> For the complete documentation index, see [llms.txt](https://docs.podtorrent.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.podtorrent.com/getting-started/quickstart.md).

# Quickstart: send your first request

You need a PodTorrent API key. Keys start with `pt_` and are issued by the PodTorrent team. Self-service sign-up isn't available yet.

## 1. See which models are available

```bash
curl https://api.podtorrent.com/v1/models \
  -H "Authorization: Bearer $PODTORRENT_API_KEY"
```

The list only contains models that a connected node serves right now, so it can change from minute to minute.

## 2. Send a chat request

Any OpenAI SDK works. Change the base URL and the key, nothing else.

{% tabs %}
{% tab title="Python" %}

```python
from openai import OpenAI

client = OpenAI(base_url="https://api.podtorrent.com/v1", api_key="pt_...")

stream = client.chat.completions.create(
    model="<a model id from step 1>",
    messages=[{"role": "user", "content": "Write a haiku about GPUs."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices:
        print(chunk.choices[0].delta.content or "", end="")
```

{% endtab %}

{% tab title="curl" %}

```bash
curl -N https://api.podtorrent.com/v1/chat/completions \
  -H "Authorization: Bearer $PODTORRENT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "<a model id from step 1>", "stream": true,
       "messages": [{"role": "user", "content": "Write a haiku about GPUs."}]}'
```

{% endtab %}
{% endtabs %}

The `if chunk.choices` check matters: PodTorrent always ends a stream with a usage chunk whose `choices` list is empty.

## 3. Check who served it

Every response carries an `X-PodTorrent-Node` header with the id of the node that answered. Handy when you're debugging speed or quality.

## Next steps

* Save money on background jobs with the [batch tier](/using-the-api/tiers-and-prices.md).
* Reuse a long system prompt cheaply with [cached prompts](/using-the-api/cached-prompts.md).
* Know what can go wrong: [Errors and limits](/using-the-api/errors-and-limits.md).


---

# 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.podtorrent.com/getting-started/quickstart.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.