fix

Author: santiagxf

articles/ai-foundry/model-inference/concepts/models.md

@@ -17,6 +17,9 @@ ms.custom: references_regions, tool_generated
 
 Azure AI model inference in Azure AI Foundry gives you access to flagship models in Azure AI to consume them as APIs without hosting them on your infrastructure.
 
+> [!TIP]
+> DeepSeek-R1 is available for deployment as [Serverless API endpoint](../../ai-studio/how-to/deploy-models-deepseek.md).
+
 :::image type="content" source="../media/models/models-catalog.gif" alt-text="An animation showing Azure AI studio model catalog section and the models available." lightbox="../media/models/models-catalog.gif":::
 
 Model availability varies by model provider, deployment SKU, and cloud. All models available in Azure AI Model Inference support the [Global standard](deployment-types.md#global-standard) deployment type which uses global capacity to guarantee throughput. [Azure OpenAI models](#azure-openai) also support regional deployments and [sovereign clouds](/entra/identity-platform/authentication-national-cloud)—Azure Government, Azure Germany, and Azure China 21Vianet.

articles/ai-foundry/model-inference/overview.md

@@ -19,7 +19,7 @@ recommendations: false
 Azure AI model inference provides access to the most powerful models available in the Azure AI model catalog. The models come from key model providers in the industry, including OpenAI, Microsoft, Meta, Mistral, Cohere, G42, and AI21 Labs. These models can be integrated with software solutions to deliver a wide range of tasks that include content generation, summarization, image understanding, semantic search, and code generation.
 
 > [!TIP]
-> DeepSeek R1 is available for deployment as [Serverless API endpoint](../../ai-studio/how-to/deploy-models-serverless.md).
+> DeepSeek-R1 is available for deployment as [Serverless API endpoint](../../ai-studio/how-to/deploy-models-deepseek.md).
 
 Azure AI model inference provides a way to **consume models as APIs without hosting them on your infrastructure**. Models are hosted in a Microsoft-managed infrastructure, which enables API-based access to the model provider's model. API-based access can dramatically reduce the cost of accessing a model and simplify the provisioning experience.
 

articles/ai-studio/how-to/deploy-models-deepseek.md

@@ -14,11 +14,12 @@ ms.custom: references_regions, generated
 zone_pivot_groups: azure-ai-model-catalog-samples-chat
 ---
 
-# How to use DeepSeek-R1
+# How to use DeepSeek-R1 reasoning model (preview)
 
 [!INCLUDE [Feature preview](~/reusable-content/ce-skilling/azure/includes/ai-studio/includes/feature-preview.md)]
 
-In this article, you learn about DeepSeek-R1 and how to use them.
+In this article, you learn about DeepSeek-R1 and how to use it.
+
 DeepSeek-R1 excels at reasoning tasks using a step-by-step training process, such as language, scientific reasoning, and coding tasks. It features 671B total parameters with 37B active parameters, and 128k context length.
 
 ::: zone pivot="programming-language-python"
@@ -27,7 +28,7 @@ DeepSeek-R1 excels at reasoning tasks using a step-by-step training process, suc
 
 DeepSeek-R1 builds on the progress of earlier reasoning-focused models that improved performance by extending Chain-of-Thought (CoT) reasoning. DeepSeek-R1 takes things further by combining reinforcement learning (RL) with fine-tuning on carefully chosen datasets. It evolved from an earlier version, DeepSeek-R1-Zero, which relied solely on RL and showed strong reasoning skills but had issues like hard-to-read outputs and language inconsistencies. To address these limitations, DeepSeek-R1 incorporates a small amount of cold-start data and follows a refined training pipeline that blends reasoning-oriented RL with supervised fine-tuning on curated datasets, resulting in a model that achieves state-of-the-art performance on reasoning benchmarks.
 
-You can learn more about the models in their respective model card:
+You can learn more about the models in its respective model card:
 
 * [DeepSeek-R1](https://aka.ms/azureai/landing/DeepSeek-R1)
 
@@ -177,7 +178,6 @@ def print_stream(result):
     """
     Prints the chat completion with streaming.
     """
-    import time
     for update in result:
         if update.choices:
             print(update.choices[0].delta.content, end="")

articles/ai-studio/reference/reference-model-inference-api.md

@@ -43,6 +43,7 @@ Models deployed to [serverless API endpoints](../how-to/deploy-models-serverless
 > [!div class="checklist"]
 > * [Cohere Embed V3](../how-to/deploy-models-cohere-embed.md) family of models
 > * [Cohere Command R](../how-to/deploy-models-cohere-command.md) family of models
+> * [DeepSeek-R1](../how-to/deploy-models-deepseek.md) family of models
 > * [Meta Llama 2 chat](../how-to/deploy-models-llama.md) family of models
 > * [Meta Llama 3 instruct](../how-to/deploy-models-llama.md) family of models
 > * [Mistral-Small](../how-to/deploy-models-mistral.md)