Skip to main content

Microsoft Foundry

Azure platform, formerly Azure AI Foundry, for building on OpenAI, Anthropic, Meta, DeepSeek and Microsoft models. Foundry Agent Service, evaluations and model router add agents and routing. Usage bills per token or per provisioned unit on Azure.

The 30-Second Take

Pick Microsoft Foundry if you want OpenAI, Anthropic and open models under Entra ID and one Azure agreement.

It sells OpenAI's models directly, plus Claude and open models from Meta, DeepSeek and others. Its data terms win buyers and its model catalog draws praise.

Best fit
Teams on Azure that want OpenAI, Anthropic and open models under Entra ID and one Azure agreement.
Main constraint
Quota tiers, deployment types and data terms differ by model family, and new subscriptions can start with little or no quota.
First move
Pick the deployment type your residency rules allow, then confirm the quota tier for each model you need.

Why

Watch the terms: quota tiers follow usage and agreement status, and deployment types and data terms differ by model family. Requesty's gateway measured 78% request success on Azure in April 2026, so test Agent Service before production.

Practitioner sentiment, all practitioners−26 Negative

34 practitioners, 59 sources reviewed, Updated Oct 28, 2026How this is measured

Read the GILD Review
Save a product your organization uses.Keep up with Microsoft Foundry without adding it to your stack.Visit Website
Operating stack
AI Application Platform

Models

Which models does Microsoft Foundry serve, and where is each strong?

Each model's page charts its public benchmark scores beside any other model you layer on it.

  1. Claude Fable 5.1Claude Fable release for demanding reasoning and long-horizon agentic work, with stronger agentic coding, multistep research, and document, spreadsheet, and slide work.Claude FableBenchmarks
  2. Claude Haiku 5.5Anthropic's small model for high-volume, latency-sensitive tasks such as classification, extraction, and routing. API model claude-haiku-5-5, 1M-token context.Claude HaikuBenchmarks
  3. Claude Opus 5.5A Claude Opus release for complex agentic, coding, and professional work.Claude OpusBenchmarks
  4. Claude Sonnet 5.5A Claude Sonnet release for everyday agentic, coding, and knowledge work.Claude SonnetBenchmarks
  5. GPT-6.1 SolOpenAI's newer Sol model, close to GPT-6 Astra on complex work at a lower cost. On OpenAI's own OSWorld 2.1 computer-use run (offline set) it scores 78%, 2.9 points under GPT-6 Astra at about a seventh of the cost per task. API model gpt-6.1-sol, with a 1,050,000-token context on the OpenAI API; Microsoft Foundry caps input at 922,000 tokens.GPT SolBenchmarks
  6. GPT-6 AstraOpenAI's highest-capability GPT-6 release for complex end-to-end work.GPT AstraBenchmarks
  7. GPT-6 LunaOpenAI's most efficient GPT-6 model, for focused, high-volume tasks. API model gpt-6-luna, with a 1,050,000-token context on the OpenAI API; Microsoft Foundry caps input at 922,000 tokens.GPT LunaBenchmarks
  8. Grok 4.7xAI's Grok release for agentic coding and multistep work. API model grok-4.7, with a 500K-token context window on the xAI API, Microsoft Foundry, and OpenRouter, and 524,288 tokens on Amazon Bedrock and Google Cloud.GrokBenchmarks

Comparisons

How does Microsoft Foundry compare with the alternatives?

  1. Pick the platform where your cloud agreement, identity and data already live. Both sell Claude, OpenAI and open models with batch and reserved capacity; Requesty measured 96% request success on Bedrock and 78% on Azure in April 2026.

Operator Insights

What are teams learning from building on Microsoft Foundry and running it in production?

Buying and deployment

What a team building on it should verify before production traffic grows.

Sourced from Microsoft documentation

How you buy it

US$2 in, US$10 out

GPT-6.1 Sol per million tokens on Global Standard in East US 2, from Oct 1, 2026.

Source 1, prices.azure.com, Retail prices, GPT-6 meters: Retail prices, GPT-6 metersSource 2, learn.microsoft.com, Deployment types: Deployment types

Details

Standard deployments bill per million tokens: GPT-6.1 Sol on Global Standard in East US 2 lists US$2 input and US$10 output per million tokens, effective Oct 1, 2026. Provisioned deployment types bill for reserved throughput units (PTU) and carry no per-token charge.

Cost drivers

Batch at 50% off

Global Standard is the lowest price; provisioned types reserve throughput for steady volume.

Source 2, learn.microsoft.com, Deployment types: Deployment typesSource 5, Microsoft, Microsoft Learn: Model router for Microsoft Foundry concepts: Microsoft Learn: Model router for Microsoft Foundry concepts

Details

Deployment type sets much of the bill. Global Standard has the lowest price, and Global Batch and Data Zone Batch take 50% off for large asynchronous jobs, Global Batch within a 24-hour window. Provisioned types reserve throughput for predictable high volume. Model router routes each prompt in real time to the most suitable model, on Global Standard and Data Zone Standard deployments.

Where it runs

Global, zone or region

Global, Data Zone (US, EU or Asia Pacific), or regional processing, set per deployment.

Source 2, learn.microsoft.com, Deployment types: Deployment typesSource 6, learn.microsoft.com, Microsoft Learn: Use Microsoft Purview to manage data security & compliance for Microsoft Foundry: Microsoft Learn: Use Microsoft Purview to manage data security & compliance for Microsoft FoundrySource 7, learn.microsoft.com, Microsoft Learn: ISO/IEC 42001:2023 compliance offering: Microsoft Learn: ISO/IEC 42001:2023 compliance offeringSource 4, Microsoft, Data, privacy, and security: Data, privacy, and security

Details

Global deployments may process in any Azure region, Data Zone deployments only inside the US, EU or Asia Pacific zone, and Standard or regional provisioned deployments inside the customer-specified Azure geography. Data stored at rest stays in the designated Azure geography. With Microsoft Purview Data Security enabled, Foundry prompts and responses are captured in the unified audit log. Purview retention policies can retain or delete those prompts and responses. Microsoft lists Microsoft Foundry in its ISO/IEC 42001 certification scope.

What to verify

No SSO or SCIM documented

0 matches on 1,350 Microsoft Learn pages (Oct 29, 2026).

Source 3, learn.microsoft.com, Quotas and limits: Quotas and limitsSource 4, Microsoft, Data, privacy, and security: Data, privacy, and security

Details

Quota comes in seven tiers, set per subscription. Microsoft documents no SSO, SAML or SCIM for Foundry: GILD found 0 matches across the 1,350 Foundry pages on Microsoft Learn, the Product Terms and the Trust Center, checked Oct 29, 2026.

Pages GILD searched, by set, Oct 29, 2026
WherePages readMatches
Microsoft Learn: Foundry, Foundry (classic) and Foundry Local docs, including Azure OpenAI1,3500
Microsoft Learn: security baselines, authentication and the Foundry reference architecture70
Microsoft Product Terms, Microsoft Azure10
Microsoft Trust Center and Azure compliance pages40
Azure product pages for Foundry, Azure OpenAI and Foundry Agent Service30
Microsoft Foundry blog: all 111 posts, read in 2 feed pages20
GILD search record, Oct 29, 2026

Signals

What is the current evidence saying about Microsoft Foundry?

A current read of what teams and builders working in Microsoft Foundry report publicly, from the model catalog to Foundry Agent Service, with each finding linked to its sources.

Whose sources count

Practitioner sentiment, all practitioners

−26 Negative net

of 36 sources that take a side, each author counted once.

How this figure is made

Teams and leaders have 8 accounts; GILD prints their sentiment from 20.

Current sentiment

Positive, mixed and negative sources

The score counts them as 9 positive, 7 mixed and 18 negative votes, one per author.

Accounts lean negative. The model catalog and the enterprise data terms draw most of the praise, and contract and data terms are the most common reason given for choosing Foundry. Agent Service failures and missing models or features are the most reported concerns, followed by reliability and a confusing portal.

Run a pilot on your own prompts to measure output quality and cost per task.

Evidence field. All 59 sources, one mark each.

Arrange by

Each mark is one source: positive, mixed, negative, no opinion stated, or documentation (not counted).

By sentiment, All practitioners. Every source GILD read, grouped as the field draws it.
GroupSourcesPositiveMixedNegativeNo opinion stated and not counted in the scoreDocumentation, checked and not counted
Positive990000
Mixed707000
Negative20002000
Not counted900090
Documentation14000014
Every source GILD read, by the quarter it was published, as the field's time axis counts it. Documentation is dated by the day it was checked.
QuarterSources
Q1 20252
Q2 20250
Q3 20256
Q4 20254
Q1 20263
Q2 20264
Q3 202615
Q4 202611
Documentation, checked14

By sentiment

14 documentation pages check facts and are not counted.

Hover a mark for a quick look, click it or press Enter to open its source.Tap a mark to open its source, then step to its neighbors with Previous and Next.

What practitioners praise

Top praise of 4. Each mark is a source on it; filled marks praise it.

  1. Model Catalog & Choice11 of 16 sources on it praise it

Most common concerns

Top concern of 6. Each mark is a source on it; filled marks raise it.

  1. Agent Service & Tool FailuresAll 9 sources on it raise it as a concern
All 59 sources behind these findings
  1. What is Microsoft Foundry?Microsoft (Official), Product documentation, checked Oct 28, 2026
  2. Authentication and authorization in Microsoft FoundryMicrosoft (Official), Product documentation, checked Oct 28, 2026
  3. What is Toolbox in Microsoft Foundry?Microsoft (Official), Product documentation, checked Oct 28, 2026
  4. Microsoft Foundry Models overviewMicrosoft (Official), Product documentation, checked Oct 28, 2026
  5. Model router for Microsoft Foundry conceptsMicrosoft (Official), Product documentation, checked Oct 28, 2026
  6. Foundry Models PricingMicrosoft (Official), Product documentation, checked Oct 28, 2026
  7. Manage traffic with spillover for provisioned deploymentsMicrosoft (Official), Product documentation, checked Oct 28, 2026
  8. Enable diagnostic logging for Microsoft FoundryMicrosoft (Official), Product documentation, checked Oct 28, 2026
  9. Azure and other Microsoft cloud services compliance scopeMicrosoft (Official), Product documentation, checked Oct 28, 2026
  10. System and Organization Controls (SOC) 2 Type 2Microsoft (Official), Product documentation, checked Oct 28, 2026
  11. ISO/IEC 27001:2013 Information Security Management StandardsMicrosoft (Official), Product documentation, checked Oct 28, 2026
  12. Data, privacy, and security for Foundry Models sold by Azure in Microsoft FoundryMicrosoft (Official), Product documentation, checked Oct 28, 2026
  13. Microsoft Foundry Models quotas and limitsMicrosoft (Official), Product documentation, checked Oct 28, 2026
  14. Migrate from the Foundry (classic) portalMicrosoft (Official), Product documentation, checked Oct 28, 2026
  15. Anthropic S-1827a, developer (self-described: Discussion of whether enterprises will run their own model hardware), Hacker News comment, published Oct 27, 2026
  16. VanillaCache on X: "for azure foundry, the platforms really good, but it's a pity I feel like any calls through it are just 2X slower"VanillaCache, developer (self-described: Calls models through Foundry and other hosts), Post on X, published Oct 27, 2026
  17. Stephen W. Thomas on X: "Microsoft Foundry AI model deployment options confused me!"Stephen W. Thomas, Azure integration architect and Microsoft MVP (self-described: Walkthrough of Foundry deployment types and regional model availability), Post on X, published Oct 27, 2026
  18. IBM CEO says open weight models are now good and cheap on-premfg137, developer (self-described: Discussion of whether to rent model capacity or buy GPUs), Hacker News comment, published Oct 26, 2026
  19. Bedrock vs Vertex AI vs Foundry: Your Cloud Commit DecidesRajesh Beri, enterprise AI practitioner and author of THE DAILY BRIEF (self-described: Platform comparison for enterprise buyers choosing where to run Claude, GPT, and Gemini), Newsletter analysis, THE DAILY BRIEF, published Oct 25, 2026
  20. AiswaryaVenkit1 on X: "At first glance, it can feel like a long list of models, agents, tools, evaluations, guardrails, and governance features."AiswaryaVenkit1, developer (self-described: Thread explaining what Microsoft Foundry includes), Post on X, published Oct 23, 2026
  21. DeepInfer: High-performance inference framework for DeepSeek modelskasey_junk, developer (self-described: Company whose compliance and procurement teams approve the models developers may use), Hacker News comment, published Oct 20, 2026
  22. OpenCode 2.0cdnsteve, developer (self-described: Engineering organization of more than 100 developers running Claude Code against its own Foundry deployments), Hacker News comment, published Oct 15, 2026
  23. [Azure.AI.AgentServer.Responses] response.completed is streamed before the conversation lock is released, so the next turn gets 409 conversation_lockedguramrit-dhillon, developer (self-described: Hosted agent on Foundry Agent Service built with Microsoft Agent Framework on .NET 9), GitHub issue, Azure/azure-sdk-for-net, published Oct 15, 2026
  24. Why isn't the industry freaking out about DeepSeek 4.1 Flash?browningstreet, developer at a large enterprise (self-described: Large enterprise with a policy on Chinese models), Hacker News comment, published Oct 8, 2026
  25. Using Opus 5.5 to discover a new eyewitness record of the dodojiggawatts, consultant (self-described: Multi-model OCR workflow that runs the same prompt through several models), Hacker News comment, published Oct 2, 2026
  26. GPT 5.6 Sol Still Fails on Basic Code Reviewchris_money202, developer (self-described: Compares model behavior across coding tools), Hacker News comment, published Sep 28, 2026
  27. azure-ai-projects: gpt-6-luna returns 500 on project endpoint, works on resource endpointKonnor (konnor-willison-deepsee), developer (self-described: Python application calling models through a Foundry project in Sweden Central), GitHub issue, Azure/azure-sdk-for-python, published Sep 24, 2026
  28. .NET: [FoundryAgent][gpt-6-luna]: [Bug]: Invalid parameter: 'text.format' of type 'json_schema' is not supported with model version gpt-6-luna-2026-09-22lucianteodorescu-milestone, developer (self-described: Foundry agent switched to a newer model), GitHub issue, microsoft/agent-framework, published Sep 24, 2026
  29. Grok 4.7taspeotis, developer (self-described: Team running non-OpenAI models from its own Foundry resource in the Pi coding harness), Hacker News comment, published Sep 21, 2026
  30. .NET: [Bug]: Hosted-agent runtime never activates OTLP export to a third-party destination, despite docs describing it as automaticCristopher Coronado, Senior AI Engineer and Microsoft MVP (self-described: .NET hosted agent on Foundry sending telemetry to a third-party destination), GitHub issue, microsoft/agent-framework, published Sep 15, 2026
  31. DeepSeek v4.1 FlashHanClinto, developer (self-described: Discussion of how to reach models with fewer safety filters), Hacker News comment, published Sep 10, 2026
  32. DeepSeek v4.1 Flashcdnsteve, developer (self-described: Engineering organization that hosts its coding models in Foundry), Hacker News comment, published Sep 10, 2026
  33. Navier-Stokes - Tristan Buckmaster [pdf]edot, developer (self-described: Discussion of whether model vendors train on customer data), Hacker News comment, published Sep 9, 2026
  34. Baptiste GHO on X: "background mode is disabled for every model we've tried in Azure AI Foundry"Baptiste GHO, CTO, Complement Learning (self-described: Course generation feature in production at Complement Learning), Post on X, published Sep 9, 2026
  35. GPT-6 Astra on OpenRouterjiggawatts, consultant (self-described: Advises customers who choose between Foundry and OpenAI's own API), Hacker News comment, published Sep 5, 2026
  36. GPT-6 Astrajiocrag, developer (self-described: Discussion of where new OpenAI models are available), Hacker News comment, published Sep 3, 2026
  37. OpenRouter is joining Stripejohnbarron, developer (self-described: Corporate AI work weighing model routers against cloud platforms), Hacker News comment, published Aug 20, 2026
  38. Kimi K2.7 Code is generally available in GitHub Copilotpkaye, developer (self-described: Discussion of which models reach Microsoft's platforms), Hacker News comment, published Jul 2, 2026
  39. Kimi K2.7 Code is generally available in GitHub Copilotrombert, developer (self-described: Discussion of where Chinese open-weight models run in GitHub Copilot), Hacker News comment, published Jul 2, 2026
  40. Kimi K2.7 Code is generally available in GitHub CopilotmvATM99, developer (self-described: Connects a Foundry model to GitHub Copilot in VS Code), Hacker News comment, published Jul 2, 2026
  41. I built a WhatsApp clone of myself; a friend agreed on a password with itdandinu, developer (self-described: Personal WhatsApp reply bot with retrieval over the author's past messages), Hacker News comment, published Jun 19, 2026
  42. Azure AI Foundry Agent published to Microsoft Teams prompts users for Foundry login instead of using Teams SSOJino George, who published a Foundry agent to Microsoft Teams for users in his organization's Microsoft 365 tenant (self-described: A Foundry agent published straight to Microsoft Teams for users in the same Microsoft 365 tenant), Microsoft Q&A thread, published Jun 15, 2026
  43. Cybersecurity researchers aren't happy about the guardrails on Anthropic's Fableconsumer451, developer building products for clients (self-described: Client products built on Claude models deployed in Azure), Hacker News comment, published Jun 11, 2026
  44. Decisions that eroded trust in Azure - by a former Azure Core engineermrsmrtss, developer (self-described: Team that has run critical services on Azure for ten years), Hacker News comment, published Apr 3, 2026
  45. Runtime validation is still fucked in AI coding agentssebringj, developer (self-described: Team trying AI end-to-end testing at the request of the author's manager), Hacker News comment, published Feb 10, 2026
  46. Create Preview web experience from new AI Foundry is incompleteJan de Vries, engineer, Zure (self-described: Publishing a Foundry agent as a web app from the new portal), GitHub issue, microsoft-foundry/foundry-agent-webapp, published Jan 28, 2026
  47. [Bug] 400 Error when chatting with an Agent published to Teams/Web using new foundry portalAlexander Danson, Product Manager, Marshall Group (self-described: Agents built in the new Foundry portal and published to Microsoft Teams), GitHub issue, microsoft-foundry/new-foundry-portal, published Jan 9, 2026
  48. Getting a Gemini API key is an exercise in frustrationhobofan, developer (self-described: Production AI features that need high uptime), Hacker News comment, published Dec 11, 2025
  49. Getting a Gemini API key is an exercise in frustrationarielcostas, developer (self-described: Project that needed Azure speech voices and Foundry resources), Hacker News comment, published Dec 10, 2025
  50. Microsoft has a problem: lack of demand for its AI productszubiaur, developer (self-described: Builds on Azure AI services, including AI Search and Document Intelligence), Hacker News comment, published Dec 8, 2025
  51. Google Antigravitykoakuma-chan, developer (self-described: Enterprise work that must reach models through a cloud platform), Hacker News comment, published Nov 18, 2025
  52. Cannot deploy on Private Network: Failed to create Aml RP virtual workspace due to System.Exception: Failed async operationDaryl Graves, developer (self-described: Deploying the standard agent setup on a private network from Microsoft's template), GitHub issue, published Sep 23, 2025
  53. The LLM Lobotomy?Julian Goldsmith (juliangoldsmith), developer (self-described: Ongoing project with low request volume on Foundry), Hacker News comment, published Sep 20, 2025
  54. azure-ai-agents connected agent with MCP will raise for approval and eventually crashIlya Rakhlin (irakhlin), developer (self-described: Multi-agent setup with a coordinator agent and a connected agent, each with an MCP tool), GitHub issue, Azure/azure-sdk-for-python, published Aug 17, 2025
  55. azure-ai-agents: MCP usage errors with Azure AI Foundryreesmonty (jacobreesmontgomery), developer (self-described: Foundry agents calling remote MCP servers such as GitMCP and Tavily), GitHub issue, Azure/azure-sdk-for-python, published Aug 8, 2025
  56. Azure AI Foundry Agent Service Deep Research Tool ErrorSashank Neelamraju (sashanknjs), developer (self-described: Trying the Deep Research tool in Foundry Agent Service), GitHub issue, Azure/azure-sdk-for-python, published Jul 8, 2025
  57. Tool call of AzureAISearchTool doesn't respect tool configuration such as filter and top_k in package azure-ai-agentsVitor Arrais, engineer, N26 (self-described: Retrieval agent over an Azure AI Search index), GitHub issue, Azure/azure-sdk-for-python, published Jul 4, 2025
  58. 400 reasons to not use Microsoft AzureOras, developer (self-described: A few months building on Azure AI Foundry and AI Search), Hacker News comment, published Mar 1, 2025
  59. DeepSeek R1 Is Now Available on Azure AI Foundry and GitHubvemonet, developer (self-described: Testing DeepSeek R1 and Mistral Large through serverless APIs on a paid subscription), Hacker News comment, published Jan 30, 2025

Jan 2025 to Oct 2026.

45 sources from practitioners, by month and sentiment.

The full readExplore all Microsoft Foundry Signals4 praise themes, 6 concerns, 2 points of agreement and 1 disagreement across all three groups, with all 59 sources open to inspect.

Where It Fits

Where does Microsoft Foundry belong in the stack?

Microsoft Foundry is Core across Model and Operate and supports Build, Data, and Evaluate.

Business area
Product & Engineering
Function
Software Development
Operating stack
AI Application Platform
Primary role
Managed Model Access & Cloud AI Platform
Microsoft Foundry beside the rest of its stackThe Stack Field, every product on every layer
FootprintMicrosoft Foundry across the AI Application Platform stack. Bar height is its role on each layer.
  1. Model

    1. Model APIs: Core

      Model APIs, core. Foundry Models lists more than 10,000 models from Microsoft, OpenAI, Anthropic, Meta and others, with Azure OpenAI models sold directly by Azure. Usage bills per token or per provisioned throughput unit on Azure.

    2. Model gateway: Supports

      Model gateway, supports. Model router is a deployable model that sends each prompt to the most suitable underlying model, and spillover moves excess provisioned traffic to a standard deployment. Use LiteLLM or OpenRouter for models outside Foundry.

  2. Build

    1. Orchestration: Supports

      Orchestration, supports. Foundry Agent Service runs declarative prompt agents and hosted agents that run the team's own code, including Microsoft Agent Framework, LangGraph and Semantic Kernel. The framework itself stays the team's choice.

    2. Tool use: Supports

      Tool use, supports. Agents call MCP servers, OpenAPI tools, Azure Logic Apps connectors and knowledge tools for Azure AI Search, SharePoint and Microsoft Fabric. Tools outside Azure still need their own hosting.

  3. Data

    1. Retrieval: Supports

      Retrieval, supports. Foundry IQ, Azure AI Search, File Search and Grounding with Bing Search cover managed retrieval for agents. Keep a separate vector store for custom retrieval.

  4. Evaluate

    1. Evaluation: Supports

      Evaluation, supports. Built-in evaluators score agents for coherence, relevance, groundedness and safety. Use LangSmith or Braintrust to compare evaluations across clouds and model vendors.

  5. Operate

    1. Observability: Supports

      Observability, supports. Foundry traces agent interactions with OpenTelemetry and sends resource logs to Azure Monitor. Use an observability tool for models and agent steps outside Azure.

    2. Cloud deployment: Core

      Cloud deployment, core. Inference runs inside the Azure subscription with Entra ID, role-based access control and network isolation. Global, Data Zone and regional deployment types, quota tiers and provisioned throughput set residency, price and capacity.

    3. Guardrails: Supports

      Guardrails, supports. Foundry Guardrails, previously content filters, run synchronously as the service processes prompts and generates content. Prompt-injection testing and red-teaming stay with a dedicated security product.

Market mapThe layers Microsoft Foundry covers, and who else owns each one.

  1. Model APIs

    CoreModel

  2. Cloud deployment & capacity

    CoreOperate

  3. Model gateways & routing

    SupportsModel

  4. Orchestration & agent frameworks

    SupportsBuild

  5. Tool use & integrations

    SupportsBuild

4 more layers on the full map. Core, Supports and Touches describe coverage. They say nothing about quality.

More on Microsoft Foundry

  1. GILD ReviewGILD's evaluation, with the buying facts
  2. Research1 piece
  3. Guides2 guides
  4. Operator Insights4 operator accounts
  5. Where It FitsOn the AI Application Platform stack
  6. Related Products7 products