Skip to main content
Deploy and serve custom models with Baseten’s enterprise-grade infrastructure for ML model serving.

​
Configuration

Add these configurations to ~/.factory/config.json: 
{
  "custom_models": [
    {
      "model_display_name": "Qwen3-Coder-480B [Baseten]",
      "model": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
      "base_url": "https://inference.baseten.co/v1",
      "api_key": "YOUR_BASETEN_API_KEY",
      "provider": "generic-chat-completion-api",
      "max_tokens": 8192
    }
  ]
}

​
Getting Started

  1. Sign up at baseten.co
  2. Deploy a model from their model library or upload your own
  3. Get your API key from the settings page
  4. Find your model ID in the deployment dashboard
  5. Add the configuration to your Factory config

​
Notes

  • Base URL format: https://inference.baseten.co/v1
  • Replace YOUR_MODEL_ID with your deployed model’s ID from Baseten dashboard
  • Supports OpenAI-compatible API format
  • Contact Baseten for enterprise features and custom deployments
⌘I