# Embedding Model

{% hint style="info" %}
To prevent errors, in this document the max input values for some models are not written as the absolute limit. For example, when the official maximum input is 8k (without a specific number given), the reference value in this document is 8191 or 8000, etc. (If you don't understand this, ignore it and just fill in according to the reference values in the document.)
{% endhint %}

### Volcano-Doubao

[Official model information reference address](https://console.volcengine.com/ark/region:ark+cn-beijing/model?feature=\&projectName=default\&vendor=Bytedance\&view=LIST_VIEW)

| Name                    | max input |
| ----------------------- | --------- |
| Doubao-embedding        | 4095      |
| Doubao-embedding-vision | 8191      |
| Doubao-embedding-large  | 4095      |

### Alibaba

[Official model information reference address](https://help.aliyun.com/zh/model-studio/user-guide/embedding?spm=a2c4g.11186623.0.i1)

| Name                    | max input |
| ----------------------- | --------- |
| text-embedding-v3       | 8192      |
| text-embedding-v2       | 2048      |
| text-embedding-v1       | 2048      |
| text-embedding-async-v2 | 2048      |
| text-embedding-async-v1 | 2048      |

### OpenAI

[Official model information reference address](https://platform.openai.com/docs/guides/embeddings#embedding-models)

| Name                   | max input |
| ---------------------- | --------- |
| text-embedding-3-small | 8191      |
| text-embedding-3-large | 8191      |
| text-embedding-ada-002 | 8191      |

### Baidu

[Official model information reference address](https://cloud.baidu.com/doc/WENXINWORKSHOP/s/om6070n97#%E8%AF%B7%E6%B1%82%E5%8F%82%E6%95%B0)

| Name         | max input |
| ------------ | --------- |
| Embedding-V1 | 384       |
| tao-8k       | 8192      |

### Zhipu

[Official model information reference address](https://bigmodel.cn/console/modelcenter/square)

| Name        | max input |
| ----------- | --------- |
| embedding-2 | 1024      |
| embedding-3 | 2048      |

### Hunyuan

[Official model information reference address](https://cloud.tencent.com/document/product/1729/102832)

| Name              | max input |
| ----------------- | --------- |
| hunyuan-embedding | 1024      |

### Baichuan

[Official model information reference address](https://platform.baichuan-ai.com/docs/text-Embedding)

| Name                    | max input |
| ----------------------- | --------- |
| Baichuan-Text-Embedding | 512       |

### together

[Official model information reference address](https://docs.together.ai/docs/serverless-models#embedding-models)

| Name                      | max input |
| ------------------------- | --------- |
| M2-BERT-80M-2K-Retrieval  | 2048      |
| M2-BERT-80M-8K-Retrieval  | 8192      |
| M2-BERT-80M-32K-Retrieval | 32768     |
| UAE-Large-v1              | 512       |
| BGE-Large-EN-v1.5         | 512       |
| BGE-Base-EN-v1.5          | 512       |

### Jina

[Official model information reference address](https://jina.ai/models/jina-embedding-b-en-v1)

| Name                               | max input |
| ---------------------------------- | --------- |
| jina-embedding-b-en-v1             | 512       |
| jina-embeddings-v2-base-en         | 8191      |
| jina-embeddings-v2-base-zh         | 8191      |
| jina-embeddings-v2-base-de         | 8191      |
| jina-embeddings-v2-base-code       | 8191      |
| jina-embeddings-v2-base-es         | 8191      |
| jina-colbert-v1-en                 | 8191      |
| jina-reranker-v1-base-en           | 8191      |
| jina-reranker-v1-turbo-en          | 8191      |
| jina-reranker-v1-tiny-en           | 8191      |
| jina-clip-v1                       | 8191      |
| jina-reranker-v2-base-multilingual | 8191      |
| reader-lm-1.5b                     | 256000    |
| reader-lm-0.5b                     | 256000    |
| jina-colbert-v2                    | 8191      |
| jina-embeddings-v3                 | 8191      |

### Silicon Flow

[Official model information reference address](https://siliconflow.cn/zh-cn/models)

| Name                                  | max input |
| ------------------------------------- | --------- |
| BAAI/bge-m3                           | 8191      |
| netease-youdao/bce-embedding-base\_v1 | 512       |
| BAAI/bge-large-zh-v1.5                | 512       |
| BAAI/bge-large-en-v1.5                | 512       |
| Pro/BAAI/bge-m3                       | 8191      |

### Gemini

[Official model information reference address](https://ai.google.dev/gemini-api/docs/models/gemini?hl=zh-cn#text-embedding)

| Name               | max input |
| ------------------ | --------- |
| text-embedding-004 | 2048      |

### nomic

[Official model information reference address](https://docs.nomic.ai/atlas/embeddings-and-retrieval/text-embedding)

| Name                  | max input |
| --------------------- | --------- |
| nomic-embed-text-v1   | 8192      |
| nomic-embed-text-v1.5 | 8192      |
| gte-multilingual-base | 8192      |

### console

[Official model information reference address](https://console.upstage.ai/docs/capabilities/embeddings)

| Name              | max input |
| ----------------- | --------- |
| embedding-query   | 4000      |
| embedding-passage | 4000      |

### cohere

[Official model information reference address](https://docs.cohere.com/docs/models#embed)

| Name                          | max input |
| ----------------------------- | --------- |
| embed-english-v3.0            | 512       |
| embed-english-light-v3.0      | 512       |
| embed-multilingual-v3.0       | 512       |
| embed-multilingual-light-v3.0 | 512       |
| embed-english-v2.0            | 512       |
| embed-english-light-v2.0      | 512       |
| embed-multilingual-v2.0       | 256       |


---

# 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.cherry-ai.com/docs/en-us/knowledge-base/emb-models-info.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.