OpenClaw

OpenClaw supports custom provider base URLs. You can create naxxen-proxied providers alongside your direct ones.

Configuration

Edit your OpenClaw config file (usually ~/.openclaw/openclaw.json). Add a provider for each LLM backend you want to proxy through naxxen.

The easiest method is the URL path prefix — embed your naxxen key in the base URL. OpenClaw sends the provider API key in headers as usual.

OpenAI via naxxen

{
  "name": "naxxen-openai",
  "baseUrl": "https://api.naxxen.ai/nxn-sk-YOUR_NAXXEN_KEY",
  "apiKey": "sk-proj-YOUR_OPENAI_KEY",
  "api": "openai-completions",
  "models": [
    { "id": "gpt-4o", "name": "GPT-4o (naxxen)" },
    { "id": "gpt-4o-mini", "name": "GPT-4o Mini (naxxen)" },
    { "id": "gpt-5.4", "name": "GPT-5.4 (naxxen)" }
  ]
}

Anthropic via naxxen

{
  "name": "naxxen-anthropic",
  "baseUrl": "https://api.naxxen.ai/nxn-sk-YOUR_NAXXEN_KEY",
  "apiKey": "sk-ant-YOUR_ANTHROPIC_KEY",
  "api": "anthropic-messages",
  "models": [
    { "id": "claude-sonnet-4-6", "name": "Claude Sonnet 4.6 (naxxen)" },
    { "id": "claude-opus-4-6", "name": "Claude Opus 4.6 (naxxen)" },
    { "id": "claude-haiku-4-5-20251001", "name": "Claude Haiku 4.5 (naxxen)" }
  ]
}

Google via naxxen

{
  "name": "naxxen-google",
  "baseUrl": "https://api.naxxen.ai/nxn-sk-YOUR_NAXXEN_KEY",
  "apiKey": "YOUR_GOOGLE_API_KEY",
  "api": "google-generative-ai",
  "models": [
    { "id": "gemini-2.5-flash", "name": "Gemini 2.5 Flash (naxxen)" },
    { "id": "gemini-2.5-pro", "name": "Gemini 2.5 Pro (naxxen)" }
  ]
}

How it works

OpenClaw sends requests to https://api.naxxen.ai/nxn-sk-YOUR_KEY/v1/chat/completions (or /v1/messages, etc.)
naxxen strips the key from the path, compresses the prompt, and forwards to the real provider
The response streams back through naxxen to OpenClaw

Your provider API key (apiKey field) is sent in the standard header for that provider and forwarded unchanged.

Verify

After configuring, make a request using one of your naxxen providers. Then check your dashboard — you should see the request with compression stats.

Set up with an AI agent

Copy this prompt and give it to your AI coding agent:

Read https://docs.naxxen.ai/llms.txt and configure naxxen as a proxy
for my OpenAI, Anthropic, and Google API calls in OpenClaw.
My naxxen key is nxn-sk-YOUR_KEY.
Add naxxen-openai, naxxen-anthropic, and naxxen-google providers
to my ~/.openclaw/openclaw.json config.