Skip to main content

DeepSeek-V3.2 Now Available on iApp AI Gateway

· 3 min read
Kobkrit Viriyayudhakorn
Kobkrit Viriyayudhakorn
CEO @ iApp Technology

We are thrilled to announce that DeepSeek-V3.2, one of the most advanced open-source large language models, is now available through the iApp AI Gateway!

DeepSeek Logo

What is DeepSeek-V3.2?​

DeepSeek-V3.2 is the latest flagship model from DeepSeek AI, released on December 1, 2025. It represents a significant leap in reasoning capabilities and achieves gold-medal level performance on prestigious competitions including:

  • International Mathematical Olympiad (IMO)
  • Chinese Mathematical Olympiad (CMO)
  • ICPC World Finals
  • International Olympiad in Informatics (IOI) 2025

This makes it one of the most capable open-source models for complex reasoning tasks, rivaling proprietary models like GPT-4 and Claude Sonnet.

Key Features​

1. Advanced Reasoning Mode​

DeepSeek-V3.2 features a built-in "thinking mode" that shows explicit reasoning processes. When using the deepseek-reasoner model, you can see the model's step-by-step thought process before it provides the final answer.

2. 685 Billion Parameters​

With 685B parameters and a 128K context length, DeepSeek-V3.2 can handle complex, long-form documents and maintain coherent conversations across extensive contexts.

3. OpenAI-Compatible API​

Our integration is fully compatible with the OpenAI API format, making it easy to switch from other providers or integrate into existing applications.

4. Competitive Pricing​

We offer DeepSeek-V3.2 at highly competitive rates:

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

This is significantly more affordable than comparable proprietary models while delivering competitive performance.

Try It Now​

Experience DeepSeek-V3.2 directly in your browser:

Sign in to run this demo.

50 credits free on sign-up. No card.

Create a free accountLog in

Available Models​

ModelDescription
deepseek-reasonerThinking mode with explicit reasoning (recommended for complex tasks)
deepseek-chatNon-thinking mode for faster responses

Quick Start​

cURL Example​

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": "Explain quantum computing in simple terms."}
    ],
    "max_tokens": 4096,
    "temperature": 0.7
  }'

Python Example​

import requests

response = requests.post(
    'https://api.iapp.co.th/v3/llm/deepseek-3p2/chat/completions',
    headers={
        'apikey': 'YOUR_API_KEY',
        'Content-Type': 'application/json'
    },
    json={
        'model': 'deepseek-reasoner',
        'messages': [
            {'role': 'user', 'content': 'Explain quantum computing in simple terms.'}
        ],
        'max_tokens': 4096,
        'temperature': 0.7
    }
)
print(response.json())

Benchmark Performance​

DeepSeek-V3.2 delivers exceptional results across various benchmarks:

DeepSeek-V3.2 Benchmark Results

Get Started Today​

  1. Get your API Key: Visit API Key Management to obtain your API key
  2. Read the Documentation: Check our comprehensive DeepSeek-V3.2 API Documentation
  3. Start Building: Integrate DeepSeek-V3.2 into your applications

Learn More​

Questions? Join our Discord Community or email us at support@iapp.co.th.

iApp Technology Co., Ltd. Your Gateway to AI in Thailand