Skip to main content

OpenAI

KhunQuant connects to OpenAI (and any OpenAI-compatible endpoint) via the openai_compat/ provider. This covers OpenAI, Azure OpenAI, LiteLLM, OpenRouter, Groq, and others that implement the OpenAI chat completions API.

Configuration​

Add to ~/.khunquant/config.json:

{
  "model_list": [
    {
      "model_name": "gpt4o",
      "model": "gpt-4o",
      "api_key": "OPENAI_API_KEY"
    }
  ]
}

Add the API key to ~/.khunquant/.security.yml:

model_list:
  - model_name: gpt4o
    api_key: "sk-..."

Azure OpenAI​

Use api_base to point to your Azure deployment:

{
  "model_list": [
    {
      "model_name": "azure-gpt4",
      "model": "gpt-4o",
      "api_base": "https://your-resource.openai.azure.com/openai/deployments/your-deployment",
      "api_key": "AZURE_OPENAI_KEY",
      "auth_method": "azure"
    }
  ]
}

OpenAI-compatible endpoints​

Any endpoint implementing the OpenAI chat completions format works:

{
  "model_list": [
    {
      "model_name": "groq-llama",
      "model": "llama-3.1-70b-versatile",
      "api_base": "https://api.groq.com/openai/v1",
      "api_key": "GROQ_API_KEY"
    },
    {
      "model_name": "openrouter",
      "model": "anthropic/claude-sonnet-4-6",
      "api_base": "https://openrouter.ai/api/v1",
      "api_key": "OPENROUTER_API_KEY"
    }
  ]
}