Skip to main content
Access high-performance inference for open-source models with Fireworks AI’s optimized serving infrastructure.

​
Configuration

Configuration examples for ~/.factory/config.json: 
{
  "custom_models": [
    {
      "model_display_name": "GLM 4.5 [Fireworks]",
      "model": "accounts/fireworks/models/glm-4p5",
      "base_url": "https://api.fireworks.ai/inference/v1",
      "api_key": "YOUR_FIREWORKS_API_KEY",
      "provider": "generic-chat-completion-api",
      "max_tokens": 16384
    },
    {
      "model_display_name": "Deepseek V3.1 Terminus [Fireworks]",
      "model": "accounts/fireworks/models/deepseek-v3p1-terminus",
      "base_url": "https://api.fireworks.ai/inference/v1",
      "api_key": "YOUR_FIREWORKS_API_KEY",
      "provider": "generic-chat-completion-api",
      "max_tokens": 20480
    }
  ]
}

​
Getting Started

  1. Sign up at fireworks.ai
  2. Get your API key from the dashboard
  3. Browse available models in their model catalog
  4. Add desired models to your configuration

​
Notes

  • Base URL format: https://api.fireworks.ai/inference/v1
  • Model IDs typically start with accounts/fireworks/models/
  • Supports streaming responses and function calling for compatible models