Multilingual E5 Small

Multilingual E5 Small is part of the E5 family of text embedding models. This small variant contains 12 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

Model ID multilingual-e5-small-maas
Launch stage GA
Supported inputs & outputs
  • Inputs:
    Text
  • Outputs:
    Embeddings
Output dimensions Up to 384
Number of layers 12
Max sequence length 512 tokens
Supported languages See Supported languages.
Usage types
Versions
  • multilingual-e5-small
    • Launch stage: GA
    • Release date: September 19, 2025
Supported regions

Model availability
  • United States
    • us-central1
  • Europe
    • europe-west4

ML processing
  • United States
    • Multi-region
  • Europe
    • Multi-region
Quota

us-central1:

  • TPM: 25,200

europe-west4:

  • TPM: 25,200

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年11月24日 UTC.