Multimodalembedding API Pricing
As of October 10, 2026, Multimodalembedding costs $0.80 per 1M input tokens on Google Vertex AI. It has a 2,048-token context window.
- Per 1M characters
- $0.20
- Input
- $0.80 / 1M tokens
- Output
- $0 / 1M tokens
- Context window
- 2,048 tokens
- Providers
- 1
- Added to LiteLLM
- April 2025
Multimodalembedding pricing by provider
2 listings across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Per 1M chars | Input | Output | Context |
|---|---|---|---|---|---|
| Google Vertex AI | vertex_ai/multimodalembedding | $0.20 | $0.80 | $0 | 2K |
| Google Vertex AI | vertex_ai/multimodalembedding@001 | $0.20 | $0.80 | $0 | 2K |
Other Multimodalembedding prices on Google Vertex AI
| Input image | $0.0001 per image |
What Multimodalembedding costs in practice
Embedding 10,000 documents of 500 tokens each
| Google Vertex AI | $4.00 |
Multimodalembedding features
Input: text, image, video.
Use Multimodalembedding with LiteLLM
Call Multimodalembedding 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="vertex_ai/multimodalembedding",
input=["hello world"],
)model_list:
- model_name: multimodalembedding
litellm_params:
model: vertex_ai/multimodalembedding
vertex_project: os.environ/VERTEX_PROJECT
vertex_location: os.environ/VERTEX_LOCATIONcurl http://0.0.0.0:4000/v1/embeddings \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "multimodalembedding",
"input": "hello world"
}'Multimodalembedding FAQ
How much does Multimodalembedding cost?
Multimodalembedding costs $0.80 per 1M input tokens on Google Vertex AI.
What is the context window of Multimodalembedding?
Multimodalembedding has a 2,048-token context window.
Which providers offer Multimodalembedding?
Multimodalembedding is available from Google Vertex AI through LiteLLM, using the model name vertex_ai/multimodalembedding.
How do I call Multimodalembedding with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="vertex_ai/multimodalembedding", 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 Multimodalembedding?
Multimodalembedding was added to LiteLLM's model price file in April 2025.
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 Vertex AI.
Provider pages: Google Vertex AI.
