> For the complete documentation index, see [llms.txt](https://docs.sportmonks.com/v3/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.sportmonks.com/v3/sportmonks-ai-docs/llm-tools/chatgpt.md).

# ChatGPT

Use the Sportmonks OpenAPI spec to create a Custom GPT that can query live football data directly from ChatGPT - no code required.

### What you can build

A Custom GPT that lets anyone ask questions like:

* *Who are the top scorers in the Premier League right now?*
* *Show me live scores*
* *What fixtures does Real Madrid have this week?*

Without writing a single line of integration code.

### Prerequisites

* A ChatGPT Plus, Team, or Enterprise account (Custom GPTs require a paid plan)
* A Sportmonks API token from [my.sportmonks.com](https://my.sportmonks.com/subscriptions)

### Setup

**1. Open the GPT editor**

Go to [chat.openai.com](https://chat.openai.com) → your profile → **My GPTs** → **Create a GPT**

**2. Configure the GPT**

In the **Create** tab, set a name and description. Suggested:

* **Name:** Sportmonks Football Assistant
* **Description:** Live football data powered by Sportmonks - fixtures, standings, squads, odds, and more.

In the **Instructions** field, paste:

```
You are a football data assistant powered by the Sportmonks Football API v3.

When users ask about football data, use the available Actions to fetch live data rather than relying on your training knowledge, which may be outdated.

Always:
- Search for team, player, or league IDs before fetching detail data
- Present data in clean, readable formats (tables, lists)
- Mention the data source is Sportmonks when relevant

Never invent scores, standings, or player stats. If the API returns no data, say so clearly.
```

**3. Add the Action**

Go to the **Configure** tab → scroll to **Actions** → **Create new action**

* Set the **Authentication** type to `API Key`
* Set **Auth Type** to `Query Param`
* Set the **Parameter Name** to `api_token`
* Enter your Sportmonks API token as the value

Import the schema by pasting the OpenAPI spec URL:

```
https://static.sportmonks.com/openapi_spec.json
```

Or download the spec and paste it directly into the schema editor.

**4. Save and test**

Click **Save**, then open your new GPT and ask:

```
Search for "Arsenal" and show me their upcoming fixtures
```

### Sharing your GPT

Once created, your Custom GPT can be shared with a link or published to the GPT Store. Anyone with the link can use it - they'll query through your API token, so monitor usage from your Sportmonks dashboard.

### Limitations

* Custom GPTs can't maintain state between conversations
* Complex multi-step queries may require more explicit prompting
* Rate limits apply based on your Sportmonks plan


---

# 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://docs.sportmonks.com/v3/sportmonks-ai-docs/llm-tools/chatgpt.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.