> For the complete documentation index, see [llms.txt](https://entermirari.gitbook.io/entermirari-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://entermirari.gitbook.io/entermirari-docs/reference/providers.md).

# Provider Presets

MIRARI ships with four provider modes. All of them are "OpenAI-compatible" — they accept the same request body and return the same response shape.

## Hermes · Local

* **Use when** you're running a Hermes-family model under Ollama, llama.cpp, vLLM, LM Studio, or any other local runner.
* **Base URL example:** `http://localhost:11434/v1`
* **Model example:** `hermes3`
* **API key:** usually empty. Local runners typically don't authenticate.

```http
POST http://localhost:11434/v1/chat/completions
Content-Type: application/json

{ "model": "hermes3", "messages": [...], "temperature": 0.7 }
```

## Hermes · Cloud

* **Use when** you've got a hosted Hermes endpoint from a Hermes-family provider.
* **Base URL:** whatever the provider gives you.
* **Model:** e.g. `hermes-3-llama-3.1-70b`, `hermes-4-405b`.
* **API key:** required.

## OpenRouter

* **Use when** you want one binding that can swap models across providers.
* **Base URL:** `https://openrouter.ai/api/v1`
* **Model examples:** `nousresearch/hermes-3-llama-3.1-70b`, `anthropic/claude-3.5-sonnet`, `openai/gpt-4o`.
* **API key:** required, from your OpenRouter account.

## Nous

* **Use when** you want Nous Research's hosted inference for Hermes-family models.
* **Base URL:** the Nous inference endpoint.
* **Model examples:** `Hermes-3-Llama-3.1-70B`, `Hermes-3-Llama-3.1-405B`.
* **API key:** required.

## Custom

Anything else. As long as the endpoint accepts:

```ts
POST {base_url}/chat/completions
Authorization: Bearer <key>           // optional for local
Content-Type: application/json

{
  model: string,
  messages: { role: "system"|"user"|"assistant", content: string }[],
  temperature?: number,
}
```

and returns:

```ts
{ choices: [{ message: { role: "assistant", content: string } }] }
```

MIRARI will talk to it.

## Tested model ids (non-exhaustive)

| Provider     | Model id                               |
| ------------ | -------------------------------------- |
| Local Ollama | `hermes3`, `hermes3:70b`               |
| Nous         | `Hermes-3-Llama-3.1-70B`               |
| OpenRouter   | `nousresearch/hermes-3-llama-3.1-70b`  |
| OpenRouter   | `nousresearch/hermes-3-llama-3.1-405b` |
| OpenRouter   | `openai/gpt-4o-mini`                   |
| OpenRouter   | `anthropic/claude-3.5-sonnet`          |


---

# 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 dynamically by asking a question.

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

```
GET https://entermirari.gitbook.io/entermirari-docs/reference/providers.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.