> For the complete documentation index, see [llms.txt](https://orbitron.gitbook.io/orbitron-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://orbitron.gitbook.io/orbitron-docs/user-guide/registering-an-api-key.md).

# Registering an API Key

In order to use Orbitron’s AI features, you **must register at least one API key** from a supported model provider after logging in.

Without a valid API key, Orbitron will not be able to communicate with any AI service and you may see the following warning:

```
No API Key found. Please add a valid API Key to proceed.
```

***

### 🧭 When and Where to Register

After logging in for the first time, Orbitron will automatically open an **API Key registration dialog**.

You can also open this dialog manually at any time by:

* Pressing `Ctrl + p`
* Or typing the command:

  ```bash
  /provider
  ```

From there, **enter the API key(s) for your preferred AI providers**.

<div align="left"><figure><img src="/files/0HOaDc5hDKpEAfLnhV5t" alt="" width="563"><figcaption></figcaption></figure></div>

<div align="left"><figure><img src="/files/5AhsHjNTqcWMVcfTroxN" alt="" width="563"><figcaption></figcaption></figure></div>

<div align="left"><figure><img src="/files/0UwxEqr6hYmix5RoSZt1" alt="" width="563"><figcaption></figcaption></figure></div>

***

### 🛠 How to Add an API Key

1. Open the API Key dialog (automatically or manually)
2. Select the **provider** you want to use (e.g. OpenAI, Claude, Gemini, etc.)
3. Paste your API key into the field
4. Save the key

> 💡 You can register multiple API keys for different providers.

***

### 📡 Supported Model Providers

You can register API keys for the following AI platforms:

| Provider                   | Supported Models                                                                                                                                                                                    |
| -------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Anthropic**              | - Claude 4 Opus- Claude 4 Sonnet- Claude 3.7 Sonnet- Claude 3.5 Sonnet- Claude 3.5 Haiku- Claude 3 Haiku- Claude 3 Opus                                                                             |
| **OpenAI**                 | - GPT-4.1 family (`gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`)- GPT-4.5 Preview- GPT-4o family (`gpt-4o`, `gpt-4o-mini`)- O1 family (`o1`, `o1-pro`, `o1-mini`)- O3 family (`o3`, `o3-mini`)- O4 Mini |
| **Google (Gemini)**        | - Gemini 2.5 Pro- Gemini 2.5 Flash- Gemini 2.0 Flash- Gemini 2.0 Flash Lite                                                                                                                         |
| **AWS Bedrock**            | - Claude 4 Opus- Claude 4 Sonnet- Claude 3.7 Sonnet- Claude 3.5 Sonnet- Claude 3.5 Haiku- Claude 3 Haiku- Claude 3 Opus                                                                             |
| **Google Cloud Vertex AI** | - Claude 4 Opus- Claude 4 Sonnet- Claude 3.7 Sonnet- Claude 3.5 Haiku                                                                                                                               |
| **Groq**                   | - LLaMA 4 Maverick (17b-128e-instruct)- LLaMA 4 Scout (17b-16e-instruct)- Qwen QWQ-32B- Deepseek R1 distill LLaMA 70B- LLaMA 3.3 70B Versatile                                                      |

> Each provider may require billing setup and specific API token scopes.

***

### 🧠 Model Selection Behavior

By default, Orbitron will select an AI model to use **based on an internal provider priority order**, unless you explicitly choose a provider or model yourself.

* If multiple API keys are registered, the platform will **automatically assign a default model** using a built-in priority logic.
* You can override this behavior by manually selecting the model or provider at runtime.

#### 🧭 How to Select a Model

You can open the **Model Selection Dialog** using:

* Pressing **`Ctrl + O`**
* Or typing the command:

  ```bash
  /model
  ```

Once the dialog appears, you can choose your preferred model from the list of available providers and models (e.g., OpenAI GPT-4, Claude 3, Gemini Pro, etc.).

> 💡 This allows fine-grained control over which model is used for different tasks or sessions.