Microsoft Foundry SDKs and Endpoints

This article refers to the Microsoft Foundry (new) portal.

A Foundry resource provides unified access to models, agents, and tools. This article explains which SDK and endpoint to use for your scenario.

SDK	What it’s for	Endpoint
Foundry SDK	Foundry-specific capabilities with OpenAI-compatible interfaces. Includes access to Foundry direct models through the Responses API (not Chat Completions).	`https://<resource-name>.services.ai.azure.com/api/projects/<project-name>`
OpenAI SDK	Latest OpenAI SDK models and features with the full OpenAI API surface. Foundry direct models available through Chat Completions API (not Responses).	`https://<resource-name>.openai.azure.com/openai/v1`
Foundry Tools SDKs	Prebuilt solutions (Vision, Speech, Content Safety, and more).	Tool-specific endpoints (varies by service).
Agent Framework	Multi-agent orchestration in code. Cloud-agnostic.	Uses the project endpoint via the Foundry SDK.

Choose your SDK:

Use Foundry SDK when building apps with agents, evaluations, or Foundry-specific features
Use OpenAI SDK when maximum OpenAI compatibility is required, or using Foundry direct models via Chat Completions
Use Foundry Tools SDKs when working with specific AI services (Vision, Speech, Language, etc.)
Use Agent Framework when building multi-agent systems in code (local orchestration)

Resource types: A Foundry resource provides all endpoints previously listed. An Azure OpenAI resource provides only the /openai/v1 endpoint.Authentication: Samples here use Microsoft Entra ID (DefaultAzureCredential). API keys work on /openai/v1. Pass the key as api_key instead of a token provider.

Prerequisites

An Azure account with an active subscription. If you don’t have one, create a free Azure account, which includes a free trial subscription.
Have one of the following Azure RBAC roles to create and manage Foundry resources:
- Azure AI User (least-privilege role for development)
- Azure AI Project Manager (for managing Foundry projects)
- Contributor or Owner (for subscription-level permissions) For details on each role’s permissions, see Role-based access control for Microsoft Foundry.
Install the required language runtimes, global tools, and VS Code extensions as described in Prepare your development environment.

Before starting, make sure your development environment is ready.
This article focuses on scenario-specific steps like SDK installation, authentication, and running sample code.

Verify prerequisites

Before proceeding, confirm:

Azure subscription is active: az account show
You have the required RBAC role: Check Azure portal → Foundry resource → Access control (IAM)
Language runtime installed:
- Python: python --version (≥3.8)
- Node.js: node --version (≥18)
- .NET: dotnet --version (≥6.0)
- Java: java --version (≥11)

Foundry SDK

The Foundry SDK connects to a single project endpoint that provides access to the most popular Foundry capabilities:

https://<resource-name>.services.ai.azure.com/api/projects/<project-name>

If your organization uses a custom subdomain, replace <resource-name> with <your-custom-subdomain> in the endpoint URL.

This approach simplifies application configuration. Instead of managing multiple endpoints, you configure one.

Install the SDK

SDK versions: The 2.x preview SDK targets the new Foundry portal and API. The 1.x GA SDK targets Foundry classic. Make sure the samples you follow match your installed package.

SDK Version	Portal Version	Status	Python Package
2.x (preview)	Foundry (new)	Preview	`azure-ai-projects>=2.0.0b1 --pre`
1.x (GA)	Foundry classic	Stable	`azure-ai-projects==1.0.0`

The Azure AI Projects client library for Python is a unified library that enables you to use multiple client libraries together by connecting to a single project endpoint. Run these commands to install the preview packages for Foundry projects.

pip install --pre azure-ai-projects
pip install azure-identity openai

SDK Version	Portal Version	Status	Java Package
1.0.0-beta.3 1.0.0-beta.1	Foundry (new)	Preview	`azure-ai-projects` `azure-ai-agents`

SDK Version	Portal Version	Status	JavaScript Package
2.0.0-beta.4 (preview)	Foundry (new)	Preview	`@azure/ai-projects 'prerelease'`
1.0.1	Foundry classic	Stable	`@azure/ai-projects`

SDK Version	Portal Version	Status	.NET Package
1.2.0-beta.5 (preview)	Foundry (new)	Preview	`Azure.AI.Projects` `Azure.AI.Projects.Openai`
1.x (GA)	Foundry classic	Stable	`Azure.AI.Projects`

The Azure AI Projects client library for Java (preview) is a unified library that enables you to use multiple client libraries together by connecting to a single project endpoint.

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.

Add these packages to your installation for Foundry projects.

package com.azure.ai.agents;

import com.azure.core.util.Configuration;
import com.azure.identity.DefaultAzureCredentialBuilder;
import com.openai.models.responses.Response;
import com.openai.models.responses.ResponseCreateParams;

The Azure AI Projects client library for JavaScript is a unified library that enables you to use multiple client libraries together by connecting to a single project endpoint. Run this command to install the preview JavaScript packages for Foundry projects.

npm install @azure/ai-projects@beta @azure/identity dotenv

The Azure AI Projects client library for .NET is a unified library that enables you to use multiple client libraries together by connecting to a single project endpoint. Run this command to add the Azure.AI.Projects package to your .NET project.

dotnet add package Azure.AI.Projects --prerelease
dotnet add package Azure.AI.Projects.OpenAI --prerelease
dotnet add package Azure.Identity

Using the Foundry SDK

The SDK exposes two client types because Foundry and OpenAI have different API shapes:

Project client – Use for Foundry-native operations where OpenAI has no equivalent. Examples: listing connections, retrieving project properties, enabling tracing.
OpenAI-compatible client – Use for Foundry functionality that builds on OpenAI concepts. The Responses API, agents, evaluations, and fine-tuning all use OpenAI-style request/response patterns. This client also gives you access to Foundry direct models (non-Azure-OpenAI models hosted in Foundry). The project endpoint serves this traffic on the /openai route.

Most apps use both clients. Use the project client for setup and configuration, then use the OpenAI-compatible client for running agents, evaluations, and calling models (including Foundry direct models). Create a project client:

from azure.identity import DefaultAzureCredential
from azure.ai.projects import AIProjectClient

project_client = AIProjectClient(
  endpoint="https://<resource-name>.services.ai.azure.com/api/projects/<project-name>",
  credential=DefaultAzureCredential())

Create an OpenAI-compatible client from your project:

with project_client.get_openai_client() as openai_client:
    response = openai_client.responses.create(
        model="gpt-5.2",
        input="What is the size of France in square miles?",
    )
    print(f"Response output: {response.output_text}")

Expected output:

Response output: France has an area of approximately 213,011 square miles (551,695 square kilometers).

Create a project client:

import com.azure.ai.projects.ProjectsClient;
import com.azure.ai.projects.ProjectsClientBuilder;
import com.azure.identity.DefaultAzureCredentialBuilder;

String endpoint = "https://<resource-name>.services.ai.azure.com/api/projects/<project-name>";

ProjectsClient projectClient = new ProjectsClientBuilder()
    .credential(new DefaultAzureCredentialBuilder().build())
    .endpoint(endpoint)
    .buildClient();

Create and use an OpenAI-compatible client from your project:

OpenAIClient openAIClient = projectClient.getOpenAIClient();

Create a project client:

import { DefaultAzureCredential } from "@azure/identity";
import { AIProjectClient } from "@azure/ai-projects";
import "dotenv/config";

const projectEndpoint = "https://<resource-name>.services.ai.azure.com/api/projects/<project-name>";
const deploymentName = "gpt-5.2";
const project = new AIProjectClient(projectEndpoint, new DefaultAzureCredential());

Create an OpenAI-compatible client from your project:

const openAIClient = await project.getOpenAIClient();
const response = await openAIClient.responses.create({
    model: deploymentName,
    input: "What is the size of France in square miles?",
});
console.log(`Response output: ${response.output_text}`);

Create a project client:

using Azure.AI.Projects.OpenAI; 
using Azure.Identity;
using OpenAI.Responses;

string endpoint = "https://<resource-name>.services.ai.azure.com/api/projects/<project-name>";

AIProjectClient projectClient = new(
    endpoint: new Uri(endpoint), 
    tokenProvider: new DefaultAzureCredential());

Create an OpenAI-compatible client from your project:

#pragma warning disable OPENAI001
OpenAIResponseClient responseClient = projectClient.OpenAI.GetProjectResponsesClientForModel("gpt-5.2");
OpenAIResponse response = responseClient.CreateResponse("What is the speed of light?");
Console.WriteLine(response.GetOutputText());
#pragma warning restore OPENAI001

What you can do with the Foundry SDK

Access Foundry Models, including Azure OpenAI
Use the Foundry Agent Service
Run cloud evaluations
Enable app tracing
Fine-tune a model
Get endpoints and keys for Foundry Tools, local orchestration, and more

Troubleshooting

Authentication errors

If you see DefaultAzureCredential failed to retrieve a token:

Verify Azure CLI is authenticated:

az account show
az login  # if not logged in

Check RBAC role assignment:
- Confirm you have at least the Azure AI User role on the Foundry project
- See Assign Azure roles
For managed identity in production:
- Ensure the managed identity has the appropriate role assigned
- See Configure managed identities

Endpoint configuration errors

If you see Connection refused or 404 Not Found:

Verify resource and project names match your actual deployment
Check endpoint URL format: Should be https://<resource-name>.services.ai.azure.com/api/projects/<project-name>
For custom subdomains: Replace <resource-name> with your custom subdomain

SDK version mismatches

If code samples fail with AttributeError or ModuleNotFoundError:

Check SDK version:

pip show azure-ai-projects  # Python
npm list @azure/ai-projects  # JavaScript
dotnet list package  # .NET

Verify moniker alignment: 2.x SDK requires Foundry portal, 1.x SDK requires Foundry classic
Reinstall with correct version flags: See installation commands in each language section above

OpenAI SDK

Use the OpenAI SDK when you want the full OpenAI API surface and maximum client compatibility. This endpoint provides access to Azure OpenAI models and Foundry direct models (via Responses API). It doesn’t provide access to Foundry-specific features like agents and evaluations. The following snippet shows how to use the Azure OpenAI /openai/v1 endpoint directly.

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://<resource-name>.openai.azure.com/openai/v1/",  
  api_key=token_provider,
)

response = client.responses.create(
    model="model_deployment_name",
    input= "What is the size of France in square miles?" 
)

print(response.model_dump_json(indent=2)) 

Expected output:

{
  "id": "resp_abc123",
  "object": "response",
  "created": 1234567890,
  "model": "gpt-5.2",
  "output_text": "France has an area of approximately 213,011 square miles (551,695 square kilometers)."
}

For more information, see Azure OpenAI supported programming languages

The following snippet shows how to use the Azure OpenAI /openai/v1 endpoint directly.

import com.azure.identity.AuthenticationUtil;
import com.azure.identity.DefaultAzureCredential;
import com.azure.identity.DefaultAzureCredentialBuilder;
import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.credential.BearerTokenCredential;

import java.util.function.Supplier;

DefaultAzureCredential tokenCredential = new DefaultAzureCredentialBuilder().build();
String endpoint = "https://<resource-name>.openai.azure.com/openai/v1";
String deploymentName = "gpt-5.2";
Supplier<String> bearerTokenSupplier = AuthenticationUtil.getBearerTokenSupplier(
        tokenCredential, "https://cognitiveservices.azure.com/.default");
OpenAIClient openAIClient = OpenAIOkHttpClient.builder()
        .baseUrl(endpoint)
        .credential(BearerTokenCredential.create(bearerTokenSupplier))
        .build();

ResponseCreateParams responseCreateParams = ResponseCreateParams.builder()
        .input("What is the speed of light?")
        .model(deploymentName) 
        .build();

Response response = openAIClient.responses().create(responseCreateParams);

System.out.println("Response output: " + response.getOutputText());

For more information on using the OpenAI SDK, see Azure OpenAI supported programming languages

const endpoint = "https://<resource-name>.openai.azure.com/openai/v1";
const scope = "https://cognitiveservices.azure.com/.default";
const azureADTokenProvider = getBearerTokenProvider(new DefaultAzureCredential(), scope);
const client = new OpenAI({ baseURL: endpoint, apiKey: azureADTokenProvider });
const response = await client.responses.create({
        model: deploymentName,
        input: "What is the size of France in square miles?",
    });
console.log(`Response output: ${response.output_text}`);

For more information on using the OpenAI SDK, see Azure OpenAI supported programming languages

Install the OpenAI package: Run this command to add the OpenAI client library to your .NET project.
```
dotnet add package OpenAI
```

When it succeeds, the .NET CLI confirms that it installed the OpenAI package. This snippet configures DefaultAzureCredential, builds OpenAIClientOptions, and creates a ResponseClient for the Azure OpenAI v1 endpoint.

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

#pragma warning disable OPENAI001

const string directModelEndpoint  = "https://<resource-name>.openai.azure.com/openai/v1/";
const string deploymentName = "gpt-5.2";    

BearerTokenPolicy tokenPolicy = new(
     new DefaultAzureCredential(),
     "https://cognitiveservices.azure.com/.default");
 
OpenAIResponseClient client = new(
     model: deploymentName,
     authenticationPolicy: tokenPolicy, // To use Entra 
  // credential: new ApiKeyCredential("<YOUR-AZURE-OPENAI-API-KEY>") // To use APIKEY 
     options: new OpenAIClientOptions()
     {
         Endpoint = new($"{directModelEndpoint}"),
     });
ResponseCreationOptions options = new ResponseCreationOptions
 {
     Temperature = (float)0.7,
 };
 
OpenAIResponse modelDirectResponse = client.CreateResponse(
      [
         ResponseItem.CreateUserMessageItem("What is the size of France in square miles?"),
      ], options);
 
Console.WriteLine($"[ASSISTANT]: {modelDirectResponse.GetOutputText()}");
#pragma warning restore OPENAI001
// The ResponseClient lets you interact with models and services in your project.

For more information on using the OpenAI SDK, see Azure OpenAI supported programming languages

Using the Agent Framework for local orchestration

Microsoft Agent Framework is an open-source SDK for building multi-agent systems in code (for example, .NET and Python) with a cloud-provider-agnostic interface. Use Agent Framework when you want to define and orchestrate agents locally. Pair it with the Foundry SDK when you want those agents to run against Foundry models or when you want Agent Framework to orchestrate agents hosted in Foundry. For more information, see the Microsoft Agent Framework overview.

Foundry Tools SDKs

Foundry Tools (formerly Azure AI Services) are prebuilt point solutions with dedicated SDKs. Use the following endpoints to work with Foundry Tools.

Which endpoint should you use?

Choose an endpoint based on your needs: Use the Azure AI Services endpoint to access Computer Vision, Content Safety, Document Intelligence, Language, Translation, and Token Foundry Tools. Foundry Tools endpoint: https://<your-resource-name>.cognitiveservices.azure.com/

Endpoints use either your resource name or a custom subdomain. If your organization set up a custom subdomain, replace your-resource-name with your-custom-subdomain in all endpoint examples.

For Speech and Translation Foundry Tools, use the endpoints in the following tables. Replace placeholders with your resource information.

Speech Endpoints

Foundry Tool	Endpoint
Speech to Text (Standard)	`https://<YOUR-RESOURCE-REGION>.stt.speech.microsoft.com`
Text to Speech (Neural)	`https://<YOUR-RESOURCE-REGION>.tts.speech.microsoft.com`
Custom Voice	`https://<YOUR-RESOURCE-NAME>.cognitiveservices.azure.com/`

Translation Endpoints

Foundry Tool	Endpoint
Text Translation	`https://api.cognitive.microsofttranslator.com/`
Document Translation	`https://<YOUR-RESOURCE-NAME>.cognitiveservices.azure.com/`

The following sections include quickstart links for the Foundry Tools SDKs and reference information.

C# supported Foundry Tools

Foundry Tool	Description	Quickstarts and reference documentation
Speech	Add speech to text, text to speech, translation, and speaker recognition capabilities to applications.	• Speech to text quickstart • Text to speech quickstart • Speech translation quickstart • Speech SDK for .NET • Speech NuGet package (Speech CLI)
Language	Build applications with natural language understanding capabilities.	• Custom question answering (CQA) quickstart • Entity linking quickstart • Language detection quickstart • Key Phrase extraction quickstart • Detecting named entities (NER) quickstart • Detect Personally Identifiable Information (PII) quickstart • Sentiment analysis and opinion mining quickstart • Using text, document and conversation summarization quickstart • Using Text Analytics for health quickstart • Language SDK for .NET (text analysis) • Language NuGet package (text analysis) • Language SDK for .NET (Question Answering) • Language NuGet package (question answering)
Translator	Use AI-powered translation technology to translate more than 100 in-use, at-risk, and endangered languages and dialects.	• Translator SDK for .NET (text) • Translator NuGet package (text) • Translator SDK for .NET (batch) • Translator NuGet package (batch)
Azure AI Search	Bring AI-powered cloud search to your mobile and web apps.	• Use agentic retrieval quickstart • Vector search quickstart • Classic generative search (RAG) using grounding data quickstart • Full-text search quickstart • Semantic ranking quickstart • Chat with Azure OpenAI models using your own data quickstart • Azure AI Search SDK for .NET • Azure AI Search NuGet package
Content Safety	Detect harmful content in applications and services.	• Analyze text content quickstart • Use a text blocklist quickstart • Analyze image content quickstart • Content Safety SDK for .NET • Content Safety NuGet package
Document Intelligence	Turn documents into intelligent data-driven solutions.	• Document Intelligence quickstart • Document Intelligence SDK for .NET • Document Intelligence NuGet package
Vision	Analyze content in digital images and rich media assets.	• Azure Vision in Foundry Tools v3.2 GA Read quickstart • Image Analysis quickstart • Use the Face service quickstart • Vision SDK for .NET • Vision NuGet package

Java supported Foundry Tools

Foundry Tool	Description	Quickstarts and reference documentation
Speech	Add speech to text, text to speech, translation, and speaker recognition capabilities to applications.	• Speech to text quickstart • Text to speech quickstart • Speech translation quickstart • Speech SDK for Java • Speech Maven package
Language	Build applications with natural language understanding capabilities.	• Entity linking quickstart • Language detection quickstart • Key Phrase extraction quickstart • Detecting named entities (NER) quickstart • Detect Personally Identifiable Information (PII) quickstart • Sentiment analysis and opinion mining quickstart • Using text, document and conversation summarization quickstart • Using Text Analytics for health quickstart • Language SDK for Java (text analysis) • Language Maven package
Translator	Use AI-powered translation technology to translate more than 100 in-use, at-risk, and endangered languages and dialects.	• Translator SDK for Java (text) • Translator Maven package (text)
Azure AI Search	Bring AI-powered cloud search to your mobile and web apps.	• Use agentic retrieval quickstart • Vector search quickstart • Classic generative search (RAG) using grounding data quickstart • Full-text search quickstart • Semantic ranking quickstart • Chat with Azure OpenAI models using your own data quickstart • Azure AI Search SDK for Java • Azure AI Search Maven package
Content Safety	Detect harmful content in applications and services.	• Analyze text content quickstart • Use a text blocklist quickstart • Analyze image content quickstart • Content Safety SDK for Java • Content Safety Maven package
Document Intelligence	Turn documents into intelligent data-driven solutions.	• Document Intelligence quickstart • Document Intelligence SDK for Java • Document Intelligence Maven package
Vision	Analyze content in digital images and rich media assets.	• Image Analysis quickstart • Use the Face service quickstart • Vision SDK for Java • Vision Maven package

JavaScript supported Foundry Tools

Foundry Tool	Description	Quickstarts and reference documentation
Speech	Add speech to text, text to speech, translation, and speaker recognition capabilities to applications.	• Speech to text quickstart • Text to speech quickstart • Speech translation quickstart • Speech SDK for JavaScript • Speech npm package
Language	Build applications with natural language understanding capabilities.	• Entity linking quickstart • Language detection quickstart • Key Phrase extraction quickstart • Detecting named entities (NER) quickstart • Detect Personally Identifiable Information (PII) quickstart • Sentiment analysis and opinion mining quickstart • Using text, document and conversation summarization quickstart • Using Text Analytics for health quickstart • Language SDK for JavaScript (text analysis) • Language npm package
Translator	Use AI-powered translation technology to translate more than 100 in-use, at-risk, and endangered languages and dialects.	• Translator SDK for JavaScript (text) • Translator npm package (text)
Azure AI Search	Bring AI-powered cloud search to your mobile and web apps.	• Use agentic retrieval quickstart • Vector search quickstart • Classic generative search (RAG) using grounding data quickstart • Full-text search quickstart • Semantic ranking quickstart • Chat with Azure OpenAI models using your own data quickstart • Azure AI Search SDK for JavaScript • Azure AI Search npm package
Content Safety	Detect harmful content in applications and services.	• Analyze text content quickstart • Use a text blocklist quickstart • Analyze image content quickstart • Content Safety npm package
Document Intelligence	Turn documents into intelligent data-driven solutions.	• Document Intelligence quickstart • Document Intelligence SDK for JavaScript • Document Intelligence npm package
Vision	Analyze content in digital images and rich media assets.	• Azure Vision in Foundry Tools v3.2 GA Read quickstart • Image Analysis quickstart • Use the Face service quickstart • Vision SDK for JavaScript • Vision npm package

Python supported Foundry Tools

Foundry Tool	Description	Quickstarts and reference documentation
Speech	Add speech to text, text to speech, translation, and speaker recognition capabilities to applications.	• Speech to text quickstart • Text to speech quickstart • Speech translation quickstart • Speech SDK for Python • Speech PyPi package
Language	Build applications with natural language understanding capabilities.	• Custom question answering (CQA) quickstart • Entity linking quickstart • Language detection quickstart • Key Phrase extraction quickstart • Detect named entities (NER) quickstart • Detect Personally Identifiable Information (PII) quickstart • Sentiment analysis and opinion mining quickstart • Using text, document and conversation summarization quickstart • Using Text Analytics for health quickstart • Language SDK for Python (text analysis) • Language PyPi package (text analysis) • Language SDK for Python (question answering) • Language PyPi package (question answering) • Language SDK for Python (language conversations) • Language PyPi package (language conversations)
Translator	Use AI-powered translation technology to translate more than 100 in-use, at-risk, and endangered languages and dialects.	• Translator SDK for Python (text) • Translator PyPi package (text) • Translator SDK for Python (batch) • Translator PyPi package (batch)
Azure AI Search	Bring AI-powered cloud search to your mobile and web apps.	• Connect to a search service quickstart • Use agentic retrieval quickstart • Vector search quickstart • Classic generative search (RAG) using grounding data quickstart • Full-text search quickstart • Semantic ranking quickstart • Chat with Azure OpenAI models using your own data quickstart • Azure AI Search SDK for Python • Azure AI Search PyPi package
Content Safety	Detect harmful content in applications and services.	• Analyze text content quickstart • Use a text blocklist quickstart • Analyze image content quickstart • Content Safety SDK for Python • Content Safety PyPi package
Document Intelligence	Turn documents into intelligent data-driven solutions.	• Document Intelligence quickstart • Document Intelligence SDK for Python • Document Intelligence PyPi package
Vision	Analyze content in digital images and rich media assets.	• Azure Vision in Foundry Tools v3.2 GA Read quickstart • Image Analysis quickstart • Use the Face service quickstart • Vision SDK for Python • Vision PyPi package

What is Microsoft Foundry (new)?

Get started

Agent development

Agent tools & integration

Model capabilities

Fine-tuning

Manage agents, models, & tools

Observability, evaluation, & tracing

Developer experience

API & SDK

Responsible AI

Best practices

Setup & configure

Security & governance

Operate & support

Get started with Microsoft Foundry SDKs and Endpoints

Microsoft Foundry SDKs and Endpoints

Prerequisites

Verify prerequisites

Foundry SDK

Install the SDK

Using the Foundry SDK

What you can do with the Foundry SDK

Troubleshooting

Authentication errors

Endpoint configuration errors

SDK version mismatches

OpenAI SDK

Using the Agent Framework for local orchestration

Foundry Tools SDKs

Which endpoint should you use?

Speech Endpoints

Translation Endpoints

C# supported Foundry Tools

Java supported Foundry Tools

JavaScript supported Foundry Tools

Python supported Foundry Tools

What is Microsoft Foundry (new)?

Get started

Agent development

Agent tools & integration

Model capabilities

Fine-tuning

Manage agents, models, & tools

Observability, evaluation, & tracing

Developer experience

API & SDK

Responsible AI

Best practices

Setup & configure

Security & governance

Operate & support

​Microsoft Foundry SDKs and Endpoints

​Prerequisites

​Verify prerequisites

​Foundry SDK

​Install the SDK

​Using the Foundry SDK

​What you can do with the Foundry SDK

​Troubleshooting

​Authentication errors

​Endpoint configuration errors

​SDK version mismatches

​OpenAI SDK

​Using the Agent Framework for local orchestration

​Foundry Tools SDKs

​Which endpoint should you use?

​Speech Endpoints

​Translation Endpoints

​C# supported Foundry Tools

​Java supported Foundry Tools

​JavaScript supported Foundry Tools

​Python supported Foundry Tools

Microsoft Foundry SDKs and Endpoints

Prerequisites

Verify prerequisites

Foundry SDK

Install the SDK

Using the Foundry SDK

What you can do with the Foundry SDK

Troubleshooting

Authentication errors

Endpoint configuration errors

SDK version mismatches

OpenAI SDK

Using the Agent Framework for local orchestration

Foundry Tools SDKs

Which endpoint should you use?

Speech Endpoints

Translation Endpoints

C# supported Foundry Tools

Java supported Foundry Tools

JavaScript supported Foundry Tools

Python supported Foundry Tools