# BGE m3

**Summary:** BGE m3 is a versatile multilingual embedding model that supports over 100 languages with an extended 8192 token context window, offering both dense and sparse retrieval capabilities. This model excels in cross-language information retrieval, multilingual document analysis, and global content discovery, making it essential for international applications, multilingual search systems, and global knowledge management platforms where language diversity and long-context understanding are crucial.

|                                                                       **Intelligence**                                                                      |                                         **Speed**                                         |                                                                      **Sovereignty**                                                                     |                                                                 **Input**                                                                 |                                                                 **Output**                                                                |
| :---------------------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------: |
| ![Intelligence active](/files/dnDi7yuqXqkBFqwaxdnm) ![Intelligence active](/files/dnDi7yuqXqkBFqwaxdnm) ![Intelligence active](/files/dnDi7yuqXqkBFqwaxdnm) | ![Speed active](/files/evfYW3bq4dTBLlZH3dQf) ![Speed active](/files/evfYW3bq4dTBLlZH3dQf) | ![Sovereignty active](/files/bNpzGRJfez9SidEjNCoy) ![Sovereignty active](/files/bNpzGRJfez9SidEjNCoy) ![Sovereignty active](/files/bNpzGRJfez9SidEjNCoy) | ![Text active](/files/45qlqURbT8c2Ekr8HJfK) ![Image inactive](/files/0mPVwOtrYhZrpz9clC3D) ![Audio inactive](/files/PRglWWEC5Zoc5fgynNLM) | ![Text active](/files/45qlqURbT8c2Ekr8HJfK) ![Image inactive](/files/0mPVwOtrYhZrpz9clC3D) ![Audio inactive](/files/PRglWWEC5Zoc5fgynNLM) |
|                                                                            *High*                                                                           |                                          *Medium*                                         |                                                                         *Medium*                                                                         |                                                                   *Text*                                                                  |                                                              *Number Vector*                                                              |

## Central parameters

**Description:** Multilingual embedding model by Beijing Academy of Artificial Intelligence with extended input length support and 1024-dimensional output vectors.

**Model identifier:** `BAAI/bge-m3`

## IONOS AI Model Hub Lifecycle and Alternatives

|  **IONOS Launch** | **End of Life** |                                                     **Alternative**                                                    | **Successor** |
| :---------------: | :-------------: | :--------------------------------------------------------------------------------------------------------------------: | :-----------: |
| *January 1, 2025* |       N/A       | [<mark style="color:blue;">**BGE Large V1.5**</mark>](/cloud/ai/ai-model-hub/models/embedding-models/bge-large-1-5.md) |               |

## Origin

|                               **Provider**                              | **Country** |                                                  **License**                                                  | **Flavor** |     **Release**    |
| :---------------------------------------------------------------------: | :---------: | :-----------------------------------------------------------------------------------------------------------: | :--------: | :----------------: |
| [<mark style="color:blue;">**BAAI**</mark>](https://www.baai.ac.cn/en/) |  Community  | [<mark style="color:blue;">**License**</mark>](https://github.com/FlagOpen/FlagEmbedding/blob/master/LICENSE) |      -     | *January 28, 2024* |

## Technology

| **Input Length** | **Parameters** | **Tensor Type** | **Multilingual** |                                   **Further details**                                   |
| :--------------: | :------------: | :-------------: | :--------------: | :-------------------------------------------------------------------------------------: |
|      *8192*      |     *568M*     |     *float*     |       *Yes*      | [<mark style="color:blue;">**Hugging Face**</mark>](https://huggingface.co/BAAI/bge-m3) |

## Modalities

|     **Text**     |   **Image**   |   **Audio**   |
| :--------------: | :-----------: | :-----------: |
| Input and output | Not supported | Not supported |

## Endpoints

| **Chat Completions** | **Embeddings** | **Image generation** |
| :------------------: | :------------: | :------------------: |
|     Not supported    |  v1/embeddings |     Not supported    |

## Features

| **Streaming** | **Reasoning** | **Tool calling** |
| :-----------: | :-----------: | :--------------: |
| Not supported | Not supported |   Not supported  |

## Usage example

### Embeddings

The following example demonstrates how to generate text embeddings using **BGE m3**.

**API Endpoint:** `POST https://openai.inference.de-txl.ionos.com/v1/embeddings`

**Request:**

```json
{
  "model": "BAAI/bge-m3",
  "input": "The food was delicious and the waiter was friendly."
}
```

**Response:**

```json
{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [
        0.0023064255,
        -0.009327292,
        0.0028842222
      ],
      "index": 0
    }
  ],
  "model": "BAAI/bge-m3",
  "usage": {
    "prompt_tokens": 10,
    "total_tokens": 10
  }
}
```

## Rate limits

Rate limits ensure fair usage and reliable access to the AI Model Hub. In addition to the [<mark style="color:blue;">contract-wide rate limits</mark>](/cloud/ai/ai-model-hub/how-tos/rate-limits.md), no model-specific limits apply.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.ionos.com/cloud/ai/ai-model-hub/models/embedding-models/bge-m3.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.