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

# Quickstart

Go from sign-up to your first request in a few minutes.

This quickstart gets you to your first LLM request as fast as possible. You'll use your default workspace, generate a workspace token, choose a model, send one request, and confirm it appears in the Usage tab.

{% hint style="success" %}
**Estimated time: 5 minutes.** All you need is an otari.ai account and a workspace token from the API keys tab.
{% endhint %}

## Steps

{% stepper %}
{% step %}

#### Open a workspace

Use your default workspace for the first request.

1. Log in to otari.ai
2. Open your default workspace in the top-left corner.
3. You will use the **API Keys**, **Models**, and **Usage** tabs in this guide.
   {% endstep %}

{% step %}

#### Generate an API token

Generate the credential your app will actually send to otari.ai. This token starts with `otk_`.

1. Open the **API Keys** tab.
2. Click **Create Key**.
3. Give the key a name and, if needed, set an expiration date. By default, the key inherits your existing model access, but you can limit it to specific models. To customize model access, click **Advanced** and select the models you want the key to use.
4. Copy the token right away. It is only shown once.

{% hint style="info" %}
**Keep it secret**. Treat the token like a password. Keep it in your shell or secret store, not in source control.
{% endhint %}
{% endstep %}

{% step %}

#### Send your first request

Pick a model your workspace can use.

1. Open the **Models** tab.
2. Choose a model using the available filters, including **modality**, **provider**, **vendor**, **capabilities**, and more, to quickly find the option that best fits your needs.
3. After selecting a model, click **Use this model** in the top-right corner.

otari.ai exposes an OpenAI-compatible endpoint at `https://api.otari.ai/v1`. The fastest first check is one cURL request that you can copy. The example uses `deepseek/deepseek-v4-pro-0813`.

```yaml
curl https://api.otari.ai/v1/chat/completions \
-H "Authorization: Bearer $OTARI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
     "model": "deepseek/deepseek-v4-pro-0813",
     "messages": [
          {
            "role": "user",
            "content": "Say hello in one short sentence."
           }
      ]
   }'
```

{% endstep %}

{% step %}

#### Confirm it worked

1. Open the **Usage** tab.
2. Look for the request you just sent.
3. If it does not appear, double-check the provider key and workspace token first.

{% hint style="success" %}
**Success**: Once the request appears in Usage, your hosted path is working. From there, you can add budgets, more providers, or an editor integration.
{% endhint %}
{% endstep %}
{% endstepper %}

## What's next?

You've sent your first LLM request! Now you can:

{% content-ref url="/pages/73b7faa18afc90c9ae3c6c1ae24f9ed214289c08" %}
[Manage Workspaces](/how-to-guides/manage-workspaces.md)
{% endcontent-ref %}

{% content-ref url="/pages/d9d593aeabc52a165190bf8c93720491a4eb9682" %}
[Manage provider keys](/how-to-guides/manage-provider-keys.md)
{% endcontent-ref %}

{% content-ref url="/pages/AhgAITMaTc8ggokxoe3I" %}
[Set a budget & ceiling](/how-to-guides/set-a-budget-and-ceiling.md)
{% endcontent-ref %}

{% content-ref url="/pages/D60TYVvwgpwvfIg3uwCO" %}
[Create a multi-provider routing](/how-to-guides/create-a-multi-provider-routing.md)
{% endcontent-ref %}

{% content-ref url="/pages/q7qG6EOTd3EjOf8yfATY" %}
[Manage guardrails](/how-to-guides/manage-guardrails.md)
{% endcontent-ref %}


---

# 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.otari.ai/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.