> For the complete documentation index, see [llms.txt](https://docs.zerve.ai/zerve-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.zerve.ai/zerve-docs/administration/model-settings.md).

# Model settings

Choose which AI providers and models people in your organization can use.

Organization admins control which AI providers and models are available, in **Organization Settings → Model Settings**.

## Approving providers

Choose which providers your organization's agents can use: **Anthropic**, **OpenAI**, **Google Gemini**, **Amazon Bedrock** or **OpenRouter**. Anthropic is approved by default.

When more than one provider is approved, Zerve uses them in this order of preference: Amazon Bedrock, Anthropic, OpenAI, Google Gemini, then OpenRouter.

## Enabling models

For each provider, choose which models people can use. Models have to be enabled before anyone can choose them, and each shows its default [reasoning effort](/zerve-docs/agents-in-the-workspace/models-and-effort.md#reasoning-effort).

New organizations have **Claude Sonnet 4.6** and **Claude Haiku 4.5** enabled.

When someone hasn't chosen a model, Zerve uses its default for the kind of work, such as Claude Sonnet 4.6 for coding. See [Default models](/zerve-docs/agents-in-the-workspace/supported-models.md#default-models).

For every available model, see [Supported models](/zerve-docs/agents-in-the-workspace/supported-models.md).

## Your own API keys

Under **AI API keys**, add your organization's own keys for Anthropic, OpenAI, Google Gemini or OpenRouter, so agents use your provider accounts instead of Zerve's. See [Bring your own API keys](/zerve-docs/administration/bring-your-own-api-keys.md).

## What people can choose

| Who                   | What they choose                                                                                                              |
| --------------------- | ----------------------------------------------------------------------------------------------------------------------------- |
| **Admins**            | Which providers are approved, which models are enabled, and the organization's API keys                                       |
| **Each user**         | Which enabled model to use, and each model's reasoning effort and speed                                                       |
| **Superagent owners** | The models a superagent and its workers use. See [Superagent settings](/zerve-docs/superagents/settings.md#model-and-effort). |

## Choosing models for your organization

| Consider                 | Why it matters                                                                                                                             |
| ------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------ |
| **Cost**                 | Larger models cost many times more per token. See [How credits are used](/zerve-docs/administration/how-credits-are-used.md#model-prices). |
| **Your data agreements** | Enable only providers your organization has approved for its data                                                                          |
| **Research**             | Evolve Mode's research specialist only works with Anthropic or Amazon Bedrock                                                              |
| **Consistency**          | Enabling a small set of models makes results easier to compare and reproduce                                                               |


---

# 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.zerve.ai/zerve-docs/administration/model-settings.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.