# team keys

Team keys are where AnyInt starts to behave like an operating platform instead of only an API relay. They let organizations separate ownership, usage, and policy by project or workload.

## Why teams use multiple keys

* separate production from staging
* isolate one project from another
* assign cost ownership by team
* keep premium models behind a narrower access boundary

## Typical key metadata

The enterprise product plan treats each key as an object with:

* a name
* an optional description
* optional tags
* a creator
* a status such as `Active` or `Disabled`

## Key-level controls

| Control                      | What it does                                           |
| ---------------------------- | ------------------------------------------------------ |
| model allowlist or blocklist | limits which models the key may call                   |
| spend limits                 | caps total usage or triggers warnings                  |
| rate limits                  | constrains RPM, RPH, RPD, TPM, or TPD                  |
| IP allowlists                | restricts which networks may use the key               |
| routing policy               | defines which models or routing groups the key can use |

## Practical ownership model

* Admin defines the global policy boundary
* Project Owner manages the keys inside the project they own
* Member uses keys inside the permissions granted to them

## Recommended lifecycle

1. create one key per environment or workload
2. add a clear name and tags
3. apply limits before broad rollout
4. disable or rotate the key when ownership changes

## Related pages

* [Roles and Permissions](/docs/teams-and-enterprise/roles-and-permissions.md)


---

# 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://anyint.gitbook.io/docs/authentication-and-keys/team-keys.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.