na{xx}en

Quickstart

Get naxxen compressing your LLM prompts in 3 minutes.

1. Sign up

Go to app.naxxen.ai and sign in with your email. You'll receive a magic link — click it to access your dashboard.

2. Create an API key

In the dashboard, go to API Keys and click Create API Key. Give it a name (e.g. "Development"). Copy the key — it starts with nxn-sk- and is shown only once.

3. Make your first request

Replace your provider's base URL with api.naxxen.ai. Pass your naxxen key via the X-Naxxen-Key header. Your provider API key stays in its normal header.

OpenAI example

curl -X POST https://api.naxxen.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-Naxxen-Key: nxn-sk-YOUR_KEY" \
  -H "Authorization: Bearer sk-YOUR_OPENAI_KEY" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant that provides detailed, thorough explanations about any topic the user asks about. You should always be polite and respectful in your responses. Make sure to consider multiple perspectives when answering questions."},
      {"role": "user", "content": "Hi"}
    ]
  }'

Anthropic example

curl -X POST https://api.naxxen.ai/v1/messages \
  -H "Content-Type: application/json" \
  -H "X-Naxxen-Key: nxn-sk-YOUR_KEY" \
  -H "x-api-key: sk-ant-YOUR_ANTHROPIC_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 100,
    "system": "You are a helpful assistant that provides detailed, thorough explanations.",
    "messages": [{"role": "user", "content": "Hi"}]
  }'

Google example

curl -X POST "https://api.naxxen.ai/v1/models/gemini-2.5-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "X-Naxxen-Key: nxn-sk-YOUR_KEY" \
  -H "x-goog-api-key: YOUR_GOOGLE_KEY" \
  -d '{
    "systemInstruction": {"parts": [{"text": "You are a helpful assistant that provides detailed, thorough explanations."}]},
    "contents": [{"role": "user", "parts": [{"text": "Hi"}]}]
  }'

4. Check your dashboard

Go back to app.naxxen.ai. You should see your request in the Usage page with a compression bar showing how many tokens were saved.

Next steps

  • Authentication — learn all 4 ways to pass your naxxen key (the URL path method is especially convenient for coding agents)
  • Compression — tune compression settings per API key
  • Integrations — configure your coding agent to use naxxen