Using Vertex AI Multimodal Embeddings on GCP Vertex AI

Implementation guide · Vertex AI Multimodal Embeddings · Google DeepMind

Serverless

GCP Vertex AI exposes Vertex AI Multimodal Embeddings through model ID multimodalembedding. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-07-01. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at GCP Vertex AI and generate an API key.
  2. 2
    Use the GCP Vertex AI SDK or REST API to call multimodalembedding — see the documentation for request format.
  3. 3
    You'll be billed Free/1M input, Free/1M output tokens. See full pricing.
API PortalDocumentationPricing

Code Examples

Install
pip install google-cloud-aiplatform
API key
GOOGLE_CLOUD_PROJECT
Model ID
multimodalembedding

For Google-published models use the model name directly, e.g. "gemini-2.0-flash-001". For third-party publishers (Anthropic, Meta, etc.) use the full publisher path, e.g. "publishers/anthropic/models/claude-3-5-sonnet-v2@20241022".

import os
import vertexai
from vertexai.generative_models import GenerativeModel

# Reads GOOGLE_CLOUD_PROJECT from env; authenticates via Application Default Credentials
vertexai.init(project=os.environ["GOOGLE_CLOUD_PROJECT"], location="us-central1")
model = GenerativeModel("multimodalembedding")
response = model.generate_content("Hello")
print(response.text)

Pricing on GCP Vertex AI

TypePrice (per 1M)
Input tokensFree
Output tokensFree

Capabilities

VisionMultimodal

About Vertex AI Multimodal Embeddings

Vertex AI Multimodal Embeddings is Google Cloud's foundation embedding model for image, text, and video inputs. It supports cross-modal retrieval and semantic search through the Vertex AI Multimodal Embeddings API.

Full model details →

Model Specs

Released2024-08-01

Provider

GCP Vertex AI

Google Cloud Platform (GCP)

Mountain View, California, United States