# Azure OpenAI in Foundry Models > 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. - Canonical: https://www.anchorterminal.com/tools/azure-openai - Pricing: https://www.anchorterminal.com/tools/azure-openai#pricing - Reviews: https://www.anchorterminal.com/tools/azure-openai#reviews - Markdown: https://www.anchorterminal.com/tools/azure-openai.md (~11,700 tokens) - Slim: https://www.anchorterminal.com/tools/azure-openai.min.md (~1,830 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/azure-openai.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key) - DNS: dig +short TXT azure-openai.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.. and .vs.. under the zone, and the same under grade.letme.dev) - Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data) - Updated: 2026-11-07 ## Overview **Grade A · 80/100 · rank #14 of 1486 · #4 in Model APIs & inference · agent-ready · confidence medium** More from Microsoft, listed separately because each is its own product: [Microsoft Foundry fine-tuning (Azure OpenAI)](https://www.anchorterminal.com/tools/azure-foundry-fine-tuning.md) (Fine-tuning), [Azure AI Content Safety (Prompt Shields)](https://www.anchorterminal.com/tools/azure-ai-content-safety.md) (Guardrails & safety filters), [Azure AI Speech speech-to-text](https://www.anchorterminal.com/tools/azure-speech-to-text.md) (Speech-to-text), [Azure AI Speech text-to-speech](https://www.anchorterminal.com/tools/azure-text-to-speech.md) (Text-to-speech), [Microsoft Agent Framework](https://www.anchorterminal.com/tools/microsoft-agent-framework.md) (Agent frameworks & SDKs), [Microsoft Execution Containers](https://www.anchorterminal.com/tools/microsoft-execution-containers.md) (Code execution sandboxes), [Microsoft Entra Agent ID](https://www.anchorterminal.com/tools/microsoft-entra-agent-id.md) (Agent auth & delegated access), [Azure Key Vault](https://www.anchorterminal.com/tools/azure-key-vault.md) (Secrets & credential vaults), [Grounding with Bing Search](https://www.anchorterminal.com/tools/bing-grounding.md) (Web search APIs), [Azure Document Intelligence](https://www.anchorterminal.com/tools/azure-document-intelligence.md) (Document parsing & extraction), [Azure DevOps MCP Server](https://www.anchorterminal.com/tools/azure-devops-mcp.md) (Code & developer platforms), [Microsoft Learn MCP Server](https://www.anchorterminal.com/tools/microsoft-learn-mcp.md) (Code & developer platforms), [TokenEconomizer](https://www.anchorterminal.com/tools/tokeneconomizer.md) (Code & developer platforms), [Playwright MCP](https://www.anchorterminal.com/tools/playwright-mcp.md) (Browser automation), [Azure MCP Server](https://www.anchorterminal.com/tools/azure-mcp.md) (Cloud & infrastructure), [Azure Maps](https://www.anchorterminal.com/tools/azure-maps.md) (Maps, geocoding & places), [Azure Translator](https://www.anchorterminal.com/tools/azure-translator.md) (Translation), [Microsoft Graph Calendar API](https://www.anchorterminal.com/tools/microsoft-graph-calendar.md) (Calendars & scheduling), [Azure Blob Storage](https://www.anchorterminal.com/tools/azure-blob-storage.md) (File storage & sharing), [OneDrive and SharePoint files (Microsoft Graph)](https://www.anchorterminal.com/tools/onedrive-sharepoint.md) (File storage & sharing), [Microsoft Teams (Microsoft Graph)](https://www.anchorterminal.com/tools/microsoft-teams.md) (Work & productivity), [Microsoft Dynamics 365 Sales](https://www.anchorterminal.com/tools/dynamics-365-sales.md) (CRM & customer platforms), [Microsoft Copilot Studio MCP](https://www.anchorterminal.com/tools/copilot-studio-mcp.md) (Workflow automation), [Microsoft Power Automate](https://www.anchorterminal.com/tools/power-automate.md) (Workflow automation), [Foundry Local](https://www.anchorterminal.com/tools/foundry-local.md) (Local AI), [Microsoft-Decision-1](https://www.anchorterminal.com/tools/microsoft-decision-1.md) (Decision models), [Microsoft Advertising API](https://www.anchorterminal.com/tools/microsoft-advertising-api.md) (Advertising & campaign operations), [Microsoft Excel (Microsoft Graph workbook API)](https://www.anchorterminal.com/tools/microsoft-excel-graph.md) (Spreadsheets & operational tables), [Outlook Mail (Microsoft Graph)](https://www.anchorterminal.com/tools/outlook-mail-graph.md) (Mailbox access), [Microsoft Graph People and Contacts API](https://www.anchorterminal.com/tools/microsoft-graph-people.md) (Contacts & address books), [Mage-VL-Cowork](https://www.anchorterminal.com/tools/mage-vl-cowork.md) (Desktop & mobile app control). ## 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 | Field | Value | | --- | --- | | Vendor | Microsoft (https://azure.microsoft.com) | | Kind | Model API | | Category | Model APIs & inference (https://www.anchorterminal.com/categories/inference) | | Transport | HTTP | | Endpoint | `https://.openai.azure.com/openai/v1` | | Auth | OAuth or key · `api-key` header with one of the resource's two regenerable keys, or a Microsoft Entra ID bearer token (scope https://ai.azure.com/.default) with the Cognitive Services OpenAI User role. Key authentication can be disabled per resource (`disableLocalAuth`). Each model must be deployed in the resource before it can be called, by deployment name. | | Pricing | 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). | | x402 | No · No x402, MPP or L402 in the Foundry docs, the v1 OpenAPI spec or the pricing page. Access needs an Azure subscription with a payment method (checked 2026-11-06). | | 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 | | Packages | pypi: `openai`; npm: `openai`; npm: `@azure/openai` | | Source | https://github.com/Azure/azure-rest-api-specs | | Docs | https://learn.microsoft.com/en-us/azure/foundry/openai/ | | llms.txt | not found | | Last release | 2026-10-26 | | npm downloads / week | 454,039 | | 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://.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 `store` is 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 | | Capabilities | inference.llm, inference.open-weights | | Tags | official, hosted, model, card-required, openapi, openai-compatible, closed-source, enterprise, eu, python, typescript, status-page, bug-bounty | | JSON | https://www.anchorterminal.com/api/v1/tools/azure-openai.json | ## Score breakdown (methodology v0.7, October 2026 research run) Assessed 2026-11-06 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. "This run" is each category's share of the 100 points. | Category | Weight | This run | Score (0–100) | Points | | --- | --- | --- | --- | --- | | Reliability | 16% | 20 | 80 | 16.0 | | Performance | 10% | pending | pending | n/a | | Schema & documentation | 13% | 16.2 | 87 | 14.1 | | Agent ergonomics | 13% | 16.2 | 98 | 15.9 | | Security & auth | 14% | 17.5 | 95 | 16.6 | | Payments & pricing | 10% | 12.5 | 20 | 2.5 | | Task success | 10% | pending | pending | n/a | | Maintenance & community | 7% | 8.8 | 86 | 7.5 | | Transparency & trust (editorial 77, provenance 88) | 7% | 8.8 | 83 | 7.3 | | Negative events | up to −15 | up to −15 | none recorded | 0 | | **Total** | | | | **80 → A** | ### Why each score - Reliability 80 (checked 2026-11-06): 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). - Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes. - Schema & documentation 87 (checked 2026-11-06): 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 ergonomics 98 (checked 2026-11-06): 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 & auth 95 (checked 2026-11-06): 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 & pricing 20 (checked 2026-11-06): 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 success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored. - Maintenance & community 86 (checked 2026-11-06): 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 & trust 83 (checked 2026-11-06): 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). Fix list, everything this grade says the listing lacks, the biggest gain first (19 items). What it covers is at https://www.anchorterminal.com/fixes/azure-openai.md (JSON https://www.anchorterminal.com/fixes/azure-openai.json). The whole list for a coding agent comes from `POST https://www.anchorterminal.com/api/v1/fix-list` with `{"listing": "azure-openai", "plan": "read"}`, free while the beta runs ### What we couldn't check - Changed since 6 October 2026 (rechecked 6 November). GPT-6.1 Terra (26 October) and a `gpt-chat-latest` preview (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-4o` 2024-05-13 and the `gpt-4.1` family 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-mini` retirement 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 `openai` 3.46.0 requires Python 3.10; the page wasn't re-read on 6 November ### Sources - status history and post-incident reviews: (seen 2026-11-06) - v1 API and API version changelog: (seen 2026-10-06) - v1 OpenAPI spec: (seen 2026-10-06) - Foundry Models sold by Azure: (seen 2026-11-06) - quotas, limits and quota tiers: (seen 2026-10-06) - quota management, rate-limit headers and retry guidance: (seen 2026-10-06) - lifecycle and support policy: (seen 2026-10-06) - model retirement schedule: (seen 2026-11-06) - data, privacy and security: (seen 2026-11-06) - Responses API, storage and remote MCP approvals: (seen 2026-10-06) - prompt caching: (seen 2026-10-06) - structured outputs: (seen 2026-10-06) - batch: (seen 2026-10-06) - supported languages and SDK versions: (seen 2026-10-06) - Retail Prices API, GPT6 meters in East US 2: (seen 2026-11-06) - pricing page (prices pending, JavaScript table): (seen 2026-10-06) - Online Services SLA page: (seen 2026-10-06) - FedRAMP and DoD audit scope: (seen 2026-10-06) - microsoft.com security.txt: (seen 2026-11-06) - Foundry what's new, August 2026: (seen 2026-11-06) - docs Markdown sources: (seen 2026-10-06) - openai on PyPI: (seen 2026-11-06) - @azure/openai on npm: (seen 2026-11-06) ## Score history Every move of a score since the listing was graded, newest first, with its cause. A score can't move without an entry here. JSON: https://www.anchorterminal.com/api/v1/tools/azure-openai/history.json - 2026-11-06: graded 80 A (methodology 0.7) ## Who's behind it (provenance 88/100, checked 2026-11-06) | Check | Finding | Points | | --- | --- | --- | | Legal entity named | Microsoft Corporation | 20/20 | | Domain age | microsoft.com, registered 1991-05-02 (35 years) | 15/15 | | Endpoint on the vendor's domain | .openai.azure.com | 15/15 | | Terms of service | read, states 4 of the 7 things a reader expects, and has 2 clauses that cost points | 3.4/10 | | Privacy policy | read, states 8 of the 8 things a reader expects, and has 1 clause that costs points | 8/10 | | Status page | azure.status.microsoft/en-us/status | 10/10 | | Changelog | published | 10/10 | | security.txt | published but past its Expires date | 5/10 | | People named | 4 named with their role, 1 with a public profile | 10/10 | | Support route | help pages | 5/5 | 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. ### Terms and privacy, as read A reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice. **Terms of service** (https://www.microsoft.com/licensing/terms/product/ForOnlineServices/all), read 2026-10-08, gives no date, states 4 of the 7 things a reader expects. - To know. Restricts automated access (costs points). "Customer may not use web scraping, web harvesting, or other data extraction methods to extract data from a Microsoft Generative AI Service." - To know. Restricts benchmarking or competitive use (costs 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." - Not found in the text. Gives the date it was last updated. - Not found in the text. Names the governing law or courts. - Not found in the text. Says how changes to the terms are announced. - Also in the text (2026-10-08). 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." - Also in the text (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." - Also in the text (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." **Privacy policy** (https://privacy.microsoft.com/en-us/privacystatement), read 2026-10-08, dated 2026-09-01, states 8 of the 8 things a reader expects. - To know. Says it may use customer content to train or improve models, and no opt-out was found (costs points). "As part of our efforts to improve and develop our products, we may use your data to develop and train our AI models." - To know. Says it sells personal data or shares it for advertising. "We also disclose personal data for digital advertising purposes." - Gives the date it was last updated. Last updated 2026-09-01. - Says how long data is kept. Names a period of 7 days. - Gives a privacy contact. Names a data protection officer. - Says where data is transferred or stored. Relies on standard contractual clauses. - Also in the text (2026-10-08). 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." - Also in the text (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." - Also in the text (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." ## Humans behind the project (researched 2026-11-06 from public pages, not part of the grade) ### Key people - Bill Gates, Co-founder and technical adviser, Microsoft. LinkedIn: https://www.linkedin.com/in/williamhgates. X: https://x.com/BillGates - Paul Allen, Co-founder, Microsoft, left day-to-day work there in 1983 - Satya Nadella, Chairman and CEO, Microsoft - Kevin Scott, Chief Technology Officer, Microsoft - Note: 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. - Microsoft: LinkedIn https://www.linkedin.com/company/microsoft X https://x.com/Microsoft ### Ownership and investors - Ownership: Public company (NASDAQ: MSFT) ### Getting support - Help: https://azure.microsoft.com/en-us/support/ - Help: https://support.microsoft.com/en-us - Sources: https://www.gatesfoundation.org/about/leadership/bill-gates, https://www.gatesfoundation.org/about/verified-accounts, https://www.linkedin.com/company/microsoft/, https://x.com/Microsoft/with_replies, https://azure.microsoft.com/en-us/support/, https://support.microsoft.com/en-us ## Live (updated 2026-11-07 17:49 UTC) - Right now: down, n/a, checked 2026-11-07 17:49 UTC (get on `https://.openai.azure.com/openai/v1`) - Uptime 24h 0.0% (195 probes) · 30 days 0.0% (195 probes) · p50 n/a · p95 n/a - npm `@azure/openai` 2.0.0 - npm `openai` 7.53.0 - pypi `openai` 3.46.0, released 2026-11-05 - security.txt: valid, expires 2027-10-27T16:00:00.000Z - Watching deprecations - Always current: https://www.anchorterminal.com/api/v1/live/azure-openai.json ## 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. Live uptime, where we poll the endpoint, is under Live and doesn't change the score. ## Models and prices (per 1M tokens) | Model | Input | Output | Context | Role | Supports | | --- | --- | --- | --- | --- | --- | | `gpt-6-astra` GPT-6 Astra | $10 | $50 | 1.05M | flagship | not checked | | `gpt-6-sol` GPT-6 Sol | $2 | $10 | 1.05M | default | not checked | | `gpt-6-luna` GPT-6 Luna | $0.10 | $0.50 | 1.05M | fast | not checked | Rate limits depend on your account tier: https://learn.microsoft.com/en-us/azure/foundry/openai/quotas-limits ## What a task costs (estimated, per task) | Model | Research report | Small website | Bug fix | | --- | --- | --- | --- | | `gpt-6-astra` (no cache price published, cached reads at the input price) | $110 | $25.07 | $5.41 | | `gpt-6-sol` (no cache price published, cached reads at the input price) | $21.94 | $5.01 | $1.08 | | `gpt-6-luna` (no cache price published, cached reads 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: https://www.anchorterminal.com/prices/index.md ## 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 | Across all listings: https://www.anchorterminal.com/prices/index.md ## Dated changes - 2026-10-14 · Shutdown · `gpt-4.1-nano` (2025-04-14) retires (source: ) - 2026-10-15 · Shutdown · `gpt-4o-transcribe`, `gpt-4o-mini-transcribe` and `gpt-4o-mini-tts` (2025-03-20) retire (source: ) - 2026-11-19 · Shutdown · `o1`, `o1-pro`, `o3`, `o3-pro`, `o3-mini`, `o3-deep-research` and `o4-mini` retire, replaced by `gpt-5.6-sol` or `gpt-5.6-terra` (source: ) - 2026-12-09 · Shutdown · `gpt-4o` (2024-05-13) retires, replaced by `gpt-5.6-sol` (source: ) All listings, as a calendar: https://www.anchorterminal.com/sunsets.ics ## 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/$0.50 per million tokens on Global Standard ## Weaknesses - Intermittent failures and 5xx errors in Sweden Central for about six hours on 29 September 2026 - An Azure subscription with a card, a resource and a model deployment come before the first call - No llms.txt, and no Azure OpenAI what's new page was found; the Foundry one still covered August on 6 November - No retention period stated for prompts kept for human abuse review, and Responses data is kept 30 days by default - The retirement schedule lists two `gpt-realtime-mini` versions twice with different retirement dates, and no GPT-6 retirement dates yet ## Before you call it (notes for agents) 1. Point the OpenAI SDK at https://.openai.azure.com/openai/v1/ and pass the deployment name as `model`, not the model id 2. Prefer Entra ID with the Cognitive Services OpenAI User role over the resource key, which opens the whole data plane 3. On 429 wait for `retry-after-ms`, then back off with jitter. The OpenAI SDK retries twice by default 4. Set `store: false` on Responses calls you don't need kept. Stored responses persist 30 days by default 5. Keep remote MCP approvals on for servers you don't control. They're required by default ## Connect Install: ```bash pip install openai azure-identity # or: npm i openai @azure/identity ``` First request: ```bash curl "https://$AZURE_OPENAI_RESOURCE.openai.azure.com/openai/v1/responses" \ -H "api-key: $AZURE_OPENAI_API_KEY" -H "content-type: application/json" \ -d '{"model":"","input":"hello"}' ``` ## Similar tools Ranked by shared capabilities, then score. Same-category tools with no shared capability key are listed last. | Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown | | --- | --- | --- | --- | --- | --- | --- | | Vertex AI (Gemini Enterprise Agent Platform) | AA | 88.7 | 2 | inference.llm, inference.open-weights | no | https://www.anchorterminal.com/tools/vertex-ai.md | | Amazon Bedrock | A | 81.7 | 8 | inference.llm, inference.open-weights | no | https://www.anchorterminal.com/tools/amazon-bedrock.md | | GroqCloud | BB | 74.5 | 81 | inference.llm, inference.open-weights | no | https://www.anchorterminal.com/tools/groq.md | | Fireworks AI Inference | B | 69.3 | 250 | inference.llm, inference.open-weights | no | https://www.anchorterminal.com/tools/fireworks-inference.md | | Cloudflare Workers AI | B | 69.2 | 255 | inference.llm, inference.open-weights | no | https://www.anchorterminal.com/tools/cloudflare-workers-ai.md | | Cerebras Inference | B | 68.6 | 277 | inference.llm, inference.open-weights | no | https://www.anchorterminal.com/tools/cerebras-inference.md | ## Panel reviews (0) Reviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): . Desk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md ## Notable - The v1 API (GA) takes the OpenAI client with `base_url` set to https://.openai.azure.com/openai/v1/, with no monthly `api-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-latest` preview 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_approval` is 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-mini` 2025-10-06 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: ) - #4 of 42 in Best model APIs and inference for AI agents: https://www.anchorterminal.com/best/inference/index.md - All 830 models comparisons: https://www.anchorterminal.com/compare/inference/index.md ## Compare - [Amazon Bedrock vs Azure OpenAI in Foundry Models](https://www.anchorterminal.com/compare/amazon-bedrock-vs-azure-openai.md): A 81.7 vs A 80 - [Claude API vs Azure OpenAI in Foundry Models](https://www.anchorterminal.com/compare/anthropic-api-vs-azure-openai.md): BB 77.3 vs A 80 - [Antseed vs Azure OpenAI in Foundry Models](https://www.anchorterminal.com/compare/antseed-vs-azure-openai.md): C 54.1 vs A 80 - [Azure OpenAI in Foundry Models vs BlockRun.AI](https://www.anchorterminal.com/compare/azure-openai-vs-blockrun-ai.md): A 80 vs A 78.9 - [Azure OpenAI in Foundry Models vs Cerebras Inference](https://www.anchorterminal.com/compare/azure-openai-vs-cerebras-inference.md): A 80 vs B 68.6 - [Azure OpenAI in Foundry Models vs Cloudflare AI Gateway](https://www.anchorterminal.com/compare/azure-openai-vs-cloudflare-ai-gateway.md): A 80 vs B 67.8 - [Azure OpenAI in Foundry Models vs Cloudflare Workers AI](https://www.anchorterminal.com/compare/azure-openai-vs-cloudflare-workers-ai.md): A 80 vs B 69.2 - [Azure OpenAI in Foundry Models vs Cohere Chat API (Command models)](https://www.anchorterminal.com/compare/azure-openai-vs-cohere-chat.md): A 80 vs B 65.6 - [Azure OpenAI in Foundry Models vs DeepInfra](https://www.anchorterminal.com/compare/azure-openai-vs-deepinfra.md): A 80 vs B 63.7 - [Azure OpenAI in Foundry Models vs DeepSeek API](https://www.anchorterminal.com/compare/azure-openai-vs-deepseek-api.md): A 80 vs D 46.7 - [Azure OpenAI in Foundry Models vs Eden AI](https://www.anchorterminal.com/compare/azure-openai-vs-eden-ai.md): A 80 vs C 59.9 - [Azure OpenAI in Foundry Models vs Glimpse](https://www.anchorterminal.com/compare/azure-openai-vs-elorian-glimpse.md): A 80 vs F 35.1 - [Azure OpenAI in Foundry Models vs Fireworks AI Inference](https://www.anchorterminal.com/compare/azure-openai-vs-fireworks-inference.md): A 80 vs B 69.3 - [Azure OpenAI in Foundry Models vs Gemini Developer API](https://www.anchorterminal.com/compare/azure-openai-vs-gemini-api.md): A 80 vs B 62.2 - [Azure OpenAI in Foundry Models vs GroqCloud](https://www.anchorterminal.com/compare/azure-openai-vs-groq.md): A 80 vs BB 74.5 - [Azure OpenAI in Foundry Models vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/azure-openai-vs-hugging-face-inference-providers.md): A 80 vs C 54 - [Azure OpenAI in Foundry Models vs Inkling 2 Small](https://www.anchorterminal.com/compare/azure-openai-vs-inkling-2-small.md): A 80 vs D 52.1 - [Azure OpenAI in Foundry Models vs Jais 3](https://www.anchorterminal.com/compare/azure-openai-vs-jais-3.md): A 80 vs D 52.1 - [Azure OpenAI in Foundry Models vs Meta Model API](https://www.anchorterminal.com/compare/azure-openai-vs-meta-model-api.md): A 80 vs D 52.3 - [Azure OpenAI in Foundry Models vs MiniMax API](https://www.anchorterminal.com/compare/azure-openai-vs-minimax-api.md): A 80 vs C 55.3 - [Azure OpenAI in Foundry Models vs Mistral AI API](https://www.anchorterminal.com/compare/azure-openai-vs-mistral-api.md): A 80 vs B 65.7 - [Azure OpenAI in Foundry Models vs Muse Spark Open](https://www.anchorterminal.com/compare/azure-openai-vs-muse-spark-open.md): A 80 vs D 53.4 - [Azure OpenAI in Foundry Models vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/azure-openai-vs-nemotron-3-5-super-vl.md): A 80 vs C 59.3 - [Azure OpenAI in Foundry Models vs Novita AI](https://www.anchorterminal.com/compare/azure-openai-vs-novita-ai.md): A 80 vs D 53.9 - [Azure OpenAI in Foundry Models vs OpenAI API](https://www.anchorterminal.com/compare/azure-openai-vs-openai-api.md): A 80 vs A 83.9 - [Azure OpenAI in Foundry Models vs OpenRouter](https://www.anchorterminal.com/compare/azure-openai-vs-openrouter.md): A 80 vs B 66.6 - [Azure OpenAI in Foundry Models vs Prism Inference](https://www.anchorterminal.com/compare/azure-openai-vs-prism-inference.md): A 80 vs C 59.6 - [Azure OpenAI in Foundry Models vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/azure-openai-vs-ramp-router.md): A 80 vs D 53.7 - [Azure OpenAI in Foundry Models vs Beam 1.0](https://www.anchorterminal.com/compare/azure-openai-vs-reflection-beam.md): A 80 vs D 53.4 - [Azure OpenAI in Foundry Models vs RouterPlus](https://www.anchorterminal.com/compare/azure-openai-vs-routerplus.md): A 80 vs D 50.3 - [Azure OpenAI in Foundry Models vs SambaCloud](https://www.anchorterminal.com/compare/azure-openai-vs-sambanova.md): A 80 vs B 64.9 - [Azure OpenAI in Foundry Models vs SiliconFlow](https://www.anchorterminal.com/compare/azure-openai-vs-siliconflow.md): A 80 vs E 42.9 - [Azure OpenAI in Foundry Models vs Simplismart](https://www.anchorterminal.com/compare/azure-openai-vs-simplismart.md): A 80 vs F 29.5 - [Azure OpenAI in Foundry Models vs StepFun API](https://www.anchorterminal.com/compare/azure-openai-vs-stepfun-api.md): A 80 vs E 44.3 - [Azure OpenAI in Foundry Models vs SWE-2 Flash](https://www.anchorterminal.com/compare/azure-openai-vs-swe-2-flash.md): A 80 vs F 36.4 - [Azure OpenAI in Foundry Models vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/azure-openai-vs-tencent-tokenhub.md): A 80 vs C 59.5 - [Azure OpenAI in Foundry Models vs Together AI Inference](https://www.anchorterminal.com/compare/azure-openai-vs-together-inference.md): A 80 vs B 67.8 - [Azure OpenAI in Foundry Models vs Vercel AI Gateway](https://www.anchorterminal.com/compare/azure-openai-vs-vercel-ai-gateway.md): A 80 vs B 67.8 - [Azure OpenAI in Foundry Models vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/azure-openai-vs-vertex-ai.md): A 80 vs AA 88.7 - [Azure OpenAI in Foundry Models vs xAI API (Grok)](https://www.anchorterminal.com/compare/azure-openai-vs-xai-api.md): A 80 vs BB 71.7 ## Verify this listing For the vendor. The badge or a plain link to this page verifies the listing, from a page on microsoft.com or one of its subdomains, or the README at the root of github.com/Azure/azure-rest-api-specs. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{"slug": "azure-openai", "url": "…"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify HTML badge: ```html Azure OpenAI in Foundry Models on Anchor Terminal ``` Markdown badge, for a README: ```markdown [![Azure OpenAI in Foundry Models on Anchor Terminal](https://www.anchorterminal.com/badges/azure-openai.svg)](https://www.anchorterminal.com/tools/azure-openai) ``` Plain link: ```html Azure OpenAI in Foundry Models on Anchor Terminal ``` ## Share this listing For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Azure OpenAI in Foundry Models is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score. - Dark: https://www.anchorterminal.com/assets/share/azure-openai-dark.png - Light: https://www.anchorterminal.com/assets/share/azure-openai-light.png --- Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp