Intelligent
AI Gateway

Enterprise-grade proxy for large language model inference. Secure, fast, and built for scale.

Try It System Status Zithera Platform

Available Models

Local LLM inference — no cloud costs, full privacy

Loading models...

API Endpoints

Integrate with your application using these endpoints

POST

/api/chat

Send a conversation with message history and get a response.

// Headers
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

// Request body
{
  "model": "qwen3:8b",
  "messages": [
    { "role": "user", "content": "Hello!" }
  ]
}

// Response
{
  "model": "qwen3:8b",
  "message": {
    "role": "assistant",
    "content": "Hi there!"
  },
  "done": true
}

POST

/api/generate

Send a single prompt and get a text completion.

// Headers
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

// Request body
{
  "model": "qwen3:8b",
  "prompt": "Explain AI in one sentence."
}

// Response
{
  "model": "qwen3:8b",
  "response": "AI is...",
  "done": true
}

All endpoints require an API key via Authorization: Bearer or X-API-Key header

Authenticated Access

SHA-256 hashed API keys with multiple auth methods.

Rate Protected

Per-key throttling with configurable request limits.

Full Audit Trail