> For the complete documentation index, see [llms.txt](https://docs.concurrence.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.concurrence.com/developer-guide/classic-api/core-api/admin.md).

# Admin

Administrative endpoints for listing available LLM models and downloading prompt logs for debugging.

Administrative endpoints for platform configuration and debugging.

## Get Available Models

Retrieve the list of LLM models currently supported by the platform. Use this to discover which models are available when configuring version sets.

**Permission required:** `Admin:GetModels`

{% openapi src="<https://api.amigo.ai/v1/openapi.json>" path="/v1/{organization}/admin/get\_models/" method="get" %}
<https://api.amigo.ai/v1/openapi.json>
{% endopenapi %}

## Get Prompt Logs

Download rendered prompt logs for debugging and auditing. The response is a zip archive containing system prompts and history prompts for all matching log keys produced in the past 30 days. If an error stops the generation of the archive entirely, the stream ends early and the transmitted bytes do not constitute a valid zip file.

**Permissions:** There is no single endpoint-level permission. Each prompt log carries its own set of required read permissions. If you lack the permissions for a given log, the zip archive contains a `{log_key}-error` file describing the error in place of that log's contents - the request itself still succeeds.

{% hint style="warning" %}
**Prefix Limit** Only prefixes corresponding to 1,000 or fewer prompt logs are allowed. Use a more specific prefix if your query matches too many logs.
{% endhint %}

Each prompt log in the zip file contains up to two files:

| File                | Contents                                                                                                      |
| ------------------- | ------------------------------------------------------------------------------------------------------------- |
| `{log_key}-system`  | The rendered system prompt                                                                                    |
| `{log_key}-history` | The rendered history prompts, separated by `---`                                                              |
| `{log_key}-error`   | An error description, in place of the log's contents, when you lack the permissions required to read that log |

Query parameters:

| Parameter           | Type   | Required | Description                      |
| ------------------- | ------ | -------- | -------------------------------- |
| `prompt_log_prefix` | string | Yes      | Prefix to match against log keys |

{% openapi src="<https://api.amigo.ai/v1/openapi.json>" path="/v1/{organization}/admin/get\_prompt\_logs/" method="get" %}
<https://api.amigo.ai/v1/openapi.json>
{% endopenapi %}

## Related

* Getting Started → [Authentication](/developer-guide/getting-started/authentication.md)
* Classic API -> [Services](/developer-guide/classic-api/core-api/services.md) (model preferences in version sets)


---

# 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.concurrence.com/developer-guide/classic-api/core-api/admin.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.