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

# Aster Agents API

> Build and manage AI agents programmatically with our REST API

<Note>
  All API endpoints require authentication using Bearer tokens. You can get your API key from the [Control Hub Settings page](https://www.asteragents.com/control-hub/settings).
</Note>

<Tip>
  **Using Claude Code or another AI coding assistant?** Install the [**build-on-aster** plugin](/api-reference/build-on-aster) and it will create, run, and maintain your agents through this API for you — no need to hand-write the calls.
</Tip>

## Welcome to the Aster Agents API

Build, manage, and orchestrate AI agents programmatically. Our REST API gives you the tools to create sophisticated agent workflows and integrate them into your applications.

## Authentication

To authenticate your API requests, you'll need an API key. Here's how to get yours:

1. Navigate to the [Control Hub Settings page](https://www.asteragents.com/control-hub/settings)
2. Under the "API Access" section, click the "Copy API Key to Clipboard" button
3. Store this key securely - it's valid for 6 months

Use this key in the Authorization header of your API requests:

```
Authorization: Bearer YOUR_API_KEY
```

## Core Concepts

### Agents

Create and manage AI agents with specific roles and capabilities. Each agent can be configured with:

* Custom instructions and system prompts
* Tool integrations for enhanced capabilities
* Model provider settings
* Conversation starters

### Model Providers

Choose from a wide range of AI model providers to power your agents. Current providers and models include:

* **Anthropic**: Claude Opus 4.7, Opus 4.6, Sonnet 4.6, Haiku 4.5
* **OpenAI**: GPT-5.5, GPT-5.4 (+ Mini / Nano / Pro), GPT-4.1
* **Google**: Gemini 3.1 Pro, Gemini 3.5 Flash, Gemini 3 Flash
* **xAI**: Grok 4-1 (+ Fast Reasoning / Non-reasoning)
* **Azure OpenAI**: Any deployed model

Models are referenced in the `provider:model-id` format (e.g. `anthropic:claude-sonnet-4-6`, `openai:gpt-5.5`). The model list changes as new models ship — see [Choosing a Model](/features/choosing-a-model) for the current identifiers, pricing, and guidance. Don't hardcode model IDs from memory.

### Integrations

Integrations allow your AI agents to connect with various external platforms and services, enhancing their capabilities and enabling seamless workflow automation. With the Aster Agents API, you can manage these integrations programmatically.

To manage integrations, you can use the following API operations:

* **List Integrations**: Retrieve a list of available integrations and their current connection status.
* **Connect Integration**: Establish a connection between an agent and a supported platform.
* **Disconnect Integration**: Remove an existing connection to prevent further access.
* **Update Integration Settings**: Modify the configuration of an existing integration to update permissions or settings.

Integrations are a powerful way to extend the functionality of your AI agents, allowing them to interact with external systems and data sources efficiently. By leveraging integrations, you can create more robust and capable AI-driven workflows.

### Agent Management

Use the API to create, update, and manage your agents. Key operations include:

* Creating new agents with specific configurations.
* Updating existing agents with new settings or capabilities.
* Managing agent performance and monitoring usage metrics.
* Integrating agents with enterprise platforms for enhanced functionality.