Chat API

Endpoint

POST https://api.pandalink.ai/v1/chat/completions

Request Body

{
  "model": "qwen3-14b",           // Required: Model identifier
  "messages": [                  // Required: Array of message objects
    {
      "role": "user",             // "system", "user", or "assistant"
      "content": "Hello!"         // The message content
    }
  ],
  "temperature": 0.7,            // Optional: Sampling temperature (0-2)
  "max_tokens": 1000,            // Optional: Maximum tokens to generate
  "stream": false                // Optional: Enable streaming responses
}

Parameters

Response

{
  "id": "chatcmpl-abc123",
  "model": "qwen3-14b",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! How can I help you today?"
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 15,
    "total_tokens": 25
  }
}

Example Request

curl -X POST https://api.pandalink.ai/v1/chat/completions \
  -H "Authorization: Bearer ak_live_demo_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-14b",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is machine learning?"}
    ],
    "temperature": 0.7,
    "max_tokens": 500
  }'