> For the complete documentation index, see [llms.txt](https://docs.maiagent.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.maiagent.ai/tech/platform-development/cloud-model-inference-api-service.md).

# 雲端模型推論 API 服務

雲端模型推論 API 服務：LLM、Embedding、Reranker 各自支援的供應商（OpenAI、Azure、AWS Bedrock、Google Vertex AI 等）與模型家族對照。

MaiAgent 透過下列供應商類型串接模型服務。**LLM、Embedding、Reranker 各自支援的供應商不同**，請分別對照下表；表中的模型家族是目前平台目錄中的例子，組織實際可選用的模型以管理後台「[模型調用權限](https://docs.maiagent.ai/org/model-access)」頁為準。

## 大型語言模型（LLM）

| 供應商類型            | 串接方式                                                                  | 平台目錄中的模型家族（舉例）                               |
| ---------------- | --------------------------------------------------------------------- | -------------------------------------------- |
| AWS Bedrock      | 雲端推論服務                                                                | Claude、GPT、DeepSeek、Amazon Nova              |
| Google Vertex AI | 雲端推論服務                                                                | Gemini、Claude                                |
| Azure            | 雲端推論服務                                                                | GPT、DeepSeek                                 |
| OpenAI           | 直連 OpenAI API                                                         | GPT、o 系列                                     |
| Anthropic        | 直連 Anthropic API                                                      | Claude                                       |
| Cohere           | 直連 Cohere API                                                         | Command                                      |
| OpenAI 相容 API    | 任何提供 OpenAI 相容介面的服務，例如 OpenRouter、Groq、xAI、阿里雲、國網中心（NCHC）、IBM watsonx | Grok、Qwen、Kimi、Mistral、GPT-OSS、Gemma、Granite |
| vLLM、Ollama      | 自建推論服務（私有雲、地端 GPU）                                                    | 開放權重模型                                       |

## 向量嵌入模型（Embedding Model）

Embedding **不支援** Azure 與 Google Vertex AI。

| 供應商類型       | 串接方式                               | 平台目錄中的模型（舉例）                   |
| ----------- | ---------------------------------- | ------------------------------ |
| OpenAI      | 直連 OpenAI API                      | text-embedding-3               |
| Cohere      | 直連 Cohere API                      | Cohere Embed v4.0              |
| AWS Bedrock | 雲端推論服務                             | Cohere Embed Multilingual v3.0 |
| Voyage      | 直連 Voyage AI API                   | —                              |
| vLLM        | 自建推論服務，或其他 OpenAI 相容的 Embedding 端點 | 開放權重模型                         |
| Ollama      | 自建推論服務                             | 開放權重模型                         |

## 重排序模型（Reranker Model）

Reranker **不支援** Azure 與 Google Vertex AI。

| 供應商類型         | 串接方式                      | 平台目錄中的模型（舉例）                      |
| ------------- | ------------------------- | --------------------------------- |
| Cohere        | 直連 Cohere API             | Cohere Rerank v3.5、v4 Pro、v4 Fast |
| AWS Bedrock   | 雲端推論服務                    | —                                 |
| Voyage        | 直連 Voyage AI API          | —                                 |
| vLLM          | 自建推論服務                    | 開放權重模型                            |
| FlagEmbedding | 在 MaiAgent 主機上直接載入開源重排序模型 | 開放權重模型                            |


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

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

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.maiagent.ai/tech/platform-development/cloud-model-inference-api-service.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
