Google - API - verified
text-multilingual-embedding-002 embeddings
text-multilingual-embedding-002 is a current embedding model from Google, called by API as text-multilingual-embedding-002. It returns 768-dimension vectors by default and accepts up to 2,048 input tokens, for text input. No per-1M-token list price is stated for it. Vertex AI lists Embeddings for Text (Excluding Gemini Embedding) at $0.000025 per 1,000 count online and $0.00002 batch; the count unit is not stated as tokens.
CurrentModel id: text-multilingual-embedding-002
- Default dims
- 768
- Max input
- 2,048 tok
- Price / 1M
- Not stated
- Inputs
- Text
Dimensions
Flexible output size- 768default
Default output: 768 dimensions.
Google documents shorter output vectors for this model (Matryoshka-style), so you can store smaller embeddings by asking for fewer dimensions instead of re-embedding with another model.
Pricing
- Per 1M input tokens
- Not stated
- Batch, per 1M
- Not stated
Vertex AI lists Embeddings for Text (Excluding Gemini Embedding) at $0.000025 per 1,000 count online and $0.00002 batch; the count unit is not stated as tokens.
Usage
Copied verbatim from the page linked below. Placeholders such as project ids and API keys are the source's own.
PROJECT_ID = PROJECT_ID
REGION = us-central1
MODEL_ID = MODEL_ID
import vertexai
from vertexai.language_models import TextEmbeddingModel
vertexai.init(project=PROJECT_ID, location=REGION)
model = TextEmbeddingModel.from_pretrained(MODEL_ID)
embeddings = model.get_embeddings(...)Source: docs.cloud.google.com/gemini-enterprise-agent-platform/reference/models/text-embeddings-api
Worth knowing
Vertex AI only model specialized in multilingual tasks and evaluated on 18 languages with about 100 supported, and Google says gemini-embedding-001 unifies it with better performance.
Release date not stated in the sources. Multilingual: yes.
FAQ
How many dimensions does text-multilingual-embedding-002 output?
Default output: 768 dimensions. Google documents shorter output vectors for this model (Matryoshka-style), so you can store smaller embeddings by asking for fewer dimensions instead of re-embedding with another model.
What is the max input length of text-multilingual-embedding-002?
2,048 tokens per input, per Google's documentation. Longer text has to be chunked before you embed it.
How much does text-multilingual-embedding-002 cost?
No per-1M-token list price is stated for it. Vertex AI lists Embeddings for Text (Excluding Gemini Embedding) at $0.000025 per 1,000 count online and $0.00002 batch; the count unit is not stated as tokens. Source: https://cloud.google.com/vertex-ai/generative-ai/pricing.
What can text-multilingual-embedding-002 embed?
Text input, per the provider. It is documented as multilingual.
Sources
Last verified from the pages below.
- Vertex AI get text embeddings - docs.cloud.google.com
- Vertex AI text embeddings API - docs.cloud.google.com
- Vertex AI pricing - cloud.google.com
More Google embedding models
Default dimensions, max input tokens and list price per 1M tokens.
Newsletter
New models, every week
One email per week. New model releases, embedding and retrieval updates and what they mean for what you build.
Keep exploring
Model API pricing and specs
First-party prices per 1M tokens for chat and reasoning models.
Local models
Open-weight LLMs you can download and run, with sizes and licenses.
What is RAG?
Where embeddings fit in a retrieval pipeline, end to end.
Vector databases compared
Where the vectors go once you have picked a model.