# Getting Started

{% hint style="success" %}
Try Arcee Conductor today! Sign up at <https://conductor.arcee.ai/> to receive $20 in credits and see how you can save up to 64% on your model costs.
{% endhint %}

<figure><img src="/files/8GKKn0Wu93i6YSzpkPw9" alt=""><figcaption><p>Arcee Conductor</p></figcaption></figure>

### Registration

To register for Arcee Conductor, go to [conductor.arcee.ai](https://conductor.arcee.ai/).

Select Login, then Register and you can sign up using your email address or Google authentication.

<figure><img src="/files/sEVTluUYUnVD5UuWnV8f" alt="" width="375"><figcaption><p>Arcee Conductor Registration</p></figcaption></figure>

### Using Arcee Conductor

Arcee Conductor can be utilized in two primary ways:

1. User Interface
2. Application Programming Interface (APIs)

#### User Interface

The UI provides a chat interface to directly invoke Arcee Conductor, as well as a [Compare](/arcee-conductor/features-and-functionality/compare.md) feature to conduct side by side evaluations of Arcee Conductor's performance against other models.

In both the chat interface and comparison sections, each model response is accompanied by model metrics and selection details and explanation.

<figure><img src="/files/Lfp7LukYNh0AqkAhSGTi" alt="" width="563"><figcaption><p>Model Response Example</p></figcaption></figure>

In this example, a very simple prompt is asked "Tell me a joke". In addition, to the (quite humorous) response, you're provided the following information:

* The model that was selected
* Input tokens
* Output tokens
* Response Time
* Cost of the query
* Explanation for why the specific model was selected
* Categorization for:
  * Task type
  * Domain
  * Complexity

This allows you to get a comprehensive understanding of the performance for your query as well as why the specific model was selected. For additional information on the router classifications and models available in Conductor, go to [Auto Mode](/arcee-conductor/features-and-functionality/auto-mode.md).

#### API

You can also directly invoke Arcee Conductor via API. The Conductor API uses an OpenAI compatible endpoint making it very easy to update current applications to use Conductor.&#x20;

To use the API, create an API key by selecting "API Key" from the Navigation pop up or "Get an API key" from API details. You can then invoke Conductor using:

```
curl -X POST https://models.arcee.ai/v1/chat/completions \
  -H "Authorization: Bearer $ARCEE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
        "model": "auto",
        "messages": [
          {
            "role": "user",
            "content": "Your prompt here"
          }
        ]
      }'
```

For more information on the API, including code snippets to integrate Conductor, go to [API](/arcee-conductor/features-and-functionality/api.md).


---

# Agent Instructions: 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.arcee.ai/arcee-conductor/getting-started.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.
