---
title: "multilingual-e5-large-instruct API hosted in the EU"
description: "Run multilingual-e5-large-instruct on inference.eu: compact embeddings in 100 languages for search, RAG and classification, processed in the EU."
canonical: "https://inference.eu/models/multilingual-e5-large-instruct/"
language: "en"
---

Embeddings · Microsoft (intfloat)

# Run multilingual-e5-large-instruct embeddings in the EU through an OpenAI-compatible API

multilingual-e5-large-instruct is a compact embedding model from Microsoft researchers that turns short texts in about 100 languages into 1024-dimension vectors. It takes a task instruction on the query side, which helps it adapt to search, classification and clustering. On inference.eu you call it through the OpenAI embeddings format, processed in EU data centres and never used for training.

[Contact sales](https://inference.eu/contact/)[Example request](#example)

1.  01560M
2.  02EU data centres
3.  03MIT

## What multilingual-e5-large-instruct is

multilingual-e5-large-instruct is part of the E5 family of text embedding models published by Microsoft researchers under the intfloat account. It was released in February 2024 under the MIT licence. It is initialised from XLM-RoBERTa large, with 24 layers, about 560 million parameters and an embedding size of 1024.

The model was trained on a large multilingual mix of text pairs and then fine-tuned with task instructions. It supports the 100 languages of XLM-RoBERTa, although quality is lower for languages with little training data. Inputs are limited to 512 tokens, so it is designed for sentences, paragraphs and short passages rather than whole documents.

## What it does well, and where it falls short

The model is small, fast and well understood, which makes it a good fit for large indexes of short texts: product descriptions, FAQ entries, support tickets and paragraphs of policies. Because queries carry an instruction, the same model can be steered towards retrieval, semantic similarity, classification or clustering without fine-tuning.

Its main limit is the 512-token input, which forces you to chunk long documents into short passages. Newer models such as bge-m3 accept 8192 tokens and Qwen3 Embedding 8B accepts 32K, and the larger Qwen model usually retrieves better on hard queries. Forgetting the query instruction also reduces quality noticeably, so it must be part of your integration.

## Calling multilingual-e5-large-instruct through the API

inference.eu uses the OpenAI request format, so OpenAI SDKs, LangChain, LlamaIndex and vector database integrations that call `/v1/embeddings` work unchanged. Set the base URL to the inference.eu API, use your inference.eu key and set the model to `multilingual-e5-large-instruct`.

Each query needs a one-sentence instruction in the form `Instruct: {task}` followed by a new line and `Query: {text}`, for example `Instruct: Given a web search query, retrieve relevant passages that answer the query`. Documents are embedded as plain text, without any instruction. Keep passages under 512 tokens, since longer input is truncated.

## Data residency for multilingual-e5-large-instruct

Indexing your content means sending every passage to the embedding model. On inference.eu, multilingual-e5-large-instruct runs on infrastructure in the European Union, so your documents and queries are processed in EU data centres and are never used to train any model.

Every customer receives a data processing agreement under Article 28 of the GDPR and our subprocessor list, which makes it straightforward to document your search or RAG pipeline in your records of processing. Billing is in euros, on the same invoice as the chat models that use the retrieved passages. The MIT licence allows commercial use with few conditions.

## multilingual-e5-large-instruct

Maker

Microsoft (intfloat)

Made in

United States

Type

Embeddings

Parameters

560M

Context window

512 tokens

Licence

[MIT](https://opensource.org/license/mit)

Released

February 2024

Model ID

multilingual-e5-large-instruct

Processing

EU data centres

Training on your data

Never

Source

[huggingface.co](https://huggingface.co/intfloat/multilingual-e5-large-instruct)

multilingual-e5-large-instruct · Python

```
import os
from openai import OpenAI

client = OpenAI(base_url="https://api.inference.eu/v1", api_key=os.environ["INFERENCE_EU_API_KEY"])

result = client.embeddings.create(
    model="multilingual-e5-large-instruct",
    input=["Where is my data processed?"],
)
print(len(result.data[0].embedding))
```

## What teams use it for

-   1

    ### FAQ and help-centre search

    Match customer questions in many languages to the right help article or FAQ entry.

-   2

    ### Classification of short texts

    Sort tickets, reviews or form submissions into categories with an instruction that describes the task.

-   3

    ### Semantic similarity

    Find similar products, duplicate questions or related paragraphs across a large catalogue.

## multilingual-e5-large-instruct: common questions

The questions buyers, developers and legal teams ask us most. Something missing? Ask us directly.

Compliance depends on how you process data. On inference.eu, requests are processed in EU data centres, not used for training and covered by a data processing agreement under Article 28 GDPR with a published subprocessor list. That gives you what you need to document the processing.

The model reads up to 512 tokens per input; longer text is truncated. That suits sentences, paragraphs and short passages. For long documents, split them into chunks first, or use bge-m3 with 8192 tokens or Qwen3 Embedding 8B with 32K tokens.

Yes. The model card states that each query must come with a one-sentence task instruction, formatted as \`Instruct:\` then the task, a new line and \`Query:\` then the text. Documents are embedded without an instruction. Leaving it out lowers quality.

Yes. It is released under the MIT licence, which allows commercial use, modification and redistribution. The main condition is keeping the licence notice if you redistribute the weights yourself, which does not apply when you call it through an API.

It inherits the 100 languages of XLM-RoBERTa, including all major European languages such as German, French, Spanish, Italian and Polish. The model card notes that quality may be lower for low-resource languages, so test minority languages on your own data.

The embeddings have 1024 dimensions, a compact size that keeps vector storage and search costs low. The size is fixed. If you need shorter vectors to shrink a very large index, Qwen3 Embedding 8B offers flexible dimensions.

Both are compact multilingual encoders with 1024-dimension vectors and similar sizes. bge-m3 reads 8192 tokens and needs no instruction; multilingual-e5-large-instruct reads 512 tokens but can be steered with task instructions. For long documents choose bge-m3; for short texts test both.

multilingual-e5-large uses fixed \`query:\` and \`passage:\` prefixes. The instruct version replaces the query prefix with a task description, so one model adapts to retrieval, classification or clustering. Vectors from the two models are not interchangeable.

The E5 models were developed by researchers at Microsoft and are published on Hugging Face under the intfloat account, with technical reports describing training. On inference.eu the open weights run in EU data centres, so your data is not sent to Microsoft.

Create an OpenAI client with the inference.eu base URL and your inference.eu key, then call \`client.embeddings.create\` with \`model\` set to \`multilingual-e5-large-instruct\`. Prepend the instruction to queries in your code; send documents as plain text.

[Ask a question](https://inference.eu/contact/)

## Related

[All models](https://inference.eu/models/#directory)

-   [BGE-M3Run bge-m3 on inference.eu: a compact multilingual embedding model for search and RAG, 100+ languages and 8192-token inputs, processed in the EU.Embeddings](https://inference.eu/models/bge-m3/)
-   [Qwen3 Embedding 8BRun Qwen3 Embedding 8B on inference.eu: multilingual text embeddings for search and RAG, up to 4096 dimensions and 32K tokens, processed in the EU.Embeddings](https://inference.eu/models/qwen3-embedding-8b/)
-   [BGE Reranker v2 M3Run bge-reranker-v2-m3 on inference.eu: a light multilingual reranker that sorts search and RAG results by relevance, processed in the EU.Reranking](https://inference.eu/models/bge-reranker-v2-m3/)

## Move your AI workloads to EU infrastructure

Tell us which models you use and roughly how much traffic you have. We reply within one working day with pricing and next steps.

-   Reply within one working day
-   Pricing for your volume
-   DPA ready to sign