OpenRouter Integration

Access a wide range of AI models through a single, unified API

Overview

OpenRouter provides a unified API to access nearly all major language models available today. Through Compute Community, you can easily connect to OpenRouter and use their service to access a variety of models, including several high-quality options that are free to use.

Free models include high-quality options like Llama 3.3 70B and Gemini Flash, allowing you to experiment with powerful AI without any cost.

Setting Up OpenRouter

Follow these steps to access free and paid models through OpenRouter:

  1. Create an OpenRouter account

    Sign up for an account on the OpenRouter website if you don't already have one.

  2. Navigate to API Keys section

    Once logged in, go to the API Keys section in your OpenRouter dashboard.

  3. Generate a new API key

    Create a new API key. Note that you may need to have a payment method associated with your account or have credits on it, even if you plan to only use free models.

  4. Copy your API key

    Save your newly generated API key in a secure location.

  5. Configure a new host in Compute Community

    In Compute Community, add a new host with the following details:

    • URL: https://openrouter.ai/api
    • API Key: Your OpenRouter API key
  6. Access models from the sidebar

    After configuring the host, you'll be able to see all available OpenRouter models in the model selector on the sidebar.

  7. Filter for free models

    Use the toggle in the model selector to display only the free models available through OpenRouter.

Available Free Models

OpenRouter frequently updates their offering of free models. Some notable free models that may be available include:

  • Llama 3.3 70B
  • Gemini Flash
  • Various other models (selection may change over time)

The selection of free models may change based on OpenRouter's current promotions and partnerships.