Your First Call

Make your first Zihin LLM call in under 5 minutes: create an API key, then POST to the public endpoint https://llm.zihin.ai/api/v3/llm/public/call with a query and model: "auto". The response returns the answer plus the model chosen, token usage, cost, and latency. Examples in curl, Node.js, and Python below.

1. Get Your API Key

1. Sign up at console.zihin.ai
2. Go to Settings > API Keys
3. Create a new key

Keys follow the format:

zhn_live_xxxxx  (production)
zhn_test_xxxxx  (sandbox)

2. Make Your First Call

curl

curl -X POST https://llm.zihin.ai/api/v3/llm/public/call \
  -H "X-Api-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "What is the capital of France?",
    "model": "auto"
  }'

Node.js

const response = await fetch('https://llm.zihin.ai/api/v3/llm/public/call', {
  method: 'POST',
  headers: {
    'X-Api-Key': 'YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    query: 'What is the capital of France?',
    model: 'auto',
  }),
});

const data = await response.json();
console.log(data.response);

Python

import requests

response = requests.post(
    "https://llm.zihin.ai/api/v3/llm/public/call",
    headers={
        "X-Api-Key": "YOUR_API_KEY",
        "Content-Type": "application/json",
    },
    json={
        "query": "What is the capital of France?",
        "model": "auto",
    },
)

data = response.json()
print(data["response"])

3. Response

{
  "success": true,
  "response": "The capital of France is Paris.",
  "model": "gpt-4o-mini",
  "provider": "openai",
  "usage": {
    "input_tokens": 15,
    "output_tokens": 8,
    "total_tokens": 23
  },
  "cost": 0.00015,
  "latency_ms": 450
}

Using Auto-Routing

Set model: "auto" to let the system automatically select the best model for your task:

{
  "query": "Write a Python function to sort a list",
  "model": "auto"
}

The system analyzes your prompt and routes to the optimal model based on:

• Task complexity
• Cost efficiency
• Response quality requirements

Next Steps

• Authentication — Learn about JWT and API keys
• Core Concepts — Understand tenants, models, and agents
• API Reference — Full API documentation
• Models — Available models and providers