> ## Documentation Index
> Fetch the complete documentation index at: https://docs.paretoinference.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Make your first Pareto API request.

# Quickstart

The Pareto application programming interface (API) uses the OpenAI Chat Completions format.

## Before you start

You need a Pareto API key. Keep the key on your server and outside source control.

## 1. Find your model

Each Pareto API key is assigned to one model. The response contains a `data` list. Copy the model `id` from that list.

```bash theme={null}
curl https://api.paretoinference.com/v1/models \
  -H "Authorization: Bearer $PARETO_API_KEY"
```

The model ID identifies the model that processes the request.

## 2. Send a message

Replace `MODEL_ID` with an `id` from the models response. The request body uses JavaScript Object Notation (JSON). The `Authorization` header carries the API key. The word `Bearer` tells the API to use the next value as the key.

```bash theme={null}
curl https://api.paretoinference.com/v1/chat/completions \
  -H "Authorization: Bearer $PARETO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MODEL_ID",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
```

Read the answer from `choices[0].message.content`.

## 3. Connect an app

The base URL is the main address that the app uses to send requests.

| Setting    | Value                                |
| ---------- | ------------------------------------ |
| API format | OpenAI Chat Completions              |
| Base URL   | `https://api.paretoinference.com/v1` |
| API key    | Your Pareto API key                  |
| Model ID   | An `id` returned by `/models`        |

Your app must support a custom base URL, an API key, and a model ID.

See [SDK examples](/sdk-examples) or the [API reference](/api-reference).