Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.gmicloud.ai/llms.txt

Use this file to discover all available pages before exploring further.

Model ID 
deepseek-ai/DeepSeek-V3.2-Speciale
  1. DeepSeek Sparse Attention (DSA): We introduce DSA, an efficient attention mechanism that substantially reduces computational complexity while preserving model performance, specifically optimized for long-context scenarios.
  2. Scalable Reinforcement Learning Framework: By implementing a robust RL protocol and scaling post-training compute, DeepSeek-V3.2 performs comparably to GPT-5. Notably, our high-compute variant, DeepSeek-V3.2-Speciale, surpasses GPT-5 and exhibits reasoning proficiency on par with Gemini-3.0-Pro.
  • Achievement: 🥇 Gold-medal performance in the 2025 International Mathematical Olympiad (IMO) and International Olympiad in Informatics (IOI).
  1. Large-Scale Agentic Task Synthesis Pipeline: To integrate reasoning into tool-use scenarios, we developed a novel synthesis pipeline that systematically generates training data at scale. This facilitates scalable agentic post-training, improving compliance and generalization in complex interactive environments.

​
API Usage

You can interact with DeepSeek-V3.2 through the standard DeepSeek Chat Completions API endpoint.
Below are example usages for shell (cURL) and Python.

​
API Examples

​
Example 1: Basic Chat Completion

Generate a conversational response from DeepSeek-V3.2-Speciale.

​
Shell

curl --request POST \
  --url https://api.gmi-serving.com/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer *************' \
  --data '{
    "model": "deepseek-ai/DeepSeek-V3.2-Speciale",
    "messages": [
      {"role": "system", "content": "You are a helpful AI assistant"},
      {"role": "user", "content": "List 3 countries and their capitals."}
    ],
    "temperature": 0,
    "max_tokens": 500,
    "reasoning": {
      "enabled": true
    }
  }'

​
Python SDK usage

import requests
import json

url = "https://api.gmi-serving.com/v1/chat/completions"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer *************"
}

payload = {
    "model": "deepseek-ai/DeepSeek-V3.2-Speciale",
    "messages": [
        {"role": "system", "content": "You are a helpful AI assistant"},
        {"role": "user", "content": "List 3 countries and their capitals."}
    ],
    "temperature": 0,
    "max_tokens": 500
}

response = requests.post(url, headers=headers, json=payload)
print(json.dumps(response.json(), indent=2))