Multilingual E5 Large

Multilingual E5 Large is part of the E5 family of text embedding models. This large variant contains 24 layers. This model is well-suited for tasks such as:

Semantic Search: Finding documents or text passages that are semantically relevant to a query.
Text Clustering: Grouping similar pieces of text based on their semantic meaning.
Informative Response Generation: Following instructions to provide summaries, explanations, or answers to factual queries.

View model card in Model Garden

Supported regions
Model ID	`multilingual-e5-large-instruct-maas`
Launch stage	GA
Supported inputs & outputs	Inputs: Text Outputs: Embeddings
Output dimensions	Up to 1,024
Number of layers	24
Max sequence length	512 tokens
Supported languages	See Supported languages.
Usage types	Supported Fixed quota Pay as you go Not supported Provisioned throughput
Versions	`multilingual-e5-large` Launch stage: GA Release date: September 19, 2025
	Model availability	United States `us-central1` Europe `europe-west4`
	ML processing	United States `Multi-region` Europe `Multi-region`
Quota	us-central1: TPM: 3,000 europe-west4: TPM: 3,000

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025-12-10 UTC.