OpenBlock Labs Integration

OB-1 by Open Block Labs is a multi-model, terminal-based coding agent that supports over 300 AI models. It features bring-your-own-API-key functionality, self-optimizing workflows, and session forking, making it a versatile tool for AI-assisted development.

OB-1 supports OpenAI-compatible providers, allowing you to connect LLM API and access all available models from the terminal.

Prerequisites

An LLM API account with an API key
OpenBlock Labs 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 OB-1

Open your terminal and launch OB-1.
Open the settings file at ~/.ob1/settings.json (or use the /model command in OB-1).
Set the following environment variables:

export OPENAI_API_KEY="your-llm-api-key-here"
export OPENAI_BASE_URL="https://api.llmapi.ai/v1"

Alternatively, configure in ~/.ob1/settings.json:

{
	"apiKey": "your-llm-api-key-here",
	"apiBase": "https://api.llmapi.ai/v1",
	"model": "openai/gpt-4o"
}

Use the /model command to switch between models at any time.

Test the Integration

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

Use /model auto to let OB-1 intelligently route tasks to the optimal model based on complexity.

Benefits of Using LLM API with OpenBlock Labs

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.