> For the complete documentation index, see [llms.txt](https://docs.trycaliber.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.trycaliber.ai/connect-your-providers/chatgpt-and-openai.md).

# ChatGPT and OpenAI

ChatGPT Enterprise and OpenAI Admin API are different products. Connecting one does not connect the other.

{% hint style="warning" %}
**Connecting ChatGPT does not connect OpenAI Platform usage, and the reverse is also true.** They use different consoles, keys, and data sets.
{% endhint %}

{% tabs %}
{% tab title="ChatGPT Enterprise" %}
**Auth:** Enterprise admin key + workspace UUID (Compliance logging platform = Read), **or** Workspace Analytics **Users CSV**.\
**Who:** ChatGPT Enterprise admin.

1. Open **Settings → Integrations → ChatGPT**.
2. Either:
   * Paste the admin key and the **workspace UUID** from Workspace settings (not the Platform org id), or
   * Upload a Workspace Analytics Users CSV export.
3. Set ChatGPT **seat price** under **Settings → General** so all-in spend includes seats.

**What Caliber reads:** Enterprise seats and daily usage (or CSV seat roster).

**What Caliber does not read:** Conversation content through this connector.
{% endtab %}

{% tab title="OpenAI Platform" %}
**Auth:** OpenAI **Admin API key** (`sk-admin-…`)\
**Who:** OpenAI organization admin (Admin API keys in platform.openai.com).

1. Open **Settings → Integrations → OpenAI**.
2. Create an Admin API key in the OpenAI organization settings.
3. Paste it into Caliber.

**What Caliber reads:** Org-level token usage by user and model.

**What Caliber does not read:** Prompt bodies from the Admin usage API path.
{% endtab %}
{% endtabs %}


---

# 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, and the optional `goal` query parameter:

```
GET https://docs.trycaliber.ai/connect-your-providers/chatgpt-and-openai.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.