How to use DeepSeek-R1 reasoning model
Important
Items marked (preview) in this article are currently in public preview. This preview is provided without a service-level agreement, and we don't recommend it for production workloads. Certain features might not be supported or might have constrained capabilities. For more information, see Supplemental Terms of Use for Microsoft Azure Previews.
In this article, you learn about DeepSeek-R1 and how to use them. 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.
DeepSeek-R1
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:
Prerequisites
To use DeepSeek-R1 with Azure AI Foundry, you need the following prerequisites:
A model deployment
Deployment to serverless APIs
DeepSeek-R1 can be deployed to serverless API endpoints with pay-as-you-go billing. This kind of deployment provides a way to consume models as an API without hosting them on your subscription, while keeping the enterprise security and compliance that organizations need.
Deployment to a serverless API endpoint doesn't require quota from your subscription. If your model isn't deployed already, use the Azure AI Studio, Azure Machine Learning SDK for Python, the Azure CLI, or ARM templates to deploy the model as a serverless API.
The inference package installed
You can consume predictions from this model by using the azure-ai-inference package with Python. To install this package, you need the following prerequisites:
- Python 3.8 or later installed, including pip.
- The endpoint URL. To construct the client library, you need to pass in the endpoint URL. The endpoint URL has the form
https://your-host-name.your-azure-region.inference.ai.azure.com, whereyour-host-nameis your unique model deployment host name andyour-azure-regionis the Azure region where the model is deployed (for example, eastus2). - Depending on your model deployment and authentication preference, you need either a key to authenticate against the service, or Microsoft Entra ID credentials. The key is a 32-character string.
Once you have these prerequisites, install the Azure AI inference package with the following command:
pip install azure-ai-inference
Read more about the Azure AI inference package and reference.
Work with chat completions
In this section, you use the Azure AI model inference API with a chat completions model for chat.
Tip
The Azure AI model inference API allows you to talk with most models deployed in Azure AI Foundry with the same code and structure, including DeepSeek-R1.
Create a client to consume the model
First, create the client to consume the model. The following code uses an endpoint URL and key that are stored in environment variables.
import os
from azure.ai.inference import ChatCompletionsClient
from azure.core.credentials import AzureKeyCredential
client = ChatCompletionsClient(
endpoint=os.environ["AZURE_INFERENCE_ENDPOINT"],
credential=AzureKeyCredential(os.environ["AZURE_INFERENCE_CREDENTIAL"]),
)
Get the model's capabilities
The /info route returns information about the model that is deployed to the endpoint. Return the model's information by calling the following method:
model_info = client.get_model_info()
The response is as follows:
print("Model name:", model_info.model_name)
print("Model type:", model_info.model_type)
print("Model provider name:", model_info.model_provider_name)
Model name: DeepSeek-R1
Model type: chat-completions
Model provider name: DeepSeek
Create a chat completion request
The following example shows how you can create a basic chat completions request to the model.
from azure.ai.inference.models import SystemMessage, UserMessage
response = client.complete(
messages=[
SystemMessage(content="You are a helpful assistant."),
UserMessage(content="How many languages are in the world?"),
],
)
The response is as follows, where you can see the model's usage statistics:
print("Response:", response.choices[0].message.content)
print("Model:", response.model)
print("Usage:")
print("\tPrompt tokens:", response.usage.prompt_tokens)
print("\tTotal tokens:", response.usage.total_tokens)
print("\tCompletion tokens:", response.usage.completion_tokens)
Response: As of now, it's estimated that there are about 7,000 languages spoken around the world. However, this number can vary as some languages become extinct and new ones develop. It's also important to note that the number of speakers can greatly vary between languages, with some having millions of speakers and others only a few hundred.
Model: DeepSeek-R1
Usage:
Prompt tokens: 19
Total tokens: 91
Completion tokens: 72
Inspect the usage section in the response to see the number of tokens used for the prompt, the total number of tokens generated, and the number of tokens used for the completion.
Understanding reasoning
Some reasoning models, like DeepSeek-R1, generate completions and include the reasoning behind it. The reasoning associated with the completion is included in the response's content within the tags <think> and </think>. The model may select on which scenarios to generate reasoning content. For example:
response = client.complete(
messages=[
SystemMessage(content="You are a helpful assistant."),
UserMessage(content="How many languages are in the world?"),
],
)
You can extract the reasoning content from the response to understand the model's thought process as follows:
import re
match = re.match(r"<think>(.*?)</think>(.*)", response.choices[0].message.content, re.DOTALL)
print("Response:", )
if match:
print("\tThinking:", match.group(1))
print("\tAnswer:", match.group(2))
else:
print("\tAnswer:", response.choices[0].message.content)
print("Model:", response.model)
print("Usage:")
print("\tPrompt tokens:", response.usage.prompt_tokens)
print("\tTotal tokens:", response.usage.total_tokens)
print("\tCompletion tokens:", response.usage.completion_tokens)
Thinking: Okay, the user is asking how many languages exist in the world. I need to provide a clear and accurate answer. Let's start by recalling the general consensus from linguistic sources. I remember that the number often cited is around 7,000, but maybe I should check some reputable organizations.\n\nEthnologue is a well-known resource for language data, and I think they list about 7,000 languages. But wait, do they update their numbers? It might be around 7,100 or so. Also, the exact count can vary because some sources might categorize dialects differently or have more recent data. \n\nAnother thing to consider is language endangerment. Many languages are endangered, with some having only a few speakers left. Organizations like UNESCO track endangered languages, so mentioning that adds context. Also, the distribution isn't even. Some countries have hundreds of languages, like Papua New Guinea with over 800, while others have just a few. \n\nA user might also wonder why the exact number is hard to pin down. It's because the distinction between a language and a dialect can be political or cultural. For example, Mandarin and Cantonese are considered dialects of Chinese by some, but they're mutually unintelligible, so others classify them as separate languages. Also, some regions are under-researched, making it hard to document all languages. \n\nI should also touch on language families. The 7,000 languages are grouped into families like Indo-European, Sino-Tibetan, Niger-Congo, etc. Maybe mention a few of the largest families. But wait, the question is just about the count, not the families. Still, it's good to provide a bit more context. \n\nI need to make sure the information is up-to-date. Let me think – recent estimates still hover around 7,000. However, languages are dying out rapidly, so the number decreases over time. Including that note about endangerment and language extinction rates could be helpful. For instance, it's often stated that a language dies every few weeks. \n\nAnother point is sign languages. Does the count include them? Ethnologue includes some, but not all sources might. If the user is including sign languages, that adds more to the count, but I think the 7,000 figure typically refers to spoken languages. For thoroughness, maybe mention that there are also over 300 sign languages. \n\nSummarizing, the answer should state around 7,000, mention Ethnologue's figure, explain why the exact number varies, touch on endangerment, and possibly note sign languages as a separate category. Also, a brief mention of Papua New Guinea as the most linguistically diverse country. \n\nWait, let me verify Ethnologue's current number. As of their latest edition (25th, 2022), they list 7,168 living languages. But I should check if that's the case. Some sources might round to 7,000. Also, SIL International publishes Ethnologue, so citing them as reference makes sense. \n\nOther sources, like Glottolog, might have a different count because they use different criteria. Glottolog might list around 7,000 as well, but exact numbers vary. It's important to highlight that the count isn't exact because of differing definitions and ongoing research. \n\nIn conclusion, the approximate number is 7,000, with Ethnologue being a key source, considerations of endangerment, and the challenges in counting due to dialect vs. language distinctions. I should make sure the answer is clear, acknowledges the variability, and provides key points succinctly.
Answer: The exact number of languages in the world is challenging to determine due to differences in definitions (e.g., distinguishing languages from dialects) and ongoing documentation efforts. However, widely cited estimates suggest there are approximately **7,000 languages** globally.
Model: DeepSeek-R1
Usage:
Prompt tokens: 11
Total tokens: 897
Completion tokens: 886
Stream content
By default, the completions API returns the entire generated content in a single response. If you're generating long completions, waiting for the response can take many seconds.
You can stream the content to get it as it's being generated. Streaming content allows you to start processing the completion as content becomes available. This mode returns an object that streams back the response as data-only server-sent events. Extract chunks from the delta field, rather than the message field.
result = client.complete(
messages=[
SystemMessage(content="You are a helpful assistant."),
UserMessage(content="How many languages are in the world?"),
],
temperature=0,
top_p=1,
max_tokens=2048,
stream=True,
)
To stream completions, set stream=True when you call the model.
To visualize the output, define a helper function to print the stream.
def print_stream(result):
"""
Prints the chat completion with streaming.
"""
for update in result:
if update.choices:
print(update.choices[0].delta.content, end="")
You can visualize how streaming generates content:
print_stream(result)
Apply content safety
The Azure AI model inference API supports Azure AI content safety. When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
from azure.ai.inference.models import AssistantMessage, UserMessage, SystemMessage
try:
response = client.complete(
messages=[
SystemMessage(content="You are an AI assistant that helps people find information."),
UserMessage(content="Chopping tomatoes and cutting them into cubes or wedges are great ways to practice your knife skills."),
]
)
print(response.choices[0].message.content)
except HttpResponseError as ex:
if ex.status_code == 400:
response = ex.response.json()
if isinstance(response, dict) and "error" in response:
print(f"Your request triggered an {response['error']['code']} error:\n\t {response['error']['message']}")
else:
raise
raise
Tip
To learn more about how you can configure and control Azure AI content safety settings, check the Azure AI content safety documentation.
DeepSeek-R1
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:
Prerequisites
To use DeepSeek-R1 with Azure AI Foundry, you need the following prerequisites:
A model deployment
Deployment to serverless APIs
DeepSeek-R1 can be deployed to serverless API endpoints with pay-as-you-go billing. This kind of deployment provides a way to consume models as an API without hosting them on your subscription, while keeping the enterprise security and compliance that organizations need.
Deployment to a serverless API endpoint doesn't require quota from your subscription. If your model isn't deployed already, use the Azure AI Studio, Azure Machine Learning SDK for Python, the Azure CLI, or ARM templates to deploy the model as a serverless API.
The inference package installed
You can consume predictions from this model by using the @azure-rest/ai-inference package from npm. To install this package, you need the following prerequisites:
- LTS versions of
Node.jswithnpm. - The endpoint URL. To construct the client library, you need to pass in the endpoint URL. The endpoint URL has the form
https://your-host-name.your-azure-region.inference.ai.azure.com, whereyour-host-nameis your unique model deployment host name andyour-azure-regionis the Azure region where the model is deployed (for example, eastus2). - Depending on your model deployment and authentication preference, you need either a key to authenticate against the service, or Microsoft Entra ID credentials. The key is a 32-character string.
Once you have these prerequisites, install the Azure Inference library for JavaScript with the following command:
npm install @azure-rest/ai-inference
Work with chat completions
In this section, you use the Azure AI model inference API with a chat completions model for chat.
Tip
The Azure AI model inference API allows you to talk with most models deployed in Azure AI Foundry with the same code and structure, including DeepSeek-R1.
Create a client to consume the model
First, create the client to consume the model. The following code uses an endpoint URL and key that are stored in environment variables.
import ModelClient from "@azure-rest/ai-inference";
import { isUnexpected } from "@azure-rest/ai-inference";
import { AzureKeyCredential } from "@azure/core-auth";
const client = new ModelClient(
process.env.AZURE_INFERENCE_ENDPOINT,
new AzureKeyCredential(process.env.AZURE_INFERENCE_CREDENTIAL)
);
Get the model's capabilities
The /info route returns information about the model that is deployed to the endpoint. Return the model's information by calling the following method:
var model_info = await client.path("/info").get()
The response is as follows:
console.log("Model name: ", model_info.body.model_name)
console.log("Model type: ", model_info.body.model_type)
console.log("Model provider name: ", model_info.body.model_provider_name)
Model name: DeepSeek-R1
Model type: chat-completions
Model provider name: DeepSeek
Create a chat completion request
The following example shows how you can create a basic chat completions request to the model.
var messages = [
{ role: "system", content: "You are a helpful assistant" },
{ role: "user", content: "How many languages are in the world?" },
];
var response = await client.path("/chat/completions").post({
body: {
messages: messages,
}
});
The response is as follows, where you can see the model's usage statistics:
if (isUnexpected(response)) {
throw response.body.error;
}
console.log("Response: ", response.body.choices[0].message.content);
console.log("Model: ", response.body.model);
console.log("Usage:");
console.log("\tPrompt tokens:", response.body.usage.prompt_tokens);
console.log("\tTotal tokens:", response.body.usage.total_tokens);
console.log("\tCompletion tokens:", response.body.usage.completion_tokens);
Response: As of now, it's estimated that there are about 7,000 languages spoken around the world. However, this number can vary as some languages become extinct and new ones develop. It's also important to note that the number of speakers can greatly vary between languages, with some having millions of speakers and others only a few hundred.
Model: DeepSeek-R1
Usage:
Prompt tokens: 19
Total tokens: 91
Completion tokens: 72
Inspect the usage section in the response to see the number of tokens used for the prompt, the total number of tokens generated, and the number of tokens used for the completion.
Understanding reasoning
Some reasoning models, like DeepSeek-R1, generate completions and include the reasoning behind it. The reasoning associated with the completion is included in the response's content within the tags <think> and </think>. The model may select on which scenarios to generate reasoning content. For example:
var messages = [
{ role: "system", content: "You are a helpful assistant" },
{ role: "user", content: "How many languages are in the world?" },
];
var response = await client.path("/chat/completions").post({
body: {
messages: messages,
}
});
You can extract the reasoning content from the response to understand the model's thought process as follows:
var content = response.body.choices[0].message.content
var match = content.match(/<think>(.*?)<\/think>(.*)/s);
console.log("Response:");
if (match) {
console.log("\tThinking:", match[1]);
console.log("\Answer:", match[2]);
}
else {
console.log("Response:", content);
}
console.log("Model: ", response.body.model);
console.log("Usage:");
console.log("\tPrompt tokens:", response.body.usage.prompt_tokens);
console.log("\tTotal tokens:", response.body.usage.total_tokens);
console.log("\tCompletion tokens:", response.body.usage.completion_tokens);
Thinking: Okay, the user is asking how many languages exist in the world. I need to provide a clear and accurate answer. Let's start by recalling the general consensus from linguistic sources. I remember that the number often cited is around 7,000, but maybe I should check some reputable organizations.\n\nEthnologue is a well-known resource for language data, and I think they list about 7,000 languages. But wait, do they update their numbers? It might be around 7,100 or so. Also, the exact count can vary because some sources might categorize dialects differently or have more recent data. \n\nAnother thing to consider is language endangerment. Many languages are endangered, with some having only a few speakers left. Organizations like UNESCO track endangered languages, so mentioning that adds context. Also, the distribution isn't even. Some countries have hundreds of languages, like Papua New Guinea with over 800, while others have just a few. \n\nA user might also wonder why the exact number is hard to pin down. It's because the distinction between a language and a dialect can be political or cultural. For example, Mandarin and Cantonese are considered dialects of Chinese by some, but they're mutually unintelligible, so others classify them as separate languages. Also, some regions are under-researched, making it hard to document all languages. \n\nI should also touch on language families. The 7,000 languages are grouped into families like Indo-European, Sino-Tibetan, Niger-Congo, etc. Maybe mention a few of the largest families. But wait, the question is just about the count, not the families. Still, it's good to provide a bit more context. \n\nI need to make sure the information is up-to-date. Let me think – recent estimates still hover around 7,000. However, languages are dying out rapidly, so the number decreases over time. Including that note about endangerment and language extinction rates could be helpful. For instance, it's often stated that a language dies every few weeks. \n\nAnother point is sign languages. Does the count include them? Ethnologue includes some, but not all sources might. If the user is including sign languages, that adds more to the count, but I think the 7,000 figure typically refers to spoken languages. For thoroughness, maybe mention that there are also over 300 sign languages. \n\nSummarizing, the answer should state around 7,000, mention Ethnologue's figure, explain why the exact number varies, touch on endangerment, and possibly note sign languages as a separate category. Also, a brief mention of Papua New Guinea as the most linguistically diverse country. \n\nWait, let me verify Ethnologue's current number. As of their latest edition (25th, 2022), they list 7,168 living languages. But I should check if that's the case. Some sources might round to 7,000. Also, SIL International publishes Ethnologue, so citing them as reference makes sense. \n\nOther sources, like Glottolog, might have a different count because they use different criteria. Glottolog might list around 7,000 as well, but exact numbers vary. It's important to highlight that the count isn't exact because of differing definitions and ongoing research. \n\nIn conclusion, the approximate number is 7,000, with Ethnologue being a key source, considerations of endangerment, and the challenges in counting due to dialect vs. language distinctions. I should make sure the answer is clear, acknowledges the variability, and provides key points succinctly.
Answer: The exact number of languages in the world is challenging to determine due to differences in definitions (e.g., distinguishing languages from dialects) and ongoing documentation efforts. However, widely cited estimates suggest there are approximately **7,000 languages** globally.
Model: DeepSeek-R1
Usage:
Prompt tokens: 11
Total tokens: 897
Completion tokens: 886
Stream content
By default, the completions API returns the entire generated content in a single response. If you're generating long completions, waiting for the response can take many seconds.
You can stream the content to get it as it's being generated. Streaming content allows you to start processing the completion as content becomes available. This mode returns an object that streams back the response as data-only server-sent events. Extract chunks from the delta field, rather than the message field.
var messages = [
{ role: "system", content: "You are a helpful assistant" },
{ role: "user", content: "How many languages are in the world?" },
];
var response = await client.path("/chat/completions").post({
body: {
messages: messages,
}
}).asNodeStream();
To stream completions, use .asNodeStream() when you call the model.
You can visualize how streaming generates content:
var stream = response.body;
if (!stream) {
stream.destroy();
throw new Error(`Failed to get chat completions with status: ${response.status}`);
}
if (response.status !== "200") {
throw new Error(`Failed to get chat completions: ${response.body.error}`);
}
var sses = createSseStream(stream);
for await (const event of sses) {
if (event.data === "[DONE]") {
return;
}
for (const choice of (JSON.parse(event.data)).choices) {
console.log(choice.delta?.content ?? "");
}
}
Apply content safety
The Azure AI model inference API supports Azure AI content safety. When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
try {
var messages = [
{ role: "system", content: "You are an AI assistant that helps people find information." },
{ role: "user", content: "Chopping tomatoes and cutting them into cubes or wedges are great ways to practice your knife skills." },
];
var response = await client.path("/chat/completions").post({
body: {
messages: messages,
}
});
console.log(response.body.choices[0].message.content);
}
catch (error) {
if (error.status_code == 400) {
var response = JSON.parse(error.response._content);
if (response.error) {
console.log(`Your request triggered an ${response.error.code} error:\n\t ${response.error.message}`);
}
else
{
throw error;
}
}
}
Tip
To learn more about how you can configure and control Azure AI content safety settings, check the Azure AI content safety documentation.
DeepSeek-R1
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:
Prerequisites
To use DeepSeek-R1 with Azure AI Foundry, you need the following prerequisites:
A model deployment
Deployment to serverless APIs
DeepSeek-R1 can be deployed to serverless API endpoints with pay-as-you-go billing. This kind of deployment provides a way to consume models as an API without hosting them on your subscription, while keeping the enterprise security and compliance that organizations need.
Deployment to a serverless API endpoint doesn't require quota from your subscription. If your model isn't deployed already, use the Azure AI Studio, Azure Machine Learning SDK for Python, the Azure CLI, or ARM templates to deploy the model as a serverless API.
The inference package installed
You can consume predictions from this model by using the Azure.AI.Inference package from NuGet. To install this package, you need the following prerequisites:
- The endpoint URL. To construct the client library, you need to pass in the endpoint URL. The endpoint URL has the form
https://your-host-name.your-azure-region.inference.ai.azure.com, whereyour-host-nameis your unique model deployment host name andyour-azure-regionis the Azure region where the model is deployed (for example, eastus2). - Depending on your model deployment and authentication preference, you need either a key to authenticate against the service, or Microsoft Entra ID credentials. The key is a 32-character string.
Once you have these prerequisites, install the Azure AI inference library with the following command:
dotnet add package Azure.AI.Inference --prerelease
You can also authenticate with Microsoft Entra ID (formerly Azure Active Directory). To use credential providers provided with the Azure SDK, install the Azure.Identity package:
dotnet add package Azure.Identity
Import the following namespaces:
using Azure;
using Azure.Identity;
using Azure.AI.Inference;
This example also uses the following namespaces but you may not always need them:
using System.Text.Json;
using System.Text.Json.Serialization;
using System.Reflection;
Work with chat completions
In this section, you use the Azure AI model inference API with a chat completions model for chat.
Tip
The Azure AI model inference API allows you to talk with most models deployed in Azure AI Foundry with the same code and structure, including DeepSeek-R1.
Create a client to consume the model
First, create the client to consume the model. The following code uses an endpoint URL and key that are stored in environment variables.
ChatCompletionsClient client = new ChatCompletionsClient(
new Uri(Environment.GetEnvironmentVariable("AZURE_INFERENCE_ENDPOINT")),
new AzureKeyCredential(Environment.GetEnvironmentVariable("AZURE_INFERENCE_CREDENTIAL")),
"DeepSeek-R1"
);
Get the model's capabilities
The /info route returns information about the model that is deployed to the endpoint. Return the model's information by calling the following method:
Response<ModelInfo> modelInfo = client.GetModelInfo();
The response is as follows:
Console.WriteLine($"Model name: {modelInfo.Value.ModelName}");
Console.WriteLine($"Model type: {modelInfo.Value.ModelType}");
Console.WriteLine($"Model provider name: {modelInfo.Value.ModelProviderName}");
Model name: DeepSeek-R1
Model type: chat-completions
Model provider name: DeepSeek
Create a chat completion request
The following example shows how you can create a basic chat completions request to the model.
ChatCompletionsOptions requestOptions = new ChatCompletionsOptions()
{
Messages = {
new ChatRequestSystemMessage("You are a helpful assistant."),
new ChatRequestUserMessage("How many languages are in the world?")
},
};
Response<ChatCompletions> response = client.Complete(requestOptions);
The response is as follows, where you can see the model's usage statistics:
Console.WriteLine($"Response: {response.Value.Content}");
Console.WriteLine($"Model: {response.Value.Model}");
Console.WriteLine("Usage:");
Console.WriteLine($"\tPrompt tokens: {response.Value.Usage.PromptTokens}");
Console.WriteLine($"\tTotal tokens: {response.Value.Usage.TotalTokens}");
Console.WriteLine($"\tCompletion tokens: {response.Value.Usage.CompletionTokens}");
Response: As of now, it's estimated that there are about 7,000 languages spoken around the world. However, this number can vary as some languages become extinct and new ones develop. It's also important to note that the number of speakers can greatly vary between languages, with some having millions of speakers and others only a few hundred.
Model: DeepSeek-R1
Usage:
Prompt tokens: 19
Total tokens: 91
Completion tokens: 72
Inspect the usage section in the response to see the number of tokens used for the prompt, the total number of tokens generated, and the number of tokens used for the completion.
Understanding reasoning
Some reasoning models, like DeepSeek-R1, generate completions and include the reasoning behind it. The reasoning associated with the completion is included in the response's content within the tags <think> and </think>. The model may select on which scenarios to generate reasoning content. For example:
ChatCompletionsOptions requestOptions = new ChatCompletionsOptions()
{
Messages = {
new ChatRequestSystemMessage("You are a helpful assistant."),
new ChatRequestUserMessage("How many languages are in the world?")
},
};
Response<ChatCompletions> response = client.Complete(requestOptions);
You can extract the reasoning content from the response to understand the model's thought process as follows:
Regex regex = new Regex(pattern, RegexOptions.Singleline);
Match match = regex.Match(response.Value.Content);
Console.WriteLine("Response:");
if (match.Success)
{
Console.WriteLine($"\tThinking: {match.Groups[1].Value}");
Console.WriteLine($"\tAnswer: {match.Groups[2].Value}");
else
{
Console.WriteLine($"Response: {response.Value.Content}");
}
Console.WriteLine($"Model: {response.Value.Model}");
Console.WriteLine("Usage:");
Console.WriteLine($"\tPrompt tokens: {response.Value.Usage.PromptTokens}");
Console.WriteLine($"\tTotal tokens: {response.Value.Usage.TotalTokens}");
Console.WriteLine($"\tCompletion tokens: {response.Value.Usage.CompletionTokens}");
Thinking: Okay, the user is asking how many languages exist in the world. I need to provide a clear and accurate answer. Let's start by recalling the general consensus from linguistic sources. I remember that the number often cited is around 7,000, but maybe I should check some reputable organizations.\n\nEthnologue is a well-known resource for language data, and I think they list about 7,000 languages. But wait, do they update their numbers? It might be around 7,100 or so. Also, the exact count can vary because some sources might categorize dialects differently or have more recent data. \n\nAnother thing to consider is language endangerment. Many languages are endangered, with some having only a few speakers left. Organizations like UNESCO track endangered languages, so mentioning that adds context. Also, the distribution isn't even. Some countries have hundreds of languages, like Papua New Guinea with over 800, while others have just a few. \n\nA user might also wonder why the exact number is hard to pin down. It's because the distinction between a language and a dialect can be political or cultural. For example, Mandarin and Cantonese are considered dialects of Chinese by some, but they're mutually unintelligible, so others classify them as separate languages. Also, some regions are under-researched, making it hard to document all languages. \n\nI should also touch on language families. The 7,000 languages are grouped into families like Indo-European, Sino-Tibetan, Niger-Congo, etc. Maybe mention a few of the largest families. But wait, the question is just about the count, not the families. Still, it's good to provide a bit more context. \n\nI need to make sure the information is up-to-date. Let me think – recent estimates still hover around 7,000. However, languages are dying out rapidly, so the number decreases over time. Including that note about endangerment and language extinction rates could be helpful. For instance, it's often stated that a language dies every few weeks. \n\nAnother point is sign languages. Does the count include them? Ethnologue includes some, but not all sources might. If the user is including sign languages, that adds more to the count, but I think the 7,000 figure typically refers to spoken languages. For thoroughness, maybe mention that there are also over 300 sign languages. \n\nSummarizing, the answer should state around 7,000, mention Ethnologue's figure, explain why the exact number varies, touch on endangerment, and possibly note sign languages as a separate category. Also, a brief mention of Papua New Guinea as the most linguistically diverse country. \n\nWait, let me verify Ethnologue's current number. As of their latest edition (25th, 2022), they list 7,168 living languages. But I should check if that's the case. Some sources might round to 7,000. Also, SIL International publishes Ethnologue, so citing them as reference makes sense. \n\nOther sources, like Glottolog, might have a different count because they use different criteria. Glottolog might list around 7,000 as well, but exact numbers vary. It's important to highlight that the count isn't exact because of differing definitions and ongoing research. \n\nIn conclusion, the approximate number is 7,000, with Ethnologue being a key source, considerations of endangerment, and the challenges in counting due to dialect vs. language distinctions. I should make sure the answer is clear, acknowledges the variability, and provides key points succinctly.
Answer: The exact number of languages in the world is challenging to determine due to differences in definitions (e.g., distinguishing languages from dialects) and ongoing documentation efforts. However, widely cited estimates suggest there are approximately **7,000 languages** globally.
Model: DeepSeek-R1
Usage:
Prompt tokens: 11
Total tokens: 897
Completion tokens: 886
Stream content
By default, the completions API returns the entire generated content in a single response. If you're generating long completions, waiting for the response can take many seconds.
You can stream the content to get it as it's being generated. Streaming content allows you to start processing the completion as content becomes available. This mode returns an object that streams back the response as data-only server-sent events. Extract chunks from the delta field, rather than the message field.
static async Task StreamMessageAsync(ChatCompletionsClient client)
{
ChatCompletionsOptions requestOptions = new ChatCompletionsOptions()
{
Messages = {
new ChatRequestSystemMessage("You are a helpful assistant."),
new ChatRequestUserMessage("How many languages are in the world? Write an essay about it.")
},
MaxTokens=4096
};
StreamingResponse<StreamingChatCompletionsUpdate> streamResponse = await client.CompleteStreamingAsync(requestOptions);
await PrintStream(streamResponse);
}
To stream completions, use CompleteStreamingAsync method when you call the model. Notice that in this example we the call is wrapped in an asynchronous method.
To visualize the output, define an asynchronous method to print the stream in the console.
static async Task PrintStream(StreamingResponse<StreamingChatCompletionsUpdate> response)
{
await foreach (StreamingChatCompletionsUpdate chatUpdate in response)
{
if (chatUpdate.Role.HasValue)
{
Console.Write($"{chatUpdate.Role.Value.ToString().ToUpperInvariant()}: ");
}
if (!string.IsNullOrEmpty(chatUpdate.ContentUpdate))
{
Console.Write(chatUpdate.ContentUpdate);
}
}
}
You can visualize how streaming generates content:
StreamMessageAsync(client).GetAwaiter().GetResult();
Apply content safety
The Azure AI model inference API supports Azure AI content safety. When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
try
{
requestOptions = new ChatCompletionsOptions()
{
Messages = {
new ChatRequestSystemMessage("You are an AI assistant that helps people find information."),
new ChatRequestUserMessage(
"Chopping tomatoes and cutting them into cubes or wedges are great ways to practice your knife skills."
),
},
};
response = client.Complete(requestOptions);
Console.WriteLine(response.Value.Content);
}
catch (RequestFailedException ex)
{
if (ex.ErrorCode == "content_filter")
{
Console.WriteLine($"Your query has trigger Azure Content Safety: {ex.Message}");
}
else
{
throw;
}
}
Tip
To learn more about how you can configure and control Azure AI content safety settings, check the Azure AI content safety documentation.
DeepSeek-R1
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:
Prerequisites
To use DeepSeek-R1 with Azure AI Foundry, you need the following prerequisites:
A model deployment
Deployment to serverless APIs
DeepSeek-R1 can be deployed to serverless API endpoints with pay-as-you-go billing. This kind of deployment provides a way to consume models as an API without hosting them on your subscription, while keeping the enterprise security and compliance that organizations need.
Deployment to a serverless API endpoint doesn't require quota from your subscription. If your model isn't deployed already, use the Azure AI Studio, Azure Machine Learning SDK for Python, the Azure CLI, or ARM templates to deploy the model as a serverless API.
A REST client
Models deployed with the Azure AI model inference API can be consumed using any REST client. To use the REST client, you need the following prerequisites:
- To construct the requests, you need to pass in the endpoint URL. The endpoint URL has the form
https://your-host-name.your-azure-region.inference.ai.azure.com, whereyour-host-name`` is your unique model deployment host name andyour-azure-region`` is the Azure region where the model is deployed (for example, eastus2). - Depending on your model deployment and authentication preference, you need either a key to authenticate against the service, or Microsoft Entra ID credentials. The key is a 32-character string.
Work with chat completions
In this section, you use the Azure AI model inference API with a chat completions model for chat.
Tip
The Azure AI model inference API allows you to talk with most models deployed in Azure AI Foundry with the same code and structure, including DeepSeek-R1.
Create a client to consume the model
First, create the client to consume the model. The following code uses an endpoint URL and key that are stored in environment variables.
Get the model's capabilities
The /info route returns information about the model that is deployed to the endpoint. Return the model's information by calling the following method:
GET /info HTTP/1.1
Host: <ENDPOINT_URI>
Authorization: Bearer <TOKEN>
Content-Type: application/json
The response is as follows:
{
"model_name": "DeepSeek-R1",
"model_type": "chat-completions",
"model_provider_name": "DeepSeek"
}
Create a chat completion request
The following example shows how you can create a basic chat completions request to the model.
{
"model": "DeepSeek-R1",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How many languages are in the world?"
}
]
}
The response is as follows, where you can see the model's usage statistics:
{
"id": "0a1234b5de6789f01gh2i345j6789klm",
"object": "chat.completion",
"created": 1718726686,
"model": "DeepSeek-R1",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "As of now, it's estimated that there are about 7,000 languages spoken around the world. However, this number can vary as some languages become extinct and new ones develop. It's also important to note that the number of speakers can greatly vary between languages, with some having millions of speakers and others only a few hundred.",
"tool_calls": null
},
"finish_reason": "stop",
"logprobs": null
}
],
"usage": {
"prompt_tokens": 19,
"total_tokens": 91,
"completion_tokens": 72
}
}
Inspect the usage section in the response to see the number of tokens used for the prompt, the total number of tokens generated, and the number of tokens used for the completion.
Understanding reasoning
Some reasoning models, like DeepSeek-R1, generate completions and include the reasoning behind it. The reasoning associated with the completion is included in the response's content within the tags <think> and </think>. The model may select on which scenarios to generate reasoning content. For example:
{
"model": "DeepSeek-R1",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How many languages are in the world?"
}
]
}
You can extract the reasoning content from the response to understand the model's thought process as follows:
{
"id": "0a1234b5de6789f01gh2i345j6789klm",
"object": "chat.completion",
"created": 1718726686,
"model": "DeepSeek-R1",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "<think>\nOkay, the user is asking how many languages exist in the world. I need to provide a clear and accurate answer. Let's start by recalling the general consensus from linguistic sources. I remember that the number often cited is around 7,000, but maybe I should check some reputable organizations.\n\nEthnologue is a well-known resource for language data, and I think they list about 7,000 languages. But wait, do they update their numbers? It might be around 7,100 or so. Also, the exact count can vary because some sources might categorize dialects differently or have more recent data. \n\nAnother thing to consider is language endangerment. Many languages are endangered, with some having only a few speakers left. Organizations like UNESCO track endangered languages, so mentioning that adds context. Also, the distribution isn't even. Some countries have hundreds of languages, like Papua New Guinea with over 800, while others have just a few. \n\nA user might also wonder why the exact number is hard to pin down. It's because the distinction between a language and a dialect can be political or cultural. For example, Mandarin and Cantonese are considered dialects of Chinese by some, but they're mutually unintelligible, so others classify them as separate languages. Also, some regions are under-researched, making it hard to document all languages. \n\nI should also touch on language families. The 7,000 languages are grouped into families like Indo-European, Sino-Tibetan, Niger-Congo, etc. Maybe mention a few of the largest families. But wait, the question is just about the count, not the families. Still, it's good to provide a bit more context. \n\nI need to make sure the information is up-to-date. Let me think – recent estimates still hover around 7,000. However, languages are dying out rapidly, so the number decreases over time. Including that note about endangerment and language extinction rates could be helpful. For instance, it's often stated that a language dies every few weeks. \n\nAnother point is sign languages. Does the count include them? Ethnologue includes some, but not all sources might. If the user is including sign languages, that adds more to the count, but I think the 7,000 figure typically refers to spoken languages. For thoroughness, maybe mention that there are also over 300 sign languages. \n\nSummarizing, the answer should state around 7,000, mention Ethnologue's figure, explain why the exact number varies, touch on endangerment, and possibly note sign languages as a separate category. Also, a brief mention of Papua New Guinea as the most linguistically diverse country. \n\nWait, let me verify Ethnologue's current number. As of their latest edition (25th, 2022), they list 7,168 living languages. But I should check if that's the case. Some sources might round to 7,000. Also, SIL International publishes Ethnologue, so citing them as reference makes sense. \n\nOther sources, like Glottolog, might have a different count because they use different criteria. Glottolog might list around 7,000 as well, but exact numbers vary. It's important to highlight that the count isn't exact because of differing definitions and ongoing research. \n\nIn conclusion, the approximate number is 7,000, with Ethnologue being a key source, considerations of endangerment, and the challenges in counting due to dialect vs. language distinctions. I should make sure the answer is clear, acknowledges the variability, and provides key points succinctly.\n</think>\n\nThe exact number of languages in the world is challenging to determine due to differences in definitions (e.g., distinguishing languages from dialects) and ongoing documentation efforts. However, widely cited estimates suggest there are approximately **7,000 languages** globally.",
"tool_calls": null
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 11,
"total_tokens": 897,
"completion_tokens": 886
}
}
Stream content
By default, the completions API returns the entire generated content in a single response. If you're generating long completions, waiting for the response can take many seconds.
You can stream the content to get it as it's being generated. Streaming content allows you to start processing the completion as content becomes available. This mode returns an object that streams back the response as data-only server-sent events. Extract chunks from the delta field, rather than the message field.
{
"model": "DeepSeek-R1",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How many languages are in the world?"
}
],
"stream": true,
"temperature": 0,
"top_p": 1,
"max_tokens": 2048
}
You can visualize how streaming generates content:
{
"id": "23b54589eba14564ad8a2e6978775a39",
"object": "chat.completion.chunk",
"created": 1718726371,
"model": "DeepSeek-R1",
"choices": [
{
"index": 0,
"delta": {
"role": "assistant",
"content": ""
},
"finish_reason": null,
"logprobs": null
}
]
}
The last message in the stream has finish_reason set, indicating the reason for the generation process to stop.
{
"id": "23b54589eba14564ad8a2e6978775a39",
"object": "chat.completion.chunk",
"created": 1718726371,
"model": "DeepSeek-R1",
"choices": [
{
"index": 0,
"delta": {
"content": ""
},
"finish_reason": "stop",
"logprobs": null
}
],
"usage": {
"prompt_tokens": 19,
"total_tokens": 91,
"completion_tokens": 72
}
}
Apply content safety
The Azure AI model inference API supports Azure AI content safety. When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
{
"model": "DeepSeek-R1",
"messages": [
{
"role": "system",
"content": "You are an AI assistant that helps people find information."
},
{
"role": "user",
"content": "Chopping tomatoes and cutting them into cubes or wedges are great ways to practice your knife skills."
}
]
}
{
"error": {
"message": "The response was filtered due to the prompt triggering Microsoft's content management policy. Please modify your prompt and retry.",
"type": null,
"param": "prompt",
"code": "content_filter",
"status": 400
}
}
Tip
To learn more about how you can configure and control Azure AI content safety settings, check the Azure AI content safety documentation.
More inference examples
For more examples of how to use DeepSeek models, see the following examples and tutorials:
| Description | Language | Sample |
|---|---|---|
| Azure AI Inference package for Python | Python | Link |
| Azure AI Inference package for JavaScript | JavaScript | Link |
| Azure AI Inference package for C# | C# | Link |
| Azure AI Inference package for Java | Java | Link |
Cost and quota considerations for DeepSeek models deployed as serverless API endpoints
Quota is managed per deployment. Each deployment has a rate limit of 200,000 tokens per minute and 1,000 API requests per minute. However, we currently limit one deployment per model per project. Contact Microsoft Azure Support if the current rate limits aren't sufficient for your scenarios.