Access 340+ AI Models for Free with a Single Smart Router API
A new API provider offers 10 million free tokens per month, unifying access to models like Claude Opus, GPT-5.5, and DeepSeek V4 into a single, cost-optimized endpoint for developers.
Practical Summary
Runtime by Bad Theory Labs provides a free-tier API that smartly routes requests to 340+ AI models. This tutorial covers the 2-minute signup process and how to configure any OpenAI-compatible tool (like Cursor or LangChain) to use this service, potentially eliminating the need for multiple $20/month subscriptions.
Why It Matters
For developers and businesses tracking AI costs, this represents a significant workflow optimization. It consolidates model access, reduces monthly software spend, and provides a practical method to test or integrate multiple frontier models without upfront financial commitment, though with noted usage limits.
How to Set Up Free Access to 340+ AI Models
This guide explains how to sign up for the Runtime API service and configure your tools to use its free tier, which includes 10 million tokens per month and smart routing across models.
Step 1: Create Your Account
Navigate to the sign-up page (linked in the source). You can register using a Google account; no credit card is required. Complete the brief onboarding form.
Step 2: Obtain Your API Key
After signing up, free credits are automatically applied to your dashboard. Locate and copy your unique API key, which will start with the prefix "BTL_".
Step 3: Configure Your Application
In any tool that supports an OpenAI-compatible API (e.g., Cursor, Aider, LangChain), change the base URL to the provided endpoint (https://runtime.badtheorylabs.com/v1). Set your API key to the one you copied. For smart, task-based model routing, use the model name "btl-2".
Important Considerations
This is a launch promotion, and the free tier may be reduced in the future. The service has rate limits and is not intended for heavy production workloads. Using the "btl-2" model is recommended for optimal value, as it automatically selects the best underlying model for each request.