OpenHands Integration

OpenHands (formerly OpenDevin) is an open-source AI software development agent that can write code, run commands, browse the web, and interact with APIs. It provides a powerful coding assistant that can tackle complex multi-step development tasks autonomously.

OpenHands supports custom LLM providers through its settings, allowing you to connect LLM API as your AI backend.

Prerequisites

An LLM API account with an API key
OpenHands installed or accessible

Setup

Get Your LLM API Key

Log in to your LLM API dashboard
Click Create Key to Start
Copy your new API key immediately — it will only be shown once
Store the key securely (e.g., in a password manager or .env file)

LLM API is an OpenAI-compatible gateway that gives you access to dozens of AI models through a single API key and endpoint.

Configure LLM API in OpenHands

Open OpenHands in your browser.
Click the Settings icon (gear) in the interface.
Navigate to the "LLM Settings" section.
In the "LLM Provider" or "Model" dropdown, select "Custom" or enter a custom model string.
Fill in the following fields:
- API Key: paste the key you copied from app.llmapi.ai/api-keys
- Base URL: https://api.llmapi.ai/v1
- Model: the model ID you wish to use (e.g., openai/gpt-4o)
Click "Save" to apply the settings.

export LLM_API_KEY="your-llm-api-key-here"
export LLM_BASE_URL="https://api.llmapi.ai/v1"
export LLM_MODEL="openai/gpt-4o"

Test the Integration

Verify that OpenHands can successfully communicate with LLM API by sending a test request. All requests will now be routed through LLM API.

OpenHands reads LLM configuration from both its UI settings and environment variables. Environment variables take precedence if both are set.

Benefits of Using LLM API with OpenHands

Multi-Provider Access: Use models from OpenAI, Anthropic, Google, and more through a single API
Cost Control: Track and limit your AI spending with detailed usage analytics
Unified Billing: One account for all providers instead of managing multiple API keys
Caching: Reduce costs with response caching for repeated requests

View all available models on the models page.