🤖 AI API Documentation

{
  "prompt": "Your question here",
  // OR
  "messages": [
    {"role": "user", "content": "Your message"}
  ]
}

{
  "success": true,
  "model": "qwen/qwen-2.5-coder-32b-instruct:free",
  "intent": "coding",
  "retryAttempt": 0,
  "response": "AI response text here...",
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 45,
    "total_tokens": 57
  }
}

Automatic Intent Detection

Intent	Trigger Keywords	Best For
Coding	python, javascript, function, api, debug, code, algorithm	Programming tasks, code generation, debugging
Math	calculus, equation, calculate, matrix, solve, derivative	Mathematical problems, calculations, formulas
Reasoning	analyze, explain, compare, logic, why, evaluate	Complex analysis, logical reasoning, comparisons
Creative	story, poem, creative, narrative, write, compose	Creative writing, storytelling, content generation
General	Default fallback	General questions and conversations

Available AI Models

Model	Specialty	Max Tokens
Qwen 2.5 Coder 32B	Code generation, debugging	4,096
DeepSeek Chat v3.1	Advanced coding, technical	8,192
DeepSeek R1	Reasoning, analysis, math	8,192
Llama 3.3 8B	General purpose, balanced	4,096
MiniMax M2	Creative writing, storytelling	8,192

Model Selection Features

• Health Monitoring: Circuit breaker disables failing models
• Auto Retry: Up to 3 attempts with exponential backoff
• Load Balancing: Health-aware round-robin distribution
• Fallback System: Emergency fallback if all models fail

cURL Examples

POST Request (Non-Streaming)

curl -X POST https://mutlimodel-ai-api.onrender.com/api/chat \
  -H "Content-Type: application/json" \
  -d '{"prompt": "Write a hello world in Python"}'

POST Request (Streaming)

curl -N -X POST https://mutlimodel-ai-api.onrender.com/api/chat/stream \
  -H "Content-Type: application/json" \
  -d '{"prompt": "Explain async/await"}'

GET Request

curl "https://mutlimodel-ai-api.onrender.com/api/chat?q=What+is+JavaScript"

JavaScript/Fetch Examples

Non-Streaming

const response = await fetch('/api/chat', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    prompt: 'Explain async/await in JavaScript'
  })
});

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

Streaming with Fetch

const response = await fetch('/api/chat/stream', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    prompt: 'Tell me a story'
  })
});

const reader = response.body.getReader();
const decoder = new TextDecoder();

while (true) {
  const { done, value } = await reader.read();
  if (done) break;
  
  const text = decoder.decode(value);
  console.log(text);
}

Python Example

import requests

response = requests.post('https://mutlimodel-ai-api.onrender.com/api/chat', 
    json={'prompt': 'Calculate 25 * 37'}
)

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

Node.js Example

const fetch = require('node-fetch');

async function chat() {
  const response = await fetch('https://mutlimodel-ai-api.onrender.com/api/chat', {
    method: 'POST',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify({
      prompt: 'Explain promises in JavaScript'
    })
  });
  
  const data = await response.json();
  console.log(data.response);
}

chat();