DeepSeek-V3.2 NEW

Powered by DeepSeek AI

Token-Based Pricing

Input: 0.01 IC / 1K tokens (~10 THB/1M, ~$0.30/1M)Output: 0.02 IC / 1K tokens (~20 THB/1M, ~$0.60/1M)

v3.2 Active POST /v3/llm/deepseek-3p2/chat/completions

Welcome to iApp DeepSeek-V3.2 API, powered by the latest DeepSeek-V3.2 model. This API provides access to one of the most advanced open-source large language models with exceptional reasoning capabilities, competitive performance against GPT-4 and Claude Sonnet, and full OpenAI-compatible interface.

Benchmark Results

DeepSeek-V3.2 delivers competitive performance across multiple benchmarks:

Key Performance Highlights

• 685B Parameters: Massive model with state-of-the-art capabilities
• 128K Context Length: Extended context window for long documents
• Reasoning Mode: Built-in chain-of-thought reasoning with deepseek-reasoner model
• OpenAI Compatible: Drop-in replacement for OpenAI API
• Gold Medal Performance: Achieves gold-medal level on International Mathematical Olympiad (IMO) and International Olympiad in Informatics (IOI)

Try Demo

DeepSeek-V3.2 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: deepseek-reasoner

Overview

DeepSeek-V3.2 represents an advanced reasoning-focused model designed to harmonize high computational efficiency with superior reasoning and agent performance. It introduces three core innovations:

1. DeepSeek Sparse Attention (DSA): An efficient attention mechanism reducing computational complexity while maintaining performance for extended contexts
2. Scalable Reinforcement Learning Framework: Post-training approach for enhanced reasoning capabilities
3. Agentic Task Synthesis Pipeline: Integrates reasoning capabilities into tool-use scenarios

Key Features

• Advanced Reasoning: Built-in thinking mode with explicit reasoning process
• OpenAI Compatible: Follows OpenAI API format for easy integration
• Streaming Support: Real-time token streaming for responsive applications
• 128K Context: Supports up to 128,000 tokens context length
• Thai & English: Supports both Thai and English languages
• Cost Effective: Competitive pricing for enterprise-grade AI

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/deepseek-3p2/chat/completions	POST	Chat completions (streaming & non-streaming)	0.01 IC/1K input + 0.02 IC/1K output

Available Models

Model	Description
deepseek-reasoner	Thinking mode with explicit reasoning (recommended)
deepseek-chat	Non-thinking mode for faster responses

Code Examples

cURL - Non-Streaming

curl -X POST 'https://api.iapp.co.th/v3/llm/deepseek-3p2/chat/completions' \
  -H 'apikey: YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "deepseek-reasoner",
    "messages": [
      {"role": "user", "content": "สวัสดีครับ คุณช่วยอะไรได้บ้าง?"}
    ],
    "max_tokens": 4096,
    "temperature": 0.7,
    "top_p": 0.9
  }'

cURL - Streaming

curl -X POST 'https://api.iapp.co.th/v3/llm/deepseek-3p2/chat/completions' \
  -H 'apikey: YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "deepseek-reasoner",
    "messages": [
      {"role": "user", "content": "สวัสดีครับ คุณช่วยอะไรได้บ้าง?"}
    ],
    "max_tokens": 4096,
    "temperature": 0.7,
    "top_p": 0.9,
    "stream": true
  }'

Response (Non-Streaming with Reasoning)

When using deepseek-reasoner, the response includes a reasoning_content field showing the model's thinking process:

{
  "id": "233c1fa8-e6ea-4b4f-86b5-2bbccb39fd9e",
  "object": "chat.completion",
  "created": 1764635256,
  "model": "deepseek-reasoner",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello there! How can I assist you today?",
        "reasoning_content": "Hmm, the user just greeted me with \"Hello!\". This is a straightforward opening greeting, so I should respond warmly and invitingly. I can start with a cheerful \"Hello there!\" to mirror their friendly tone, then offer my assistance to encourage them to share what they need. Keeping it simple and open-ended works best here since they haven't specified a request yet."
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 109,
    "total_tokens": 121,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 96
    },
    "prompt_cache_hit_tokens": 0,
    "prompt_cache_miss_tokens": 12
  },
  "system_fingerprint": "fp_eaab8d114b_prod0820_fp8_kvcache"
}

Python

import requests
import json

url = "https://api.iapp.co.th/v3/llm/deepseek-3p2/chat/completions"

payload = {
    "model": "deepseek-reasoner",
    "messages": [
        {"role": "user", "content": "สวัสดีครับ คุณช่วยอะไรได้บ้าง?"}
    ],
    "max_tokens": 4096,
    "temperature": 0.7,
    "top_p": 0.9
}

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/deepseek-3p2/chat/completions"

payload = {
    "model": "deepseek-reasoner",
    "messages": [
        {"role": "user", "content": "อธิบายเกี่ยวกับ AI ให้หน่อย"}
    ],
    "max_tokens": 4096,
    "temperature": 0.7,
    "top_p": 0.9,
    "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/deepseek-3p2/chat/completions';

const payload = {
  model: 'deepseek-reasoner',
  messages: [
    { role: 'user', content: 'สวัสดีครับ คุณช่วยอะไรได้บ้าง?' }
  ],
  max_tokens: 4096,
  temperature: 0.7,
  top_p: 0.9
};

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' => 'deepseek-reasoner',
    'messages' => [
        ['role' => 'user', 'content' => 'สวัสดีครับ คุณช่วยอะไรได้บ้าง?']
    ],
    'max_tokens' => 4096,
    'temperature' => 0.7,
    'top_p' => 0.9
]);

curl_setopt_array($curl, [
    CURLOPT_URL => 'https://api.iapp.co.th/v3/llm/deepseek-3p2/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: deepseek-reasoner or deepseek-chat
messages	Array	Yes	Array of message objects with role and content
max_tokens	Integer	No	Maximum tokens to generate (default: 4096, max: 128000)
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

Response Fields

Field	Type	Description
content	String	The generated response
reasoning_content	String	(deepseek-reasoner only) The reasoning process

Recommended Temperature Settings

Use Case	Temperature
Coding / Math	0.0
Data Analysis	1.0
General Conversation	1.3
Translation	1.3
Creative Writing	1.5

Model Information

Property	Value
Model Name	deepseek-reasoner / deepseek-chat
Base Model	DeepSeek-V3.2
Parameters	685B
Context Length	128,000 tokens
Languages	Thai, English, Chinese, and more
License	MIT

Use Cases

• Advanced Reasoning: Complex problem-solving, mathematical proofs, logical deduction
• Coding Assistance: Code generation, debugging, code explanation
• Content Generation: Articles, reports, creative writing in multiple languages
• Translation: High-quality translation between Thai, English, and other languages
• Q&A Systems: Intelligent question answering with reasoning capabilities
• Data Analysis: Data interpretation and insights generation

Pricing

AI API Service Name	Endpoint	IC Cost	On-Premise
DeepSeek-V3.2 [v3.2]	/v3/llm/deepseek-3p2/chat/completions	Input: 0.01 IC / 1K tokens (~10 THB/1M, ~$0.30/1M) Output: 0.02 IC / 1K tokens (~20 THB/1M, ~$0.60/1M)	Contact

Support

For support and questions:

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