MAI-DS-R1

MAI-DS-R1 is a post-trained variant of DeepSeek-R1 developed by the Microsoft AI team to improve the model’s responsiveness on previously blocked topics while enhancing its safety profile. Built on top of DeepSeek-R1’s reasoning foundation, it integrates 110k examples from the Tulu-3 SFT dataset and 350k internally curated multilingual safety-alignment samples. The model retains strong reasoning, coding, and problem-solving capabilities, while unblocking a wide range of prompts previously restricted in R1. MAI-DS-R1 demonstrates improved performance on harm mitigation benchmarks and maintains competitive results across general reasoning tasks. It surpasses R1-1776 in satisfaction metrics for blocked queries and reduces leakage in harmful content categories. The model is based on a transformer MoE architecture and is suitable for general-purpose use cases, excluding high-stakes domains such as legal, medical, or autonomous systems.

Available at 4 Providers

	Provider	Model Name	Original Model	Input ($/1M)	Output ($/1M)	Free
	GitHub Models	MAI-DS-R1	microsoft/mai-ds-r1	$0.00	$0.00		Visit
	Azure OpenAI	MAI-DS-R1	mai-ds-r1	$1.35	$5.40		Visit
	Azure AI Services	MAI-DS-R1	mai-ds-r1	$1.35	$5.40		Visit
	LangDB	mai-ds-r1	mai-ds-r1	-	-