Chinda Thai LLM 4B

FREE(until Dec 31, 2025)

Input: 0.00 IC / 1K tokens (~0.0 บาท/1M, ~$0.00/1M)

Output: 0.00 IC / 1K tokens (~0.0 บาท/1M, ~$0.00/1M)

v1.0 Active POST /v3/llm/chinda-thaillm-4b/chat/completions

Welcome to Chinda Thai LLM 4B API, an open-source Thai Large Language Model developed by iApp Technology in collaboration with AIEAT (AI Engineering Association of Thailand). Chinda is powered by the Qwen3 4B architecture, optimized for Thai language understanding and generation.

Try Demo

Chinda Thai LLM 4B Chat

API Key

Log in to use your API keys or Create an account

Start a conversation with the AI assistant

Type your message below and press Enter or click Send

สวัสดีครับ คุณช่วยอะไรได้บ้าง?

0 messages in conversationModel: chinda-qwen3-4b

Overview

Chinda (จินดา) is Thailand's first community-driven open-source LLM, designed to provide powerful Thai language AI capabilities. The model supports both streaming and non-streaming inference for chat completions.

Learn more about Chinda Open Source LLM

Key Features

• Thai-Optimized: Fine-tuned specifically for Thai language understanding and generation
• Open Source: Available for both API access and local deployment
• OpenAI Compatible: Follows OpenAI API format for easy integration
• Streaming Support: Real-time token streaming for responsive applications
• 40K Context: Supports up to 40,960 tokens context length
• Free Access: No cost until December 31, 2025

Getting Started

1. Prerequisites

   • An API key from iApp Technology
   • Internet connection

2. Quick Start

   • Simple REST API interface
   • OpenAI-compatible format
   • Both streaming and non-streaming support

3. Rate Limits

   • 5 requests per second
   • 200 requests per minute

How to get API Key?

Please visit API Key Management page to view your existing API key or request a new one.

API Endpoints

Endpoint	Method	Description	Cost
/v3/llm/chinda-thaillm-4b/chat/completions	POST	Chat completions (streaming & non-streaming)	FREE (0 IC)
/v3/llm/chinda-thaillm-4b/completions	POST	Text completions	FREE (0 IC)
/v3/llm/chinda-thaillm-4b/models	GET	List available models	FREE (0 IC)

Code Examples

cURL - Non-Streaming

curl -X POST 'https://api.iapp.co.th/v3/llm/chinda-thaillm-4b/chat/completions' \
  -H 'apikey: YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "chinda-qwen3-4b",
    "messages": [
      {"role": "user", "content": "สวัสดีครับ คุณช่วยอะไรได้บ้าง?"}
    ],
    "max_tokens": 4096
  }'

cURL - Streaming

curl -X POST 'https://api.iapp.co.th/v3/llm/chinda-thaillm-4b/chat/completions' \
  -H 'apikey: YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "chinda-qwen3-4b",
    "messages": [
      {"role": "user", "content": "อธิบายเกี่ยวกับ AI ให้หน่อย"}
    ],
    "max_tokens": 4096,
    "stream": true
  }'

Response (Non-Streaming)

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1700000000,
  "model": "chinda-qwen3-4b",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "สวัสดีครับ! ผมเป็น Chinda ผู้ช่วย AI ภาษาไทย ผมสามารถช่วยคุณได้หลายอย่าง เช่น:\n\n1. ตอบคำถามทั่วไป\n2. ช่วยเขียนข้อความ\n3. อธิบายเรื่องต่างๆ\n4. แปลภาษา\n5. ช่วยคิดไอเดีย\n\nมีอะไรให้ช่วยไหมครับ?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 89,
    "total_tokens": 104
  }
}

Python

import requests
import json

url = "https://api.iapp.co.th/v3/llm/chinda-thaillm-4b/chat/completions"

payload = {
    "model": "chinda-qwen3-4b",
    "messages": [
        {"role": "user", "content": "สวัสดีครับ คุณช่วยอะไรได้บ้าง?"}
    ],
    "max_tokens": 4096
}

headers = {
    'apikey': 'YOUR_API_KEY',
    'Content-Type': 'application/json'
}

response = requests.post(url, headers=headers, json=payload)
print(response.json())

Python - Streaming

import requests
import json

url = "https://api.iapp.co.th/v3/llm/chinda-thaillm-4b/chat/completions"

payload = {
    "model": "chinda-qwen3-4b",
    "messages": [
        {"role": "user", "content": "อธิบายเกี่ยวกับ AI"}
    ],
    "max_tokens": 4096,
    "stream": True
}

headers = {
    'apikey': 'YOUR_API_KEY',
    'Content-Type': 'application/json'
}

response = requests.post(url, headers=headers, json=payload, stream=True)

for line in response.iter_lines():
    if line:
        line = line.decode('utf-8')
        if line.startswith('data: '):
            data = line[6:]
            if data != '[DONE]':
                chunk = json.loads(data)
                content = chunk['choices'][0]['delta'].get('content', '')
                print(content, end='', flush=True)

JavaScript / Node.js

const axios = require('axios');

const url = 'https://api.iapp.co.th/v3/llm/chinda-thaillm-4b/chat/completions';

const payload = {
  model: 'chinda-qwen3-4b',
  messages: [
    { role: 'user', content: 'สวัสดีครับ คุณช่วยอะไรได้บ้าง?' }
  ],
  max_tokens: 4096
};

const config = {
  headers: {
    'apikey': 'YOUR_API_KEY',
    'Content-Type': 'application/json'
  }
};

axios.post(url, payload, config)
  .then(response => {
    console.log(response.data.choices[0].message.content);
  })
  .catch(error => {
    console.error(error);
  });

PHP

<?php

$curl = curl_init();

$payload = json_encode([
    'model' => 'chinda-qwen3-4b',
    'messages' => [
        ['role' => 'user', 'content' => 'สวัสดีครับ คุณช่วยอะไรได้บ้าง?']
    ],
    'max_tokens' => 4096
]);

curl_setopt_array($curl, [
    CURLOPT_URL => 'https://api.iapp.co.th/v3/llm/chinda-thaillm-4b/chat/completions',
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_POST => true,
    CURLOPT_POSTFIELDS => $payload,
    CURLOPT_HTTPHEADER => [
        'apikey: YOUR_API_KEY',
        'Content-Type: application/json'
    ],
]);

$response = curl_exec($curl);
curl_close($curl);

$result = json_decode($response, true);
echo $result['choices'][0]['message']['content'];

API Reference

Headers

Parameter	Type	Required	Description
apikey	String	Yes	Your API key
Content-Type	String	Yes	application/json

Request Body Parameters

Parameter	Type	Required	Description
model	String	Yes	Model name: chinda-qwen3-4b
messages	Array	Yes	Array of message objects with role and content
max_tokens	Integer	No	Maximum tokens to generate (default: 4096, max: 40960)
stream	Boolean	No	Enable streaming response (default: false)
temperature	Float	No	Sampling temperature 0-2 (default: 0.7)
top_p	Float	No	Nucleus sampling (default: 0.9)

Message Object

Field	Type	Description
role	String	system, user, or assistant
content	String	The message content

Model Information

Property	Value
Model Name	chinda-qwen3-4b
Base Model	Qwen3 4B
Context Length	40,960 tokens
Languages	Thai, English
License	Open Source

Use Cases

• Chatbots: Build Thai-speaking conversational AI assistants
• Content Generation: Generate Thai content for articles, social media, and marketing
• Translation: Translate between Thai and English
• Q&A Systems: Answer questions in Thai
• Code Assistance: Help with programming questions (with Thai explanations)
• Education: Thai language tutoring and explanations

Open Source

Chinda is also available as an open-source model that you can run locally:

• Hugging Face: iapp/chinda-qwen3-4b

For tutorials on running Chinda locally, see:

• LM Studio Tutorial
• Ollama Tutorial
• OpenWebUI Tutorial

Pricing

AI API Service Name	Endpoint	IC Cost	On-Premise
Chinda Thai LLM 4B [v1.0]	/v3/llm/chinda-thaillm-4b/chat/completions	FREE (until Dec 31, 2025) Input: 0.00 IC / 1K tokens Output: 0.00 IC / 1K tokens	Contact

Support

For support and questions:

• Discord: Join our community
• Email: support@iapp.co.th
• Documentation: Full API Docs