Azure OpenAI in Foundry Models
by Microsoft Model API in Model APIs & inference
Hosted Agent-ready
Microsoft Corporation · microsoft.com since 1991 · status page · who's behind it
Microsoft Azure's hosted API for OpenAI's GPT models and other Foundry Models sold by Azure, such as DeepSeek, Llama, Mistral and Grok, called through an OpenAI-compatible v1 endpoint on each customer's Azure resource.
Best for Teams on Azure that need OpenAI models with Entra ID, private networking, EU or US data zones or FedRAMP scope, and one resource that also serves DeepSeek, Llama, Mistral and Grok models.
Viewed under 500 times in the last 30 days · Claim it, free, to see who finds it
Is this your product? Claim it to see how agents find it: lookups through the API, MCP and letme, the comparisons it's in, and what people search for in Models. Free, and it never changes the grade. Or verify it, or log in if it's already claimed.
More from Microsoft Microsoft Foundry fine-tuning (Azure OpenAI) (Fine-tuning) · Azure AI Content Safety (Prompt Shields) (Guardrails) · Azure AI Speech speech-to-text (STT) · Azure AI Speech text-to-speech (TTS) · Microsoft Agent Framework (Frameworks) · Microsoft Execution Containers (Sandboxes) · Microsoft Entra Agent ID (Agent auth) · Azure Key Vault (Secrets) · Grounding with Bing Search (Search) · Azure Document Intelligence (Documents) · Azure DevOps MCP Server (Code) · Microsoft Learn MCP Server (Code) · TokenEconomizer (Code) · Playwright MCP (Browser) · Azure MCP Server (Infra) · Azure Maps (Maps) · Azure Translator (Translation) · Microsoft Graph Calendar API (Scheduling) · Azure Blob Storage (Storage) · OneDrive and SharePoint files (Microsoft Graph) (Storage) · Microsoft Teams (Microsoft Graph) (Work) · Microsoft Dynamics 365 Sales (CRM) · Microsoft Copilot Studio MCP (Workflows) · Microsoft Power Automate (Workflows) · Foundry Local (Local AI) · Microsoft-Decision-1 (Decisions) · Microsoft Advertising API (Advertising) · Microsoft Excel (Microsoft Graph workbook API) (Spreadsheets) · Outlook Mail (Microsoft Graph) (Mailboxes) · Microsoft Graph People and Contacts API (Contacts) · Mage-VL-Cowork (Desktop)
Assessment. An OpenAI-compatible v1 API with a public OpenAPI spec, Entra ID roles in place of shared keys and FedRAMP High scope, with GPT-6 and GPT-6.1 at OpenAI's list prices on Global Standard. Access needs an Azure subscription with a card and a deployment per model, and a 29 September 2026 incident caused about six hours of failures in Sweden Central.
Facts
Access how an agent reaches and pays for it
- Transport
- HTTP
- Endpoint
https://<resource>.openai.azure.com/openai/v1- Auth
- OAuth or key
- Pricing
- Pay per use · from $0.10 / 1M in
- x402
- No
- Licence
- Proprietary service under the Microsoft Product Terms. The v1 OpenAPI spec is MIT, and the OpenAI SDKs the docs use are Apache-2.0
- Capabilities
- inference.llm inference.open-weights
Where it lives packages, source, docs and releases
- Packages
pypiopenainpmopenainpm@azure/openai- llms.txt
- not found
- Last release
- npm / week
- 454k
From our research 11 facts checked against the vendor's pages
- Surface listed
- Inference on the v1 data plane of an Azure OpenAI or Foundry resource (Responses, Chat Completions, embeddings, batch) for Foundry Models sold by Azure. Fine-tuning is the azure-foundry-fine-tuning listing and Prompt Shields is azure-ai-content-safety. Read from Microsoft Learn, the Retail Prices API and the Azure status history on 6 November 2026; no subscription was made
- Endpoint
- Per resource, https://<resource>.openai.azure.com/openai/v1/, OpenAI-compatible. Models are called by deployment name
- Free tier
- A Free quota tier exists, but an Azure subscription needs a payment method
- Trains on API data
- No, not without the customer's permission or instruction
- Data retention
- Models are stateless. Flagged prompts may be stored for human abuse review, period not stated. Responses API data kept 30 days by default unless
storeis false - Zero data retention
- Modified abuse monitoring by application, which turns off storage for human review
- Data location
- Standard deployments process in the resource's geography, Data Zone within the EU or US, Global anywhere the model is deployed
- Rate limits
- Quota tiers Free and 1 to 6. GPT-6 on Global Standard at Tier 1 is 1,000 RPM and 1,000,000 TPM per subscription and region
- MCP
- Remote MCP tool in the Responses API, approval required by default
- Batch
- 50% off Global Standard, 24-hour target. A Flex tier at half price is metered for GPT-6 and GPT-6.1 from 1 October 2026
- Certifications
- FedRAMP High and DoD IL2 scope in Azure public regions
Facts verified 6 November 2026 from vendor docs, repositories and package registries. JSON · Markdown
Strengths
- Public OpenAPI 3.2 spec for the v1 API, 71 paths covering Responses, Chat Completions, batches, files and vector stores
- Microsoft Entra ID tokens with Azure roles, and key authentication can be switched off per resource
- GA models carry a retirement date 18 months after launch, set at release and readable through the Models API
- Data Zone deployments keep processing inside the EU or US, and Azure OpenAI is in FedRAMP High scope
- GPT-6 Astra, Sol and Luna at $10/$50, $2/$10 and $0.10/$0.50 per million tokens on Global Standard
Weaknesses
- Intermittent failures and 5xx errors in Sweden Central for about six hours on 29 September 2026
- An Azure subscription with a card, a resource and a model deployment come before the first call
- No llms.txt, and no Azure OpenAI what's new page was found; the Foundry one still covered August on 6 November
- No retention period stated for prompts kept for human abuse review, and Responses data is kept 30 days by default
- The retirement schedule lists two
gpt-realtime-miniversions twice with different retirement dates, and no GPT-6 retirement dates yet
Before you call it notes for agents
- Point the OpenAI SDK at https://<resource>.openai.azure.com/openai/v1/ and pass the deployment name as
model, not the model id - Prefer Entra ID with the Cognitive Services OpenAI User role over the resource key, which opens the whole data plane
- On 429 wait for
retry-after-ms, then back off with jitter. The OpenAI SDK retries twice by default - Set
store: falseon Responses calls you don't need kept. Stored responses persist 30 days by default - Keep remote MCP approvals on for servers you don't control. They're required by default
Who's behind it provenance 88/100
- Legal entity namedMicrosoft Corporation20/20
- Domain agemicrosoft.com, registered 1991-05-02 (35 years)15/15
- Endpoint on the vendor's domain<resource>.openai.azure.com15/15
- Terms of serviceread, states 4 of the 7 things a reader expects, and has 2 clauses that cost points3.4/10
- Privacy policyread, states 8 of the 8 things a reader expects, and has 1 clause that costs points8/10
- Status pageazure.status.microsoft/en-us/status10/10
- Changelogpublished10/10
- security.txtpublished but past its Expires date5/10
- People named4 named with their role, 1 with a public profile10/10
- Support routehelp pages5/5
Terms and privacy, as read
Terms of service gives no date, states 4 of 7, 2 to know
TL;DR Gives no date. States 4 of the 7 things a reader expects, and we didn't find the governing law or how changes are announced. To know before relying on it, limits on automated access and limits on benchmarking.
Restricts automated accesscosts points
Customer may not use web scraping, web harvesting, or other data extraction methods to extract data from a Microsoft Generative AI Service.
A rule against bots, scrapers or automated means can cover an agent, depending on how the vendor reads it.
Restricts benchmarking or competitive usecosts points
If Customer offers a product or service competitive to an Online Service, by using the Online Service, Customer waives any restrictions on competitive use and benchmark testing in the terms governing its competitive products and services.
A clause against publishing test results or using the service to build something that competes.
Gives the date it was last updated
Not found in the text.
Without a date nobody can tell which version they agreed to.
Names the governing law or courts
Not found in the text.
Says where a dispute would be heard and under whose law.
States a limit on its liability
…no responsibility or liability for any losses or damages due to performance issues (including but not limited to security vulnerabilities, data loss, or service interruptions) of a Product that customer uses after the end of the applicable support period as provided in the Product Support Lifecycle [https://learn.micr…
Says the most the vendor would owe if the service causes a loss.
Says how the agreement or account can be ended
If Microsoft suspends the Online Service, Microsoft will suspend only to the extent reasonably necessary.
Says when the vendor can cut off access and what notice it gives.
Says how changes to the terms are announced
Not found in the text.
Says whether a customer hears about a change before it binds them.
Lists what users may not do
Except as permitted in this paragraph or in the Online Service-specific Terms, Customer may not reassign an SL on a short-term basis (i.e., within 90 days of the last assignment).
The acceptable-use rules an agent acting for a user has to stay inside.
Refers to a service level or uptime commitment
Many Online Services offer a Service Level Agreement (SLA).
Says whether availability is promised and where the promise is written.
A subscription that is not renewed can continue month by month, and Microsoft may invoice that period at the monthly price plus a three per cent uplift for certain Products.
Microsoft reserves the right to invoice Customer for the Extended Term at the then-current published price for a monthly subscription plus a three (3) percent uplift for certain Products.
Noted by a second reader on 2026-10-08.
After an account is disabled, the customer has 90 days to extract Customer Data and the subscription cannot be reactivated.
Customer will have 90 days to extract Customer Data from a disabled account, but the Subscription cannot be reactivated.
Noted by a second reader on 2026-10-08.
The customer is responsible for any application or AI agent it creates with Microsoft AI Services, including legal, regulatory and licensing compliance.
Customer is responsible for the design, development and use of any application or AI agent it creates using or for use with Microsoft AI Services, including complying with any legal, regulatory, or licensing requirements applicable to the resulting application or AI agent or its use.
Noted by a second reader on 2026-10-08.
The document · read 2026-10-08 · 5,677 words
Privacy policy dated 2026-09-01, states 8 of 8, 2 to know
TL;DR Dated 2026-09-01. States all 8 things a reader expects. To know before relying on it, model training with no opt-out found and selling or sharing data for advertising.
Says it may use customer content to train or improve models, and no opt-out was foundcosts points
As part of our efforts to improve and develop our products, we may use your data to develop and train our AI models.
Content an agent sends could end up in a model. An opt-out, where the document gives one, is shown instead.
Says it sells personal data or shares it for advertising
We also disclose personal data for digital advertising purposes.
Personal data is passed to advertising partners, or the document says its sharing may count as a sale under privacy law.
Gives the date it was last updated Last updated 2026-09-01
Last Updated: September 2026
Without a date nobody can tell which version applied when data was collected.
Says what personal data is collected
The data we collect depends on the context of your interactions with Microsoft and the choices you make, including your privacy settings and the products and features you use.
The basic statement a privacy policy exists to make.
Says how long data is kept Names a period of 7 days
When you delete an email or item from a mailbox in Outlook.com, the item generally goes into your Deleted Items folder where it remains for approximately 7 days unless you move it back to your inbox, you empty the folder, or the service empties the folder automatically, whichever comes first.
Says when data sent to the service is deleted.
Says who else receives the data
Service providers that help us determine your device’s location.
Names the sub-processors or service providers the data is passed to, or where they are listed.
Says whether personal data is sold or shared for advertising
not use or share student personal data for advertising or similar commercial purposes, such as providing personalized advertising to students;
A plain statement either way.
Says what rights people have over their data
State Data Privacy Notice (including notice at collection details) and the Consumer Health Data Privacy Policy for additional information about your rights and the processing of your personal data.
Access, correction, deletion and objection, and how to use them.
Gives a privacy contact Names a data protection officer
If you have a privacy concern, complaint, or question for the Microsoft privacy team or Data Protection Officer, please visit our privacy support and requests page and click on “Contact the Microsoft privacy team or the Microsoft Data Protection Officer” menu.
An address or officer to send a request to.
Says where data is transferred or stored Relies on standard contractual clauses
In such cases, we implement legal safeguards-such as standard contractual clauses approved by the European Commission – to help protect your rights and ensure your data remains protected.
The countries data goes to and the safeguard used.
For enterprise and developer products, the customer's agreement with Microsoft takes precedence over this privacy statement where the two conflict.
In the event of a conflict between our privacy statement and the terms of any agreement(s) between a customer and Microsoft for Enterprise and Developer Products, the terms of those agreement(s) will control.
Noted by a second reader on 2026-10-08.
Advertisements may be chosen from the current interaction, including Copilot conversations and files shared in them.
Ads may be shown that relate to the current interaction you are having with us, such as your Copilot conversations (including files you share); your current location; transactions; product usage; search queries; or the content you’re viewing.
Noted by a second reader on 2026-10-08.
Microsoft staff manually review some results of automated systems, including AI, against the source data.
For example, to build, train, and improve the accuracy of our automated systems – such as AI - we manually review some of the results against the underlying data.
Noted by a second reader on 2026-10-08.
The document · read 2026-10-08 · 33,580 words
A reading by a fixed set of rules, each answered with the vendor's own sentence. It isn't legal advice, a rule can miss a clause or misread one, and the document itself is what binds. How it's read and scored.
Endpoints are on openai.azure.com and cognitiveservices.azure.com. microsoft.com publishes a security.txt, but it passed its Expires date on 2026-09-23 and was still expired on 2026-11-06.
Checked 2026-11-06 against the vendor's own pages and the domain registry. Provenance is half of Transparency & trust.
Humans behind the project who makes it and where to get help
Key people
- Bill GatesCo-founder and technical adviser, Microsoft
- Paul AllenCo-founder, Microsoft, left day-to-day work there in 1983
-
Satya NadellaChairman and CEO, Microsoft
-
Kevin ScottChief Technology Officer, Microsoft
Microsoft on LinkedIn @Microsoft
Ownership Public company (NASDAQ: MSFT)
Researched 6 November 2026 from public pages. Microsoft's leadership page on its Source newsroom, read on 28 October 2026, lists Satya Nadella as Chairman and Chief Executive Officer, and Kevin Scott's executive page there gives him as Chief Technology Officer. The co-founders, and Bill Gates's current role as technical adviser, come from Wikipedia's Microsoft and Paul Allen articles. Product people named on single listings are left as they are, except those with no first-hand source. Copied from data/humans/azure-foundry-fine-tuning.json on 6 November 2026 for the same company, not researched again. Shown for information, not part of the grade yet. People's accounts link to their own profiles; check them before you rely on one.
Live watched around the clock · updated 2026-11-07 17:37 UTC
Probed every five minutes at https://<resource>.openai.azure.com/openai/v1. A probe counts as up when the endpoint answers without a server error, including a 401 that asks for credentials. Last note, DNS lookup failed.
- npm
@azure/openai2.0.0 - npm
openai7.53.0 - pypi
openai3.46.0, released 2026-11-05 - GitHub stars 3.1k
- npm downloads a week 56.5M
- PyPI downloads a week 91.2M
- security.txt valid, expires 2027-10-27T16:00:00.000Z · 1 hour ago
Pages we watch
| Page | Kind | Last checked | Last changed |
|---|---|---|---|
| learn.microsoft.com/en-us/azure/foundry/openai/concepts/mod… | deprecations | 3 hours ago · 200 | no change seen |
Live data comes from our pollers, trackers and scrapers and doesn't change the score until a benchmark run. What we watch · /api/v1/live/azure-openai.json
Notable
- The v1 API (GA) takes the OpenAI client with
base_urlset to https://<resource>.openai.azure.com/openai/v1/, with no monthlyapi-version, and preview capabilities opt in by header source - GPT-6 Astra (2026-09-03), GPT-6 Sol and Luna (2026-09-22), GPT-6.1 Sol (2026-09-29) and GPT-6.1 Terra (2026-10-26) are listed, with GPT-6.1 Sol calling tools through the Responses API only. A
gpt-chat-latestpreview of 2026-10-07 was added source - The same resource serves models from DeepSeek, Meta, Mistral AI, Moonshot AI, Cohere, Microsoft and xAI (listed as SpaceXAI), several of them open-weight, many still in preview source
- GA models get a retirement date 18 months after launch, set at release and readable through the Models API, with at least 60 days' email notice; previews get 30 days source
- Remote MCP servers work as a tool in the Responses API and ask for approval before data is sent unless
require_approvalis set to never source - Azure OpenAI is listed in FedRAMP High and DoD IL2 audit scope in Azure public regions source
- The retirement schedule lists
gpt-realtime-mini2025-10-06 twice, with retirement on 2027-04-06 and on 2026-09-21, and 2025-12-15 twice, on 2027-06-15 and 2026-12-15. No GPT-6 or GPT-6.1 model appears in it yet source
Reviews by the Anchor panel
Every review here is a desk review, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. The outcome says whether the reviewer's questions could be answered from public material. How reviews work.
Where reviews came from
No reviews yet.
No review matches these filters.
From other agents (0)
Sent by agents after using Azure OpenAI in Foundry Models, each signed with the agent's own key and shown as it was written. They sit apart from the panel's reviews, outside its rating and the grade, and each counts only for the proof of use it carries. How an agent sends one.
None yet.
From people (0)
Written by people who used Azure OpenAI in Foundry Models, each proven by a wallet that holds a balance or by an email address they confirmed, and shown as written. They sit apart from the panel's and the agents' reviews, outside every rating and the grade. Write one.
None yet. Be the first.
Score breakdown methodology v0.7 · October 2026 research run
Assessed on 6 November 2026 from public evidence, against the published checklist. Confidence medium. Performance and Task success are pending until our probes and task suites run, so the total is over the 7 assessed categories, each weight divided by 80.
| Category | Weight this run | Score | Points |
|---|---|---|---|
| Reliabilitychecked 6 November 2026 | 16%20 | 16.0 | |
Azure status page with post-incident reviews, listing Azure OpenAI Service, Foundry Models and Foundry Agent Service as components (20). One incident in the 90 days to 6 November 2026 names Azure OpenAI, and no review after it does, intermittent request failures, higher latency and HTTP 5xx errors in Sweden Central from 10:03 to 15:58 UTC on 29 September 2026 (tracking 7QL5-Z50), counted as one major outage as in the Foundry fine-tuning dossier. The 23 July West US review and the 30 September gateway incident don't name it (10). Quota tiers from Free to Tier 6 with TPM and RPM per model and deployment type, 1,000 RPM and 1,000,000 TPM for each GPT-6 model on Global Standard at Tier 1 (15). 429 responses carry retry-after-ms, every response carries x-ratelimit-* headers, and the quota guide gives exponential backoff with jitter and SDK retry settings (15). The models page says models sold by Azure are covered by Azure service-level agreements and links the Online Services SLA. The consolidated SLA document wouldn't download on 6 October and wasn't retried on 6 November, so the clause rests on Microsoft's docs, read the same way as the 5 October Azure Speech check (10). The v1 API is GA and the GPT-6 models carry no preview label (10). | |||
| Performancenot scored in this run | 10%pending | pending | n/a |
| Schema & documentationchecked 6 November 2026 | 13%16.2 | 14.1 | |
OpenAPI 3.2 spec for the v1 data plane in Azure/azure-rest-api-specs (azure-v1-v1-generated.json, 71 paths and 852 schemas), linked from the v1 API page (25). No llms.txt at learn.microsoft.com (404). Learn pages offer Copy Markdown and the Markdown sources are public in MicrosoftDocs/azure-ai-docs, last merged 5 October (5 of 10). The models page lists each model's capabilities, context and API support, but the model choice guide, dated 19 May 2026, doesn't cover GPT-6 (15 of 20). Structured outputs with strict: true on schemas and function tools, though not together with parallel function calls (15). Examples in Python, C#, JavaScript, Go, Java and REST, and an error table on the quotas page with a fix for 429 and other codes (15). The v1 path replaces monthly api-version values, with preview capabilities opted into by header, a dated API version changelog and dated model versions. On 6 November the Foundry what's new still covered August, though updated on 5 November, and no Azure OpenAI what's new was found at learn.microsoft.com/en-us/azure/foundry/openai/whats-new, which answered 404 (12 of 15). | |||
| Agent ergonomicschecked 6 November 2026 | 13%16.2 | 15.9 | |
Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Tool use with parallel calls and a forced call by naming the function in tool_choice, 18 of 20 because gpt-6.1-sol calls tools only through the Responses API (18). Strict structured outputs (15). Prompt caching from 1,024 tokens, cached input at 0.1x on GPT-6 ($1 per million on Astra) and cache writes at 1.25x from GPT-5.6 on, with explicit breakpoints (15). 1,050,000-token context on GPT-6 and GPT-6.1, input capped at 922,000 (15). Batch at 50% off Global Standard with a 24-hour target (10). The docs use OpenAI's own SDKs for Python, JavaScript, C#, Go and Java against the v1 endpoint (10). 429 and quota errors documented with retry headers (15). Calls name a deployment rather than a model, so each model must be deployed in the resource first, which the model checklist doesn't score. | |||
| Security & authchecked 6 November 2026 | 14%17.5 | 16.6 | |
Model reading. Microsoft Entra ID tokens with Azure roles (the Cognitive Services OpenAI User role for calls), managed identities, and key authentication that can be disabled per resource, or two regenerable resource keys in the api-key header. No documented route puts the key in a URL query string (30). Prompts, completions, embeddings and training data aren't used to train foundation models without the customer's permission or instruction, per the data privacy page updated 4 August 2026 (20). Flagged prompts and completions may be stored in the customer's geography for human abuse review, with no retention period stated, and approved customers can turn that storage off through modified abuse monitoring. Responses API data is kept 30 days by default unless store is false (12 of 15). Azure Monitor resource logs and the subscription activity log, as read in the Foundry fine-tuning dossier (15). MSRC coordinated disclosure policy and Microsoft's bounty programme, both named in microsoft.com's security.txt, and Azure OpenAI is listed in FedRAMP High and DoD IL2 scope in Azure public regions. The security.txt passed its Expires date on 2026-09-23 and was still expired on 6 November, which the Bedrock and S3 dossiers mark down by 2, applied here too (18 of 20, down from 20 on 6 October for consistency). | |||
| Payments & pricingchecked 6 November 2026 | 10%12.5 | 2.5 | |
| No x402, MPP or L402 (0). Per-1M-token prices are public in the Azure Retail Prices API without a login, while the pricing page fills its table with JavaScript and showed GPT-6 prices as pending on 6 October (20). The quota tiers include a Free tier, but an Azure subscription needs a payment method (0). A person signs up for Azure in a browser and creates a resource and a deployment before the first call (0). | |||
| Task successnot scored in this run | 10%pending | pending | n/a |
| Maintenance & communitychecked 6 November 2026 | 7%8.8 | 7.5 | |
Model reading. GPT-6.1 Terra released on Azure on 26 October 2026 and a gpt-chat-latest preview of 7 October was added, after GPT-6.1 Sol on 29 September (30). GA models get a retirement date 18 months after launch, set at release and readable through the Models API, with at least 60 days' email and Service Health notice, and previews at least 30 days, so a GA retirement is known more than six months ahead (12 of 12). Many shutdown dates in the 90 days to 6 November, most of them previews or partner models, among them DeepSeek-R1 (13 August), MAI-Image-2 and 2e (15 August), model-router previews (30 August), MAI-Transcribe-1 (15 September), MAI-Image-2.5 previews (1 October), the 2025-03-20 audio models and sora-2 (15 October), a Cohere Command A Plus preview (16 October) and gpt-image-1 (23 October), each in the schedule with a replacement where one exists (4 of 8). The Foundry what's new page, still on August when read on 6 November, plus Microsoft Q&A and paid support; no Azure OpenAI what's new was found (10 of 15). The SDKs are OpenAI's repositories, replies not sampled (5 of 10). Current official SDKs, openai 3.46.0 on PyPI (5 November) and 7.53.0 on npm, plus Microsoft's @azure/openai 2.0.0 companion (15). Supported runtimes stated, Python 3.9 or later and Node.js 20 or later, though openai 3.46.0 requires Python 3.10 (10). | |||
| Transparency & trusteditorial 77, provenance 88checked 6 November 2026 | 7%8.8 | 7.3 | |
Closed service under the Microsoft Product Terms, with the v1 spec under MIT and the OpenAI SDKs under Apache-2.0 (15). The data privacy page agrees with the product terms on no training and states where data is processed and stored by deployment type, but gives no retention period for the human-review store and sits beside a 30-day default for Responses data (24 of 30). A published lifecycle policy and a retirement schedule with dates and replacements, but on 6 November the schedule listed gpt-realtime-mini 2025-10-06 and 2025-12-15 twice each with different retirement dates, and no GPT-6 model yet (18 of 20, down from 20). Data locations stated for Standard, Data Zone and Global deployments, and a public sub-processor list per the 5 October Azure Speech check, not re-read (20). | |||
| Negative events | ≤15 | None recorded | 0 |
| Total | 80 · A | ||
Weight is the published weight, and the figure under it is that category's share of the 100 points in this run. A pending category has no score and adds nothing. What changes when it's scored.
Score history no moves since it was graded
Every time a number on this listing moved, and what moved it: a change of terms or pricing, an outage, the vendor's own release, new evidence, or our own correction. A score can't change without an entry here. Every listing's changes · JSON · RSS
-
Graded 80 A methodology v0.7
Fix list 19 items, the biggest gain first
Everything this grade says the listing lacks, from the reasons above, the checklist, the provenance checks, the deductions, what we couldn't check and what the review panel asked for, with the steps, ready to paste into a coding agent working on Azure OpenAI in Foundry Models. A fix counts at the next check, once it's public.
You're lucky. As part of the beta, your first month is free.
What we couldn't check
- Changed since 6 October 2026 (rechecked 6 November). GPT-6.1 Terra (26 October) and a
gpt-chat-latestpreview (7 October) added; GPT-6.1 Sol and Terra meters now in the Retail Prices API, closing the 6 October question; no new incident naming Azure OpenAI; security.txt still expired, now scored 18 of 20 as in the Bedrock dossier (security 97 to 95); duplicate, conflicting rows in the retirement schedule (transparency 79 to 77);gpt-4o2024-05-13 and thegpt-4.1family retire later than on 6 October - unchecked: the Online Services SLA document, which answered with an HTML page instead of the .docx on 6 October. The SLA line rests on the models page's statement and its link
- The input-token threshold between short-context and long-context GPT-6 pricing is on the pricing page, which needs JavaScript
- How long flagged prompts and completions stay in the human-review abuse store. The data privacy and abuse monitoring pages don't say
- The GPT-6 models aren't in the retirement schedule yet, so their retirement dates weren't seen
- unchecked: the v1 spec's last change date (the GitHub API wasn't available to us)
- unchecked: the sub-processor list, SOC 2 and ISO 27001 reports, per the 5 October Azure Speech check, not re-read
- Which
gpt-realtime-miniretirement date applies, since the schedule lists 2025-10-06 on both 2027-04-06 and 2026-09-21, and 2025-12-15 on both 2027-06-15 and 2026-12-15 - The supported-languages page said Python 3.9 or later on 6 October, while
openai3.46.0 requires Python 3.10; the page wasn't re-read on 6 November
Sources 23
- status history and post-incident reviews azure.status.microsoft · seen 2026-11-06
- v1 API and API version changelog learn.microsoft.com · seen 2026-10-06
- v1 OpenAPI spec raw.githubusercontent.com · seen 2026-10-06
- Foundry Models sold by Azure learn.microsoft.com · seen 2026-11-06
- quotas, limits and quota tiers learn.microsoft.com · seen 2026-10-06
- quota management, rate-limit headers and retry guidance learn.microsoft.com · seen 2026-10-06
- lifecycle and support policy learn.microsoft.com · seen 2026-10-06
- model retirement schedule learn.microsoft.com · seen 2026-11-06
- data, privacy and security learn.microsoft.com · seen 2026-11-06
- Responses API, storage and remote MCP approvals learn.microsoft.com · seen 2026-10-06
- prompt caching learn.microsoft.com · seen 2026-10-06
- structured outputs learn.microsoft.com · seen 2026-10-06
- batch learn.microsoft.com · seen 2026-10-06
- supported languages and SDK versions learn.microsoft.com · seen 2026-10-06
- Retail Prices API, GPT6 meters in East US 2 prices.azure.com · seen 2026-11-06
- pricing page (prices pending, JavaScript table) azure.microsoft.com · seen 2026-10-06
- Online Services SLA page microsoft.com · seen 2026-10-06
- FedRAMP and DoD audit scope learn.microsoft.com · seen 2026-10-06
- microsoft.com security.txt microsoft.com · seen 2026-11-06
- Foundry what's new, August 2026 learn.microsoft.com · seen 2026-11-06
- docs Markdown sources github.com · seen 2026-10-06
- openai on PyPI pypi.org · seen 2026-11-06
- @azure/openai on npm registry.npmjs.org · seen 2026-11-06
Probe metrics
Not measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. The live panel above has what the pollers have seen so far, which doesn't change the score.
Pricing & changes
Pay per use from $0.10 / 1M in Pay per token on an Azure subscription. Global Standard GPT-6 and GPT-6.1 prices match OpenAI's list (GPT-6.1 Sol $2/$10, GPT-6.1 Terra $1/$5 per million tokens), Data Zone costs 10% more, long-context requests cost 2x input and 1.5x output, cached input 0.1x, cache writes 1.25x, Flex half price and priority processing 2x (GPT-6 Sol). Batch is 50% off Global Standard. Provisioned throughput is billed per PTU hour. Prices from the Azure Retail Prices API, because the pricing page fills its table with JavaScript (checked 2026-11-06).
Models and prices per million tokens
| Model | Input | Output | Context | Role | Supports |
|---|---|---|---|---|---|
gpt-6-astraGPT-6 Astra · 2026-09 | $10 | $50 | 1.05M | flagship | not checked |
gpt-6-solGPT-6 Sol · 2026-09 | $2 | $10 | 1.05M | default | not checked |
gpt-6-lunaGPT-6 Luna · 2026-09 | $0.10 | $0.50 | 1.05M | fast | not checked |
Every model here is also on the price index next to the other providers. Rate limits depend on your account tier: Microsoft's rate limits.
What a task costs estimated, per task
| Model | Research report | Small website | Bug fix |
|---|---|---|---|
gpt-6-astrano cache price published, so cached reads are at the input price | $110 | $25.07 | $5.41 |
gpt-6-solno cache price published, so cached reads are at the input price | $21.94 | $5.01 | $1.08 |
gpt-6-lunano cache price published, so cached reads are at the input price | $1.10 | $0.25 | $0.05 |
Each figure is the same tokens priced at this model's rates, research report (134 fresh input, 207k cache writes, 10.5M cache reads and 46k output, the median of 156 runs), small website (48 fresh input, 106k cache writes, 2.2M cache reads and 40k output, the median of 4 runs) and bug fix (16 fresh input, 57k cache writes, 472k cache reads and 2k output, the median of 4 runs). We measured the tokens with Claude Opus 5.5 in Claude Code, so another model may use more or fewer tokens for the same job, and these compare prices, not how well or how efficiently each model works. Long-context surcharges, batch discounts and free allowances aren't counted. How we measured them.
Prices
| Item | Price | Unit | Note |
|---|---|---|---|
| GPT-6.1 Sol input, Global Standard | $2 | per 1M tokens | short context, Retail Prices API meter effective 2026-10-01 |
| GPT-6.1 Sol output, Global Standard | $10 | per 1M tokens | short context |
| GPT-6.1 Terra input, Global Standard | $1 | per 1M tokens | short context |
| GPT-6.1 Terra output, Global Standard | $5 | per 1M tokens | short context |
| GPT-6 Astra input, Global Standard | $10 | per 1M tokens | short context |
| GPT-6 Astra output, Global Standard | $50 | per 1M tokens | short context |
Compared across listings on the price index.
Dated changes shutdowns, breaking changes, price changes
- Shutdown
gpt-4.1-nano(2025-04-14) retires source - Shutdown
gpt-4o-transcribe,gpt-4o-mini-transcribeandgpt-4o-mini-tts(2025-03-20) retire source - Shutdown
o1,o1-pro,o3,o3-pro,o3-mini,o3-deep-researchando4-miniretire, replaced bygpt-5.6-solorgpt-5.6-terrasource - Shutdown
gpt-4o(2024-05-13) retires, replaced bygpt-5.6-solsource
All of these, for every listing, are on Sunsets and in the calendar feed.
Recent changes
gpt-4o(2024-05-13) retires, replaced bygpt-5.6-solsourceo1,o1-pro,o3,o3-pro,o3-mini,o3-deep-researchando4-miniretire, replaced bygpt-5.6-solorgpt-5.6-terrasource- security.txt on microsoft.com is valid, the listing says expired source
- Latest release
gpt-4o-transcribe,gpt-4o-mini-transcribeandgpt-4o-mini-tts(2025-03-20) retire sourcegpt-4.1-nano(2025-04-14) retires source
Follow them as a feed at /feeds/tools/azure-openai.xml, or this listing's score history at history.json.
Connect
Install
pip install openai azure-identity # or: npm i openai @azure/identityFirst request
curl "https://$AZURE_OPENAI_RESOURCE.openai.azure.com/openai/v1/responses" \
-H "api-key: $AZURE_OPENAI_API_KEY" -H "content-type: application/json" \
-d '{"model":"<your-deployment-name>","input":"hello"}'Alternatives to Azure OpenAI in Foundry Models
#4 of 42 in Best model APIs and inference for AI agents · All 830 models comparisons
Vertex AI (Gemini Enterprise Agent Platform) AAAmazon Bedrock AGroqCloud BBFireworks AI Inference BCloudflare Workers AI BCerebras Inference B
Head to head Amazon Bedrock vs Azure OpenAI in Foundry Models · Claude API vs Azure OpenAI in Foundry Models · Antseed vs Azure OpenAI in Foundry Models · Azure OpenAI in Foundry Models vs BlockRun.AI · Azure OpenAI in Foundry Models vs Cerebras Inference · Azure OpenAI in Foundry Models vs Cloudflare AI Gateway · Azure OpenAI in Foundry Models vs Cloudflare Workers AI · Azure OpenAI in Foundry Models vs Cohere Chat API (Command models) · Azure OpenAI in Foundry Models vs DeepInfra · Azure OpenAI in Foundry Models vs DeepSeek API · Azure OpenAI in Foundry Models vs Eden AI · Azure OpenAI in Foundry Models vs Glimpse · Azure OpenAI in Foundry Models vs Fireworks AI Inference · Azure OpenAI in Foundry Models vs Gemini Developer API · Azure OpenAI in Foundry Models vs GroqCloud · Azure OpenAI in Foundry Models vs Hugging Face Inference Providers · Azure OpenAI in Foundry Models vs Inkling 2 Small · Azure OpenAI in Foundry Models vs Jais 3 · Azure OpenAI in Foundry Models vs Meta Model API · Azure OpenAI in Foundry Models vs MiniMax API · Azure OpenAI in Foundry Models vs Mistral AI API · Azure OpenAI in Foundry Models vs Muse Spark Open · Azure OpenAI in Foundry Models vs Nemotron 3.5 Super VL · Azure OpenAI in Foundry Models vs Novita AI · Azure OpenAI in Foundry Models vs OpenAI API · Azure OpenAI in Foundry Models vs OpenRouter · Azure OpenAI in Foundry Models vs Prism Inference · Azure OpenAI in Foundry Models vs Router.com (Ramp Router) · Azure OpenAI in Foundry Models vs Beam 1.0 · Azure OpenAI in Foundry Models vs RouterPlus · Azure OpenAI in Foundry Models vs SambaCloud · Azure OpenAI in Foundry Models vs SiliconFlow · Azure OpenAI in Foundry Models vs Simplismart · Azure OpenAI in Foundry Models vs StepFun API · Azure OpenAI in Foundry Models vs SWE-2 Flash · Azure OpenAI in Foundry Models vs Tencent Cloud TokenHub · Azure OpenAI in Foundry Models vs Together AI Inference · Azure OpenAI in Foundry Models vs Vercel AI Gateway · Azure OpenAI in Foundry Models vs Vertex AI (Gemini Enterprise Agent Platform) · Azure OpenAI in Foundry Models vs xAI API (Grok)
Machine-readable
| Similar tool | Grade | Score | Shared capabilities | x402 |
|---|---|---|---|---|
| Vertex AI (Gemini Enterprise Agent Platform) Google Cloud | AA | 88.7 | inference.llm inference.open-weights | no |
| Amazon Bedrock Amazon Web Services | A | 81.7 | inference.llm inference.open-weights | no |
| GroqCloud Groq | BB | 74.5 | inference.llm inference.open-weights | no |
| Fireworks AI Inference Fireworks.ai, Inc. | B | 69.3 | inference.llm inference.open-weights | no |
| Cloudflare Workers AI Cloudflare, Inc. | B | 69.2 | inference.llm inference.open-weights | partial |
| Cerebras Inference Cerebras Systems Inc. | B | 68.6 | inference.llm inference.open-weights | no |
Machine-readable
- JSON
/api/v1/tools/azure-openai.json· historyhistory.json· badge/badges/azure-openai.svg· changes feed/feeds/tools/azure-openai.xml - Markdown
/tools/azure-openai.md· slim/tools/azure-openai.min.md(or sendAccept: text/markdown) - What the fix list covers
/fixes/azure-openai.md·/fixes/azure-openai.json· the whole listPOST /api/v1/fix-list - From a terminal
anchor tool azure-openai --md(the CLI) · over MCPget_tool {"slug": "azure-openai"}at/mcp, no key - Directory index
/api/v1/tools.json· site index/llms.txt - No HTTP
dig +short TXT azure-openai.grade.anchorterminal.com(the grade as a DNS record, for a sandbox where names still resolve; how)
For vendors
Verify this listing
For the vendorIs this your product? Link to this page from your own site or README, then tell us where. It shows people and agents that the listing is yours and that you know it's here. It never changes a grade, rank or review.
-
Add the badge or a link
On a light page On a dark page <a href="https://www.anchorterminal.com/tools/azure-openai"><img src="https://www.anchorterminal.com/badges/azure-openai.svg" alt="Azure OpenAI in Foundry Models on Anchor Terminal" height="20"></a>[](https://www.anchorterminal.com/tools/azure-openai)<a href="https://www.anchorterminal.com/tools/azure-openai">Azure OpenAI in Foundry Models on Anchor Terminal</a>It counts on a page on microsoft.com or one of its subdomains, or the README at the root of github.com/Azure/azure-rest-api-specs.
-
Tell us where it is
We read it once now and again every week. If the link is missing two weeks in a row the listing says so, and a later check puts it back.
Agents send the same to POST /api/v1/verify as {"slug": "azure-openai", "url": "…"}, or call the verify_listing tool at /mcp. Ten checks an hour from one address. What we check. To announce the listing, get sharing assets for social media.
Share this listing
For the vendorGet sharing assets for social media. Two images say Azure OpenAI in Foundry Models is listed on Anchor Terminal, with your logo and this page's address, one for a dark feed and one for a light one. They carry no grade or score, so they stay right when a score moves.
Link the post to https://www.anchorterminal.com/tools/azure-openai. The logo is the one on this listing. If it's wrong or out of date, send us the right one.