你当前正在访问 Microsoft Azure Global Edition 技术文档网站。如果需要访问由世纪互联运营的 Microsoft Azure 中国技术文档网站，请访问 https://docs.azure.cn。

Azure OpenAI 支持的编程语言

2025-10-06

Azure OpenAI API 版本支持

v1 正式发布版 (GA) API 现在允许访问 GA 和预览操作。若要了解详细信息，请参阅 API 版本生命周期指南。

安装

dotnet add package OpenAI

身份验证

Microsoft Entra ID
API 密钥

安全、无密钥的身份验证方法是通过 Azure 标识库使用Microsoft Entra ID（以前为 Azure Active Directory）。若要使用该库，请使用以下代码：

dotnet add package Azure.Identity

使用库中的所需凭据类型。例如，DefaultAzureCredential：

using Azure.Identity;
using OpenAI;
using OpenAI.Chat;
using System.ClientModel.Primitives;

#pragma warning disable OPENAI001

BearerTokenPolicy tokenPolicy = new(
    new DefaultAzureCredential(),
    "https://cognitiveservices.azure.com/.default");

ChatClient client = new(
    model: "gpt-4.1-nano",
    authenticationPolicy: tokenPolicy,
    options: new OpenAIClientOptions() { 
    
        Endpoint = new Uri("https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1")
   }
);

ChatCompletion completion = client.CompleteChat("Tell me about the bitter lesson.'");

Console.WriteLine($"[ASSISTANT]: {completion.Content[0].Text}");

有关 Azure OpenAI 无密钥身份验证的详细信息，请参阅“Azure OpenAI 安全构建基块入门”快速入门文章。

using OpenAI;
using OpenAI.Chat;
using System.ClientModel;

string keyFromEnvironment = Environment.GetEnvironmentVariable("AZURE_OPENAI_API_KEY");

ChatClient client = new(
    model: "gpt-4.1-nano",
    credential: new ApiKeyCredential(keyFromEnvironment),
    options: new OpenAIClientOptions() { 
    
        Endpoint = new Uri("https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1")
   }
);

ChatCompletion completion = client.CompleteChat("Tell me about the bitter lesson.'");

Console.WriteLine($"[ASSISTANT]: {completion.Content[0].Text}");

聊天

向推理模型发送聊天补全请求的示例。

using OpenAI;
using OpenAI.Chat;
using System.ClientModel.Primitives;

#pragma warning disable OPENAI001 //currently required for token based authentication

BearerTokenPolicy tokenPolicy = new(
    new DefaultAzureCredential(),
    "https://cognitiveservices.azure.com/.default");

ChatClient client = new(
    model: "o4-mini",
    authenticationPolicy: tokenPolicy,
    options: new OpenAIClientOptions()
    {

        Endpoint = new Uri("https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1")
    }
);

ChatCompletionOptions options = new ChatCompletionOptions
{
    ReasoningEffortLevel = ChatReasoningEffortLevel.Low,
    MaxOutputTokenCount = 100000
};

ChatCompletion completion = client.CompleteChat(
         new DeveloperChatMessage("You are a helpful assistant"),
         new UserChatMessage("Tell me about the bitter lesson")
    );

Console.WriteLine($"[ASSISTANT]: {completion.Content[0].Text}");

嵌入

using OpenAI;
using OpenAI.Embeddings;
using System.ClientModel;

string apiKey = Environment.GetEnvironmentVariable("AZURE_OPENAI_API_KEY")
    ?? throw new InvalidOperationException("AZURE_OPENAI_API_KEY environment variable is not set");

EmbeddingClient client = new(
    "text-embedding-3-large",
    credential: new ApiKeyCredential(apiKey),
    options: new OpenAIClientOptions()
    {
        Endpoint = new Uri("https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1")
    }
);

string input = "This is a test";

OpenAIEmbedding embedding = client.GenerateEmbedding(input);
ReadOnlyMemory<float> vector = embedding.ToFloats();
Console.WriteLine($"Embeddings: [{string.Join(", ", vector.ToArray())}]");

响应 API

using OpenAI;
using OpenAI.Responses;
using System.ClientModel.Primitives;
using Azure.Identity;

#pragma warning disable OPENAI001 //currently required for token based authentication

BearerTokenPolicy tokenPolicy = new(
    new DefaultAzureCredential(),
    "https://cognitiveservices.azure.com/.default");

OpenAIResponseClient client = new(
    model: "o4-mini",
    authenticationPolicy: tokenPolicy,
    options: new OpenAIClientOptions()
    {
        Endpoint = new Uri("https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1")
    }
);

OpenAIResponse response = await client.CreateResponseAsync(
    userInputText: "What's the optimal strategy to win at poker?",
    new ResponseCreationOptions()
    {
        ReasoningOptions = new ResponseReasoningOptions()
        {
            ReasoningEffortLevel = ResponseReasoningEffortLevel.High,
        },
    });

Console.WriteLine(response.GetOutputText());

流媒体

using OpenAI;
using OpenAI.Responses;
using System.ClientModel.Primitives;
using Azure.Identity;

#pragma warning disable OPENAI001 //currently required for token based authentication

BearerTokenPolicy tokenPolicy = new(
    new DefaultAzureCredential(),
    "https://cognitiveservices.azure.com/.default");

#pragma warning disable OPENAI001

OpenAIResponseClient client = new(
    model: "o4-mini",
    authenticationPolicy: tokenPolicy,
    options: new OpenAIClientOptions()
    {
        Endpoint = new Uri("https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1")
    }
);


await foreach (StreamingResponseUpdate update
    in client.CreateResponseStreamingAsync(
        userInputText: "What's the optimal strategy to win at poker?",
        new ResponseCreationOptions()
        {
            ReasoningOptions = new ResponseReasoningOptions()
            {
                ReasoningEffortLevel = ResponseReasoningEffortLevel.High,
            },
        }))
{
    if (update is StreamingResponseOutputItemAddedUpdate itemUpdate
        && itemUpdate.Item is ReasoningResponseItem reasoningItem)
    {
        Console.WriteLine($"[Reasoning] ({reasoningItem.Status})");
    }
    else if (update is StreamingResponseOutputTextDeltaUpdate delta)
    {
        Console.Write(delta.Delta);
    }
}

MCP 服务器

using OpenAI;
using OpenAI.Responses;
using System.ClientModel.Primitives;
using Azure.Identity;

#pragma warning disable OPENAI001 //currently required for token based authentication

BearerTokenPolicy tokenPolicy = new(
    new DefaultAzureCredential(),
    "https://cognitiveservices.azure.com/.default");

OpenAIResponseClient client = new(
    model: "o4-mini",
    authenticationPolicy: tokenPolicy,
    options: new OpenAIClientOptions()
    {
        Endpoint = new Uri("https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1")
    }
);

ResponseCreationOptions options = new();
options.Tools.Add(ResponseTool.CreateMcpTool(
    serverLabel: "microsoft_learn",
    serverUri: new Uri("https://free.blessedness.top/api/mcp"),
    toolCallApprovalPolicy: new McpToolCallApprovalPolicy(GlobalMcpToolCallApprovalPolicy.NeverRequireApproval)
));

OpenAIResponse response = (OpenAIResponse)client.CreateResponse([
    ResponseItem.CreateUserMessageItem([
        ResponseContentPart.CreateInputTextPart("Search for information about Azure Functions")
    ])
], options);

Console.WriteLine(response.GetOutputText());

错误处理

错误代码

状态代码	错误类型
400	`Bad Request Error`
401	`Authentication Error`
403	`Permission Denied Error`
404	`Not Found Error`
422	`Unprocessable Entity Error`
429	`Rate Limit Error`
500	`Internal Server Error`
503	`Service Unavailable`
504	`Gateway Timeout`

重试

客户端类将使用指数退避自动重试以下错误最多三次：

408 请求超时
429 请求过多
500 内部服务器错误
502 错误的网关
503 服务不可用
504 网关超时

源代码 | 包 (pkg.go.dev) | REST API 参考文档 | 包参考文档

Azure OpenAI API 版本支持

v1 正式发布版 (GA) API 现在允许访问 GA 和预览操作。若要了解详细信息，请参阅 API 版本生命周期指南。

安装

使用 go get 安装 openai 和 azidentity 模块：

go get -u 'github.com/openai/openai-go@v2.1.1'

# optional
go get github.com/Azure/azure-sdk-for-go/sdk/azidentity

azidentity 模块用于通过 Azure OpenAI 进行 Microsoft Entra ID 身份验证。

package main

import (
	"context"
	"fmt"

	"github.com/Azure/azure-sdk-for-go/sdk/azidentity"
	"github.com/openai/openai-go/v2"
	"github.com/openai/openai-go/v2/azure"
	"github.com/openai/openai-go/v2/option"
)

func main() {
	// Create an Azure credential
	tokenCredential, err := azidentity.NewDefaultAzureCredential(nil)
	if err != nil {
		panic(fmt.Sprintf("Failed to create credential: %v", err))
	}

	// Create a client with Azure OpenAI endpoint and token credential
	client := openai.NewClient(
		option.WithBaseURL("https://YOUR-RESOURCE_NAME.openai.azure.com/openai/v1/"),
		azure.WithTokenCredential(tokenCredential),
	)

	// Make a completion request
	chatCompletion, err := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
		Messages: []openai.ChatCompletionMessageParamUnion{
			openai.UserMessage("Explain what the bitter lesson is?"),
		},
		Model: "o4-mini", // Use your deployed model name on Azure
	})
	if err != nil {
		panic(err.Error())
	}

	fmt.Println(chatCompletion.Choices[0].Message.Content)
}

有关 Azure OpenAI 无密钥身份验证的详细信息，请参阅不使用密钥的 Azure OpenAI。

package main

import (
	"context"
	"fmt"

	"github.com/openai/openai-go/v2"
	"github.com/openai/openai-go/v2/option"
)

func main() {
	// Create a client with Azure OpenAI endpoint and API key
	client := openai.NewClient(
		option.WithBaseURL("https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/"),
		option.WithAPIKey("API-KEY-HERE"),
	)

	// Make a completion request
	chatCompletion, err := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
		Messages: []openai.ChatCompletionMessageParamUnion{
			openai.UserMessage("Tell me about the bitter lesson"),
		},
		Model: "o4-mini", // Use your deployed model name on Azure
	})
	if err != nil {
		panic(err.Error())
	}

	fmt.Println(chatCompletion.Choices[0].Message.Content)
}

嵌入

package main

import (
	"context"
	"fmt"
	"os"

	"github.com/openai/openai-go/v2"
	"github.com/openai/openai-go/v2/option"
)

func main() {
	// Get API key from environment variable
	apiKey := os.Getenv("AZURE_OPENAI_API_KEY")
	if apiKey == "" {
		panic("AZURE_OPENAI_API_KEY environment variable is not set")
	}

	// Create a client with Azure OpenAI endpoint and API key
	client := openai.NewClient(
		option.WithBaseURL("https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/"),
		option.WithAPIKey(apiKey),
	)

	ctx := context.Background()
	text := "The attention mechanism revolutionized natural language processing"

	// Make an embedding request
	embedding, err := client.Embeddings.New(ctx, openai.EmbeddingNewParams{
		Input: openai.EmbeddingNewParamsInputUnion{OfString: openai.String(text)},
		Model: "text-embedding-3-small", // Use your deployed model name on Azure
	})
	if err != nil {
		panic(err.Error())
	}

	// Print embedding information
	fmt.Printf("Model: %s\n", embedding.Model)
	fmt.Printf("Number of embeddings: %d\n", len(embedding.Data))
	fmt.Printf("Embedding dimensions: %d\n", len(embedding.Data[0].Embedding))
	fmt.Printf("Usage - Prompt tokens: %d, Total tokens: %d\n", embedding.Usage.PromptTokens, embedding.Usage.TotalTokens)
	
	// Print first few values of the embedding vector
	fmt.Printf("First 10 embedding values: %v\n", embedding.Data[0].Embedding[:10])
}

Responses

package main

import (
	"context"

	"github.com/Azure/azure-sdk-for-go/sdk/azidentity"
	"github.com/openai/openai-go/v2"
	"github.com/openai/openai-go/v2/azure"
	"github.com/openai/openai-go/v2/option"
	"github.com/openai/openai-go/v2/responses"
)

func main() {
	// Create Azure token credential
	tokenCredential, err := azidentity.NewDefaultAzureCredential(nil)
	if err != nil {
		panic(err)
	}

	// Create client with Azure endpoint and token credential
	client := openai.NewClient(
		option.WithBaseURL("https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/"),
		azure.WithTokenCredential(tokenCredential),
	)

	ctx := context.Background()
	question := "Tell me about the attention is all you need paper"

	resp, err := client.Responses.New(ctx, responses.ResponseNewParams{
		Input: responses.ResponseNewParamsInputUnion{OfString: openai.String(question)},
		Model: "o4-mini",
	})

	if err != nil {
		panic(err)
	}

	println(resp.OutputText())
}

源代码 |REST API 参考文档 | 包参考文档 | Maven Central

Azure OpenAI API 版本支持

v1 正式发布版 (GA) API 现在允许访问 GA 和预览操作。若要了解详细信息，请参阅 API 版本生命周期指南。

安装

Gradle

implementation("com.openai:openai-java:4.0.1")

Maven

<dependency>
  <groupId>com.openai</groupId>
  <artifactId>openai-java</artifactId>
  <version>4.0.1</version>
</dependency>

身份验证

Microsoft Entra ID
API 密钥

使用 Microsoft Entra ID 进行身份验证需要一些初始设置：

添加 Azure 标识包：

<dependency>
    <groupId>com.azure</groupId>
    <artifactId>azure-identity</artifactId>
    <version>1.18.0</version>
</dependency>

设置后，可以从 azure.identity 中选择要使用的凭据类型。例如，DefaultAzureCredential 可用于对客户端进行身份验证：将 Microsoft Entra ID 应用程序的客户端 ID、租户 ID 和客户端密码的值设置为环境变量：AZURE_CLIENT_ID、AZURE_TENANT_ID、AZURE_CLIENT_SECRET。

授权是最简单的使用 DefaultAzureCredential。它会找到可在其运行环境中使用的最佳凭据，尽管我们仅建议在测试而非生产中使用 DefaultAzureCredential。

Credential tokenCredential = BearerTokenCredential.create(
        AuthenticationUtil.getBearerTokenSupplier(
                new DefaultAzureCredentialBuilder().build(),
                "https://cognitiveservices.azure.com/.default"));
OpenAIClient client = OpenAIOkHttpClient.builder()
        .baseUrl("https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/")
        .credential(tokenCredential)
        .build();

有关 Azure OpenAI 无密钥身份验证的详细信息，请参阅不使用密钥的 Azure OpenAI。

OpenAIClient client = OpenAIOkHttpClient.builder()
                .baseUrl("https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/")
                .apiKey(apiKey)
                .build();

Responses

package com.example;

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.ChatModel;
import com.openai.models.responses.Response;
import com.openai.models.responses.ResponseCreateParams;
import com.azure.core.credential.AzureKeyCredential;

public class OpenAITest {
    public static void main(String[] args) {
        // Get API key from environment variable for security
        String apiKey = System.getenv("OPENAI_API_KEY");
        String resourceName = "https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1";
        String modelDeploymentName = "gpt-4.1"; //replace with you model deployment name

        try {
            OpenAIClient client = OpenAIOkHttpClient.builder()
                    .baseUrl(resourceName)
                    .apiKey(apiKey)
                    .build();

            ResponseCreateParams params = ResponseCreateParams.builder()
                    .input("Tell me about the bitter lesson?")
                    .model(modelDeploymentName)
                    .build();

            Response response = client.responses().create(params);
            
            System.out.println("Response: " + response);
        } catch (Exception e) {
            System.err.println("Error: " + e.getMessage());
            e.printStackTrace();
        }
    }
}

源代码 | 包（npm） | 参考 |

Azure OpenAI API 版本支持

v1 正式发布版 (GA) API 现在允许访问 GA 和预览操作。若要了解详细信息，请参阅 API 版本生命周期指南。

安装

npm install openai

身份验证

Microsoft Entra ID
API 密钥

npm install @azure/identity

但是，为了对 OpenAI 客户端进行身份验证，我们需要使用 getBearerTokenProvider 包中的 @azure/identity 函数。该函数创建一个令牌提供程序，OpenAI 内部使用该提供程序为每个请求获取令牌。令牌提供程序的创建方式如下：

import { DefaultAzureCredential, getBearerTokenProvider } from "@azure/identity";
import { OpenAI } from "openai";

const tokenProvider = getBearerTokenProvider(
    new DefaultAzureCredential(),
    'https://cognitiveservices.azure.com/.default');
const client = new OpenAI({
    baseURL: "https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",
    apiKey: tokenProvider
});

有关 Azure OpenAI 无密钥身份验证的详细信息，请参阅“Azure OpenAI 安全构建基块入门”快速入门文章。

不建议在生产环境中使用 API 密钥，因为其安全性低于其他身份验证方法。

import { OpenAI } from "openai";

const client = new OpenAI({
    baseURL: "https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",
    apiKey: process.env['OPENAI_API_KEY'] //Your Azure OpenAI API key
});

重要

请谨慎使用 API 密钥。请不要直接在代码中包含 API 密钥，并且切勿公开发布该密钥。如果使用 API 密钥，请将其安全地存储在 Azure Key Vault 中。若要详细了解如何在应用中安全地使用 API 密钥，请参阅 API 密钥与 Azure 密钥保管库。

有关 AI 服务安全性的详细信息，请参阅对 Azure AI 服务的请求进行身份验证。

Responses

responses.create

import { DefaultAzureCredential, getBearerTokenProvider } from "@azure/identity";
import { OpenAI } from "openai";

const tokenProvider = getBearerTokenProvider(
    new DefaultAzureCredential(),
    'https://cognitiveservices.azure.com/.default');
const client = new OpenAI({
    baseURL: "https://YOUR-RESORCE-NAME.openai.azure.com/openai/v1/",
    apiKey: tokenProvider
});

const response = await client.responses.create({
  model: 'gpt-4.1-nano', //model deployment name
  instructions: 'You are a helpful AI agent',
  input: 'Tell me about the bitter lesson?',
});

console.log(response.output_text);

流媒体

import { DefaultAzureCredential, getBearerTokenProvider } from "@azure/identity";
import { OpenAI } from "openai";

const tokenProvider = getBearerTokenProvider(
    new DefaultAzureCredential(),
    'https://cognitiveservices.azure.com/.default');
const client = new OpenAI({
    baseURL: "https://YOUR-RESORCE-NAME.openai.azure.com/openai/v1/",
    apiKey: tokenProvider
});

const stream = await client.responses.create({
  model: 'gpt-4.1-nano', // model deployment name
  input: 'Provide a brief history of the attention is all you need paper.',
  stream: true,
});

for await (const event of stream) {
  if (event.type === 'response.output_text.delta' && event.delta) {
    process.stdout.write(event.delta);
  }
}

MCP 服务器

import { DefaultAzureCredential, getBearerTokenProvider } from "@azure/identity";
import { OpenAI } from "openai";

const tokenProvider = getBearerTokenProvider(
    new DefaultAzureCredential(),
    'https://cognitiveservices.azure.com/.default');
const client = new OpenAI({
    baseURL: "https://YOUR-RESORCE-NAME.openai.azure.com/openai/v1/",
    apiKey: tokenProvider
});

const resp = await client.responses.create({
  model: "gpt-5",
  tools: [
    {
      type: "mcp",
      server_label: "microsoft_learn",
      server_description: "Microsoft Learn MCP server for searching and fetching Microsoft documentation.",
      server_url: "https://free.blessedness.top/api/mcp",
      require_approval: "never",
    },
  ],
  input: "Search for information about Azure Functions",
});

console.log(resp.output_text);

聊天

chat.completions.create

import { DefaultAzureCredential, getBearerTokenProvider } from "@azure/identity";
import { OpenAI } from "openai";

const tokenProvider = getBearerTokenProvider(
    new DefaultAzureCredential(),
    'https://cognitiveservices.azure.com/.default');
const client = new OpenAI({
    baseURL: "https://france-central-test-001.openai.azure.com/openai/v1/",
    apiKey: tokenProvider
});

const messages = [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'Tell me about the attention is all you need paper' }
];

// Make the API request with top-level await
const result = await client.chat.completions.create({ 
    messages, 
    model: 'gpt-4.1-nano', // model deployment name
    max_tokens: 100 
});

// Print the full response
console.log('Full response:', result);

// Print just the message content from the response
console.log('Response content:', result.choices[0].message.content);

错误处理

错误代码

状态代码	错误类型
400	`Bad Request Error`
401	`Authentication Error`
403	`Permission Denied Error`
404	`Not Found Error`
422	`Unprocessable Entity Error`
429	`Rate Limit Error`
500	`Internal Server Error`
503	`Service Unavailable`
504	`Gateway Timeout`

重试

默认情况下，以下错误会自动停用两次，并出现短暂的指数退避：

连接错误
408 请求超时
429 速率限制
>=500 内部错误

使用 maxRetries 设置/禁用重试行为：

// Configure the default for all requests:
const client = new OpenAI({
  maxRetries: 0, // default is 2
});

// Or, configure per-request:
await client.chat.completions.create({ messages: [{ role: 'user', content: 'How can I get the name of the current day in Node.js?' }], model: '' }, {
  maxRetries: 5,
});

库源代码 | 包（PyPi） | 参考 |

注释

此库由 OpenAI 维护。请参阅发布历史记录，跟踪库的最新更新。

Azure OpenAI API 版本支持

v1 正式发布版 (GA) API 现在允许访问 GA 和预览操作。若要了解详细信息，请参阅 API 版本生命周期指南。

安装

pip install openai

有关最新版本：

pip install openai --upgrade

身份验证

可以从 Azure 门户或 AI Foundry 检索资源的终结点和 API 密钥：

登录到 Azure 门户> ，选择资源 >资源管理>密钥和终结点
登录到 AI Foundry 门户> 选择资源

from openai import OpenAI
from azure.identity import DefaultAzureCredential, get_bearer_token_provider

token_provider = get_bearer_token_provider(
    DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
)

client = OpenAI(  
  base_url = "https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",  
  api_key = token_provider  
)

重要

有关 AI 服务安全性的详细信息，请参阅对 Azure AI 服务的请求进行身份验证。

 import os
from openai import OpenAI
    
client = OpenAI(
    api_key=os.getenv("AZURE_OPENAI_API_KEY"),  
    base_url="https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/"
    )

如果您使用默认环境变量 OPENAI_BASE_URL 和 OPENAI_API_KEY ，它们会被客户端自动使用，无需进一步配置。

环境变量	价值
`OPENAI_BASE_URL`	`https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/`
`OPENAI_API_KEY`	Azure OpenAI 或 AI Foundry API 密钥。

from openai import OpenAI

client = OpenAI()

响应 API

responses.create（）

from openai import OpenAI
from azure.identity import DefaultAzureCredential, get_bearer_token_provider

token_provider = get_bearer_token_provider(
    DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
)

client = OpenAI(  
  base_url = "https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",  
  api_key=token_provider,
)

response = client.responses.create(
    model="gpt-4.1-nano",
    input= "This is a test" 
)

print(response.model_dump_json(indent=2))

有关更多示例，请参阅响应 API 文档。

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("AZURE_OPENAI_API_KEY"),
    base_url="https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",
)

response = client.responses.create(   
  model="gpt-4.1-nano", # Replace with your model deployment name 
  input="This is a test.",
)

print(response.model_dump_json(indent=2))

有关更多示例，请参阅响应 API 文档。

from openai import OpenAI

client = OpenAI()

response = client.responses.create(   
  model="gpt-4.1-nano", # Replace with your model deployment name 
  input="This is a test.",
)

print(response.model_dump_json(indent=2))

有关更多示例，请参阅响应 API 文档。

{
  "id": "resp_088ffc6b5f37c64d0068e187d0ceac819499c9331c2a02e92e",
  "created_at": 1759610832.0,
  "error": null,
  "incomplete_details": null,
  "instructions": null,
  "metadata": {},
  "model": "gpt-4.1-nano",
  "object": "response",
  "output": [
    {
      "id": "msg_088ffc6b5f37c64d0068e187d15f8c819495f84e214435175d",
      "content": [
        {
          "annotations": [],
          "text": "Hello! I see you've sent a message saying \"This is a test.\" How can I assist you today?",
          "type": "output_text",
          "logprobs": []
        }
      ],
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "parallel_tool_calls": true,
  "temperature": 1.0,
  "tool_choice": "auto",
  "tools": [],
  "top_p": 1.0,
  "background": false,
  "conversation": null,
  "max_output_tokens": null,
  "max_tool_calls": null,
  "previous_response_id": null,
  "prompt": null,
  "prompt_cache_key": null,
  "reasoning": {
    "effort": null,
    "generate_summary": null,
    "summary": null
  },
  "safety_identifier": null,
  "service_tier": "default",
  "status": "completed",
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "top_logprobs": 0,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 11,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 23,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 34
  },
  "user": null,
  "content_filters": null,
  "store": true
}

responses.create() 与 MCP 服务器工具一起使用

from openai import OpenAI
from azure.identity import DefaultAzureCredential, get_bearer_token_provider

token_provider = get_bearer_token_provider(
    DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
)

client = OpenAI(  
  base_url = "https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",  
  api_key=token_provider,
)

resp = client.responses.create(
    model="gpt-5",
    tools=[
        {
            "type": "mcp",
            "server_label": "microsoft_learn",
            "server_description": "Microsoft Learn MCP server for searching and fetching Microsoft documentation.",
            "server_url": "https://free.blessedness.top/api/mcp",
            "require_approval": "never",
        },
    ],
    input="Search for information about Azure Functions",
)

print(resp.output_text)

有关更多示例，请参阅响应 API 文档。

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("AZURE_OPENAI_API_KEY"),
    base_url="https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",
)

resp = client.responses.create(
    model="gpt-5",
    tools=[
        {
            "type": "mcp",
            "server_label": "microsoft_learn",
            "server_description": "Microsoft Learn MCP server for searching and fetching Microsoft documentation.",
            "server_url": "https://free.blessedness.top/api/mcp",
            "require_approval": "never",
        },
    ],
    input="Search for information about Azure Functions",
)

print(resp.output_text)

有关更多示例，请参阅响应 API 文档。

from openai import OpenAI

client = OpenAI()

resp = client.responses.create(
    model="gpt-5",
    tools=[
        {
            "type": "mcp",
            "server_label": "microsoft_learn",
            "server_description": "Microsoft Learn MCP server for searching and fetching Microsoft documentation.",
            "server_url": "https://free.blessedness.top/api/mcp",
            "require_approval": "never",
        },
    ],
    input="Search for information about Azure Functions",
)

print(resp.output_text)

有关更多示例，请参阅响应 API 文档。

Here is a summary of Azure Functions based on official Microsoft documentation:

## What is Azure Functions?
Azure Functions is a serverless compute service that enables you to run event-driven code without managing infrastructure. You write code in your preferred language—such as C#, Java, JavaScript, PowerShell, or Python—and Azure Functions handles the hosting, scaling, and maintenance for you. You pay only for the compute time you consume, making it cost-effective for many use cases.

- **Official overview:** [What is Azure Functions?](https://free.blessedness.top/en-us/azure/azure-functions/functions-overview)

## Key Scenarios for Azure Functions
Azure Functions supports a wide range of cloud application scenarios, including:

- Processing file uploads from blob storage.
- Real-time stream and event processing (IoT, analytics).
- Executing AI and machine learning inference.
- Running scheduled tasks or background jobs.
- Building scalable web APIs with HTTP endpoints.
- Orchestrating serverless workflows (using Durable Functions).
- Responding to data or database changes.
- Creating reliable message processing systems (with queues, Service Bus, Event Hubs).

Read more about scenarios here: [Azure Functions scenarios](https://free.blessedness.top/en-us/azure/azure-functions/functions-scenarios).

## How It Works
- **Triggers and Bindings:** Functions are executed by triggers (events like HTTP requests, file uploads, timers, etc.) and can use bindings to automatically interact with other Azure services.
- **Coding:** Write only the code you need for business logic; Azure Functions integrates with IDEs like Visual Studio and VS Code for development and debugging.
- **Monitoring:** Built-in integration with Azure Monitor and Application Insights.
- **Hosting plans:** Choose serverless (Consumption plan), Premium, Dedicated, or deploy in custom containers.

## Getting Started
You can create your first Azure Function quickly using:

- [Azure CLI or Developer CLI](https://free.blessedness.top/en-us/azure/azure-functions/create-first-function-azure-developer-cli)
- [Visual Studio Code](https://free.blessedness.top/en-us/azure/azure-functions/how-to-create-function-vs-code)
- [Visual Studio](https://free.blessedness.top/en-us/azure/azure-functions/functions-create-your-first-function-visual-studio)

See quickstarts for all languages: [Getting started with Azure Functions](https://free.blessedness.top/en-us/azure/azure-functions/functions-get-started)

## Supported Languages
- Native: C#, Java, JavaScript, PowerShell, Python
- With custom handlers: Go, Rust, and more

## Learn More
- [Overview of Azure Functions](https://free.blessedness.top/en-us/azure/azure-functions/functions-overview)
- [Supported languages](https://free.blessedness.top/en-us/azure/azure-functions/supported-languages)
- [Triggers and bindings](https://free.blessedness.top/en-us/azure/azure-functions/functions-triggers-bindings)

Let me know if you’re looking for step-by-step tutorials, specific language samples, or deeper technical details!

聊天

chat.completions.create()

from openai import OpenAI
from azure.identity import DefaultAzureCredential, get_bearer_token_provider

token_provider = get_bearer_token_provider(
    DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
)

client = OpenAI(  
  base_url = "https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",  
  api_key=token_provider,
)

completion = client.chat.completions.create(
  model="gpt-4o", # Replace with your model deployment name.
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "When was Microsoft founded?"}
  ]
)

#print(completion.choices[0].message)
print(completion.model_dump_json(indent=2))

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("AZURE_OPENAI_API_KEY"),
    base_url="https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",
)

completion = client.chat.completions.create(
  model="gpt-4o", # Replace with your model deployment name.
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "When was Microsoft founded?"}
  ]
)

#print(completion.choices[0].message)
print(completion.model_dump_json(indent=2))

from openai import OpenAI
client = OpenAI()

completion = client.chat.completions.create(
  model="gpt-4o", # Replace with your model deployment name.
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "When was Microsoft founded?"}
  ]
)

#print(completion.choices[0].message)
print(completion.model_dump_json(indent=2))

{
  "id": "chatcmpl-AUhZ11g6aNb1Nnxjp4hFUNcszw3uf",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null,
      "message": {
        "content": "Microsoft was founded on April 4, 1975, by Bill Gates and Paul Allen in Albuquerque, New Mexico.",
        "refusal": null,
        "role": "assistant",
        "function_call": null,
        "tool_calls": null
      },
      "content_filter_results": {
        "hate": {
          "filtered": false,
          "severity": "safe"
        },
        "self_harm": {
          "filtered": false,
          "severity": "safe"
        },
        "sexual": {
          "filtered": false,
          "severity": "safe"
        },
        "violence": {
          "filtered": false,
          "severity": "safe"
        }
      }
    }
  ],
  "created": 1731880663,
  "model": "gpt-4o-2024-08-06",
  "object": "chat.completion",
  "service_tier": null,
  "system_fingerprint": "fp_04751d0b65",
  "usage": {
    "completion_tokens": 24,
    "prompt_tokens": 22,
    "total_tokens": 46,
    "completion_tokens_details": null,
    "prompt_tokens_details": null
  },
  "prompt_filter_results": [
    {
      "prompt_index": 0,
      "content_filter_results": {
        "hate": {
          "filtered": false,
          "severity": "safe"
        },
        "jailbreak": {
          "filtered": false,
          "detected": false
        },
        "self_harm": {
          "filtered": false,
          "severity": "safe"
        },
        "sexual": {
          "filtered": false,
          "severity": "safe"
        },
        "violence": {
          "filtered": false,
          "severity": "safe"
        }
      }
    }
  ]
}

chat.completions.create() - 流式处理

from openai import OpenAI
from azure.identity import DefaultAzureCredential, get_bearer_token_provider

token_provider = get_bearer_token_provider(
    DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
)

client = OpenAI(  
  base_url = "https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",  
  api_key=token_provider,
)

completion = client.chat.completions.create(
  model="gpt-4o", # Replace with your model deployment name.
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "When was Microsoft founded?"}
  ],
  stream=True
)

for chunk in completion:
    if chunk.choices and chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end='',)

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("AZURE_OPENAI_API_KEY"),
    base_url="https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",
)

completion = client.chat.completions.create(
  model="gpt-4o", # Replace with your model deployment name.
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "When was Microsoft founded?"}
  ],
  stream=True
)

for chunk in completion:
    if chunk.choices and chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end='',)

from openai import OpenAI

client = OpenAI()

completion = client.chat.completions.create(
  model="gpt-4o", # Replace with your model deployment name.
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "When was Microsoft founded?"}
  ],
  stream=True
)

for chunk in completion:
    if chunk.choices and chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end='',)

Microsoft was founded on April 4, 1975, by Bill Gates and Paul Allen.

chat.completions.create() - 图像输入

from openai import OpenAI
from azure.identity import DefaultAzureCredential, get_bearer_token_provider

token_provider = get_bearer_token_provider(
    DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
)

client = OpenAI(  
  base_url = "https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",  
  api_key=token_provider,
)

completion = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's in this image?"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://raw.githubusercontent.com/MicrosoftDocs/azure-ai-docs/main/articles/ai-foundry/openai/media/how-to/generated-seattle.png",
                    }
                },
            ],
        }
    ],
    max_tokens=300,
)

print(completion.model_dump_json(indent=2))

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("AZURE_OPENAI_API_KEY"),
    base_url="https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",
)

completion = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's in this image?"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://raw.githubusercontent.com/MicrosoftDocs/azure-ai-docs/main/articles/ai-foundry/openai/media/how-to/generated-seattle.png",
                    }
                },
            ],
        }
    ],
    max_tokens=300,
)

print(completion.model_dump_json(indent=2))

from openai import OpenAI

client = OpenAI()

completion = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's in this image?"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://raw.githubusercontent.com/MicrosoftDocs/azure-ai-docs/main/articles/ai-foundry/openai/media/how-to/generated-seattle.png",
                    }
                },
            ],
        }
    ],
    max_tokens=300,
)

print(completion.model_dump_json(indent=2))

{
  "id": "chatcmpl-AUisNBsjzPisMbx3k5Uz5SOKN63KN",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null,
      "message": {
        "content": "This image is a watercolor painting of a city skyline, featuring a prominent tower that resembles the Space Needle, which is located in Seattle. The painting uses a blend of colors to depict the cityscape and sky.",
        "refusal": null,
        "role": "assistant",
        "function_call": null,
        "tool_calls": null
      },
      "content_filter_results": {
        "hate": {
          "filtered": false,
          "severity": "safe"
        },
        "self_harm": {
          "filtered": false,
          "severity": "safe"
        },
        "sexual": {
          "filtered": false,
          "severity": "safe"
        },
        "violence": {
          "filtered": false,
          "severity": "safe"
        }
      }
    }
  ],
  "created": 1731885707,
  "model": "gpt-4o-2024-08-06",
  "object": "chat.completion",
  "service_tier": null,
  "system_fingerprint": "fp_04751d0b65",
  "usage": {
    "completion_tokens": 42,
    "prompt_tokens": 639,
    "total_tokens": 681,
    "completion_tokens_details": null,
    "prompt_tokens_details": null
  },
  "prompt_filter_results": [
    {
      "prompt_index": 0,
      "content_filter_results": {
        "jailbreak": {
          "filtered": false,
          "detected": false
        }
      }
    },
    {
      "prompt_index": 1,
      "content_filter_results": {
        "sexual": {
          "filtered": false,
          "severity": "safe"
        },
        "violence": {
          "filtered": false,
          "severity": "safe"
        },
        "hate": {
          "filtered": false,
          "severity": "safe"
        },
        "self_harm": {
          "filtered": false,
          "severity": "safe"
        }
      }
    }
  ]
}

嵌入

embeddings.create()

嵌入式技术当前不支持在 Azure OpenAI 和 v1 API 中使用 Microsoft Entra ID。

client = OpenAI(
    api_key=os.getenv("AZURE_OPENAI_API_KEY"),
    base_url="https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",
)

embedding = client.embeddings.create(
  model="text-embedding-3-large", # Replace with your model deployment name
  input="Attenion is all you need",
  encoding_format="float" 
)

print(embedding)

client = OpenAI()

embedding = client.embeddings.create(
  model="text-embedding-3-large", # Replace with your model deployment name
  input="Attenion is all you need",
  encoding_format="float" 
)

print(embedding)

为了简洁起见，截断了该响应。

CreateEmbeddingResponse(data=[Embedding(embedding=[0.009098228, -0.010369237, -0.00048062875, -0.014328566, 0.019677775, 0.010049199, -0.005600668, 0.003858746, -0.007818076, 0.012554641, 0.005134327, 0.004514824, -0.020262988, -0.0039181816, 0.025475038, 0.016733425, 0.002136255, 0.0155172795, 0.0058978465, 0.012911255, -0.014273703, -0.016806576, 0.0265906, 0.037673064, 0.003909038, 0.0265906, -0.001935088, -0.014913779, 0.01781241, -0.017821554, 0.0016596265, -0.002987785, -0.014346854, -0.000962972, 0.0068671047, 0.004405097, -0.015764166, -0.007539185, -0.030394483, -0.01586475, 0.0074706054, -0.013761641, 0.010186358, 0.008805621, -0.009939471, 0.013944521, -0.010113207, -0.015745878, -0.021927187, 0.03231471, 0.0026951786, 0.004759425, 0.0065196347, 0.010927018, 0.017263774, 0.0055229445, 0.009381691, -0.042903405], index=0, object='embedding')], model='text-embedding-3-large', object='list', usage=Usage(prompt_tokens=7, total_tokens=7))

微调

有关使用 Python 进行微调的操作方法文章

错误处理

# from openai import OpenAI
# client = OpenAI()

import openai

try:
    client.fine_tuning.jobs.create(
        model="gpt-4o",
        training_file="file-test",
    )
except openai.APIConnectionError as e:
    print("The server could not be reached")
    print(e.__cause__)  # an underlying Exception, likely raised within httpx.
except openai.RateLimitError as e:
    print("A 429 status code was received; we should back off a bit.")
except openai.APIStatusError as e:
    print("Another non-200-range status code was received")
    print(e.status_code)
    print(e.response)

错误代码

状态代码	错误类型
400	`BadRequestError`
401	`AuthenticationError`
403	`PermissionDeniedError`
404	`NotFoundError`
422	`UnprocessableEntityError`
429	`RateLimitError`
>=500	`InternalServerError`
无	`APIConnectionError`

请求 ID

若要检索请求的 ID，可以使用对应于 _request_id 响应头的 x-request-id 属性。

print(completion._request_id) 
print(legacy_completion._request_id)

重试

默认情况下，以下错误会自动停用两次，并出现短暂的指数退避：

连接错误
408 请求超时
429 速率限制
>=500 内部错误

使用 max_retries 设置/禁用重试行为：

# For all requests

from openai import OpenAI
client = OpenAI(
      max_retries=0
)

# max retires for specific requests

client.with_options(max_retries=5).chat.completions.create(
    messages=[
        {
            "role": "user",
            "content": "When was Microsoft founded?",
        }
    ],
    model="gpt-4o",
)

后续步骤

若要查看当前支持哪些模型，请查看 Azure OpenAI 模型页

反馈

此页面是否有帮助？

通过

Azure OpenAI 支持的编程语言

Azure OpenAI API 版本支持

安装

身份验证

聊天

嵌入

响应 API

流媒体

MCP 服务器

错误处理

错误代码

重试

Azure OpenAI API 版本支持

安装

身份验证

嵌入

Responses

Azure OpenAI API 版本支持

安装

Gradle

Maven

身份验证

Responses

Azure OpenAI API 版本支持

安装

身份验证

Responses

流媒体

MCP 服务器

聊天

错误处理

错误代码

重试

Azure OpenAI API 版本支持

安装

身份验证

响应 API

responses.create（）

responses.create() 与 MCP 服务器工具一起使用

聊天

chat.completions.create()

chat.completions.create() - 流式处理

chat.completions.create() - 图像输入

嵌入

embeddings.create()

微调

错误处理

错误代码

请求 ID

重试

后续步骤

反馈

其他资源