> 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/en/platform-development/cloud-model-inference-api-service.md).

# Cloud Model Inference API Services

Cloud model inference API services: supported providers for LLM, Embedding, and Reranker (OpenAI, Azure, AWS Bedrock, Google Vertex AI, etc.) and their model families.

MaiAgent connects to model services through the provider types below. **LLM, Embedding, and Reranker support different providers**, so refer to their respective tables. The model families listed are examples from the current platform catalog. The models available to your organization are shown on the “[Model Access Permissions](https://docs.maiagent.ai/org/model-access)” page in the admin console.

## Large Language Models (LLM)

| Provider Type         | Integration Method                                                                                                                                                            | Model Families in the Platform Catalog (Examples)  |
| --------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------- |
| AWS Bedrock           | Cloud inference service                                                                                                                                                       | Claude, GPT, DeepSeek, Amazon Nova                 |
| Google Vertex AI      | Cloud inference service                                                                                                                                                       | Gemini, Claude                                     |
| Azure                 | Cloud inference service                                                                                                                                                       | GPT, DeepSeek                                      |
| OpenAI                | Direct connection to the OpenAI API                                                                                                                                           | GPT, o series                                      |
| Anthropic             | Direct connection to the Anthropic API                                                                                                                                        | Claude                                             |
| Cohere                | Direct connection to the Cohere API                                                                                                                                           | Command                                            |
| OpenAI-compatible API | Any service providing an OpenAI-compatible interface, such as OpenRouter, Groq, xAI, Alibaba Cloud, the National Center for High-performance Computing (NCHC), or IBM watsonx | Grok, Qwen, Kimi, Mistral, GPT-OSS, Gemma, Granite |
| vLLM, Ollama          | Self-hosted inference service (private cloud, on-premises GPU)                                                                                                                | Open-weight models                                 |

## Embedding Models (Embedding Model)

Embedding **does not support** Azure or Google Vertex AI.

| Provider Type | Integration Method                                                            | Models in the Platform Catalog (Examples) |
| ------------- | ----------------------------------------------------------------------------- | ----------------------------------------- |
| OpenAI        | Direct connection to the OpenAI API                                           | text-embedding-3                          |
| Cohere        | Direct connection to the Cohere API                                           | Cohere Embed v4.0                         |
| AWS Bedrock   | Cloud inference service                                                       | Cohere Embed Multilingual v3.0            |
| Voyage        | Direct connection to the Voyage AI API                                        | —                                         |
| vLLM          | Self-hosted inference service or another OpenAI-compatible Embedding endpoint | Open-weight models                        |
| Ollama        | Self-hosted inference service                                                 | Open-weight models                        |

## Reranking Models (Reranker Model)

Reranker **does not support** Azure or Google Vertex AI.

| Provider Type | Integration Method                                              | Models in the Platform Catalog (Examples) |
| ------------- | --------------------------------------------------------------- | ----------------------------------------- |
| Cohere        | Direct connection to the Cohere API                             | Cohere Rerank v3.5, v4 Pro, v4 Fast       |
| AWS Bedrock   | Cloud inference service                                         | —                                         |
| Voyage        | Direct connection to the Voyage AI API                          | —                                         |
| vLLM          | Self-hosted inference service                                   | Open-weight models                        |
| FlagEmbedding | Load open-source reranking models directly on the MaiAgent host | Open-weight models                        |


---

# 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/en/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.