Models
Aihubmix-MAI-DS-R1
Compare
Microsoft logo

Aihubmix-MAI-DS-R1

Microsoft
MAI-DS-R1 is a refined version of DeepSeek-R1 by Microsoft AI, designed to improve responsiveness to previously blocked topics while enhancing safety. It integrates 110k Tulu-3 SFT samples and 350k multilingual safety-alignment examples. The model retains strong reasoning and coding abilities, surpasses R1-1776 in handling sensitive queries, and reduces harmful content leakage. Based on a transformer MoE architecture, it suits general-purpose tasks—excluding legal, medical, or autonomous systems.

Pricing

  • Input Tokens: $0.6 /M tokens
  • Output Tokens: $1.8 /M tokens

Input Modalities

    Try this model

    Python
    import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AIHUBMIX_API_KEY"],
    base_url="https://shkq.org/v1",
)

response = client.chat.completions.create(
    model="Aihubmix-MAI-DS-R1",
    messages=[
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    max_tokens=1024,
    stream=False,
)

print(response.choices[0].message.content)

    Frequently asked questions

    What is Aihubmix-MAI-DS-R1?

    MAI-DS-R1 is a refined version of DeepSeek-R1 by Microsoft AI, designed to improve responsiveness to previously blocked topics while enhancing safety. It integrates 110k Tulu-3 SFT samples and 350k multilingual safety-alignment examples. The model retains strong reasoning and coding abilities, surpasses R1-1776 in handling sensitive queries, and reduces harmful content leakage. Based on a transformer MoE architecture, it suits general-purpose tasks—excluding legal, medical, or autonomous systems.

    © 2023 - 2026 AIHubMix, LLC

    Product

    Developer

    Connect

    Terms & Policies