call Gemini Embedding 001 through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/embeddings. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import embedding

response = embedding(
    model="gemini/gemini-embedding-001",
    input=["hello world"],
)
Proxy config.yaml
model_list:
  - model_name: gemini-embedding-001
    litellm_params:
      model: gemini/gemini-embedding-001
      api_key: os.environ/GEMINI_API_KEY
Call the proxy
curl http://0.0.0.0:4000/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "gemini-embedding-001",
    "input": "hello world"
  }'

Gemini Embedding 001 FAQ

How much does Gemini Embedding 001 cost?

Gemini Embedding 001 costs $0.15 per 1M input tokens on Google AI Studio.

What is the context window of Gemini Embedding 001?

Gemini Embedding 001 has a 2,048-token context window.

Which providers offer Gemini Embedding 001?

Gemini Embedding 001 is available from 3 providers through LiteLLM: Google AI Studio, Google Vertex AI and Vercel AI Gateway.

How do I call Gemini Embedding 001 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="gemini/gemini-embedding-001", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/embeddings from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

When did LiteLLM add Gemini Embedding 001?

Gemini Embedding 001 was added to LiteLLM's model price file in June 2025.

Is Gemini Embedding 001 being deprecated?

Google AI Studio lists a deprecation date of May 14, 2028 for gemini/gemini-embedding-001.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: Google AI Studio, Google Vertex AI, Vercel AI Gateway.

Provider pages: Google AI Studio, Google Vertex AI, Vercel AI Gateway.