Gemini Embedding 2 API Pricing
As of October 10, 2026, Gemini Embedding 2 costs $0.20 per 1M input tokens on Google AI Studio. It has an 8,192-token context window.
- Input
- $0.20 / 1M tokens
- Output
- $0 / 1M tokens
- Context window
- 8,192 tokens
- Providers
- 2
- Added to LiteLLM
- April 2026
Gemini Embedding 2 pricing by provider
2 listings across 2 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Batch in | Context |
|---|---|---|---|---|---|
| Google AI Studio | gemini/gemini-embedding-2 | $0.20 | $0 | $0.10 | 8K |
| Google Vertex AI | vertex_ai/gemini-embedding-2 | $0.20 | $0 | $0.10 | 8K |
Other Gemini Embedding 2 prices on Google AI Studio
| Audio input | $6.50 per 1M tokens |
What Gemini Embedding 2 costs in practice
Embedding 10,000 documents of 500 tokens each
| Google AI Studio | $1.00 |
| Google Vertex AI | $1.00 |
Gemini Embedding 2 features
- Image input
- Audio input
Use Gemini Embedding 2 with LiteLLM
Call Gemini Embedding 2 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.
from litellm import embedding
response = embedding(
model="gemini/gemini-embedding-2",
input=["hello world"],
)model_list:
- model_name: gemini-embedding-2
litellm_params:
model: gemini/gemini-embedding-2
api_key: os.environ/GEMINI_API_KEYcurl http://0.0.0.0:4000/v1/embeddings \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "gemini-embedding-2",
"input": "hello world"
}'Gemini Embedding 2 FAQ
How much does Gemini Embedding 2 cost?
Gemini Embedding 2 costs $0.20 per 1M input tokens on Google AI Studio.
What is the context window of Gemini Embedding 2?
Gemini Embedding 2 has an 8,192-token context window.
Which providers offer Gemini Embedding 2?
Gemini Embedding 2 is available from 2 providers through LiteLLM: Google AI Studio and Google Vertex AI.
How do I call Gemini Embedding 2 with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="gemini/gemini-embedding-2", 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.
What features does Gemini Embedding 2 support?
Gemini Embedding 2 supports image input and audio input.
When did LiteLLM add Gemini Embedding 2?
Gemini Embedding 2 was added to LiteLLM's model price file in April 2026.
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:
- ai.google.dev/gemini-api/docs/pricing
- cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing
LiteLLM docs: Google AI Studio, Google Vertex AI.
Provider pages: Google AI Studio, Google Vertex AI.
