DeepSeek R1 has been newly added to an Azure AI Foundry model catalog, whereby it becomes part of the diverse portfolio of over 1,800 models ranging from frontier, open-source, and industry-specific to task-based AI models. As part of Azure AI Foundry, DeepSeek R1 is available on a reliable, scalable, and enterprise-ready platform, enabling businesses to seamlessly integrate advanced AI while meeting SLA, security, and responsible AI commitments—backed by Microsoft’s trust and innovation.
Accelerating AI Logic for Developers on Azure AI Foundry
AI logic is becoming more accessible, enabling developers and enterprises to take advantage of cutting-edge intelligence in new ways. As DeepSeek notes, R1 provides a powerful, cost-effective model that allows more users to access advanced AI capabilities with minimal infrastructure investment. One of the key benefits of using DeepSeek R1 or any other model on Azure AI Foundry is the speed at which developers can experiment, iterate, and integrate AI into their workflows.
With built-in model evaluation tools, they can compare outputs, benchmark performance, and scale AI-powered applications. This fast access—which was unimaginable just a few months ago—is central to our vision for Azure AI Foundry: bringing the best AI models into one place to accelerate innovation and unlock new possibilities for enterprises worldwide.
Develop with Trustworthy AI
We are committed to enabling customers to rapidly build production-ready AI applications while maintaining the highest levels of security and safety. DeepSeek R1 has undergone rigorous red-teaming and security evaluations, including automated model behavior assessments and extensive security reviews to mitigate potential risks. With Azure AI’s content security, built-in content filtering is available by default, with opt-out options for flexibility. Additionally, the security assessment system allows customers to efficiently test their applications before deployment. These security measures help Azure AI Foundry provide enterprises with a safe, compliant, and responsible environment to deploy AI solutions with confidence.
How to Use DeepSeek in the Model Catalog
- If you don’t have an Azure subscription, you can sign up for an Azure account here.
- Search for DeepSeek R1 in the model catalog.
- Open the model card in the model catalog on Azure AI Foundry.
- Click on “Deploy” to get the prediction API and keys and access the playground.
- You should reach the deployment page in less than a minute, which will show you the API and keys. You can try your prompts in the playground.
- You can use the API and keys with different clients.
Get Started Today
DeepSeek R1 is now available through a serverless endpoint via the model catalog on Azure AI Foundry. Get started here on Azure AI Foundry and choose the DeepSeek model.
On GitHub, you can view additional resources and step-by-step guides for integrating DeepSeek R1 into your applications. Read the GitHub model blog post.
Coming Soon: Customers will soon be able to use distilled versions of DeepSeek R1 models on their Copilot+ PCs for local execution. Read the Windows Developer blog post.
As we continue to expand the model catalog on Azure AI Foundry, we are excited to see how developers and enterprises leverage DeepSeek R1 to address real-world challenges and deliver transformative experiences. We are committed to offering the most comprehensive portfolio of AI models, ensuring businesses of all sizes have access to cutting-edge tools to drive innovation and success.
