# Azure OpenAI in Foundry Models (slim)

> 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.

- Full: https://www.anchorterminal.com/tools/azure-openai.md (~11,700 tokens) · this version ~1,830 tokens · JSON https://www.anchorterminal.com/tools/azure-openai.json · canonical https://www.anchorterminal.com/tools/azure-openai
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07 · pricing https://www.anchorterminal.com/tools/azure-openai#pricing · reviews https://www.anchorterminal.com/tools/azure-openai#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**A · 80/100 · rank #14 of 1486 · #4 in Model APIs & inference · agent-ready · confidence medium**


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

- Kind: Model API · vendor: Microsoft · category: Model APIs & inference · legal entity: Microsoft Corporation · provenance 88/100
- Endpoint: `https://<resource>.openai.azure.com/openai/v1` (HTTP)
- Auth: OAuth or key · pricing: Pay per use · 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
- Benchmark probes: not run yet, so Performance is pending
- Live, from our pollers (not part of the score): down at 2026-11-07 17:49 UTC · uptime 30 days 0.0% (195 probes) · p50 n/a · p95 n/a over 24 hours
- 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 `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
- Models ($/1M in/out): `gpt-6-astra` $10/$50; `gpt-6-sol` $2/$10; `gpt-6-luna` $0.10/$0.50
- Prices: GPT-6.1 Sol input, Global Standard $2 per 1M tokens; GPT-6.1 Sol output, Global Standard $10 per 1M tokens; GPT-6.1 Terra input, Global Standard $1 per 1M tokens; GPT-6.1 Terra output, Global Standard $5 per 1M tokens; GPT-6 Astra input, Global Standard $10 per 1M tokens; GPT-6 Astra output, Global Standard $50 per 1M tokens
- 2026-10-14 Shutdown: `gpt-4.1-nano` (2025-04-14) retires
- 2026-10-15 Shutdown: `gpt-4o-transcribe`, `gpt-4o-mini-transcribe` and `gpt-4o-mini-tts` (2025-03-20) retire
- 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`
- 2026-12-09 Shutdown: `gpt-4o` (2024-05-13) retires, replaced by `gpt-5.6-sol`

- Scores: Reliability 80, Performance pending, Schema & documentation 87, Agent ergonomics 98, Security & auth 95, Payments & pricing 20, Task success pending, Maintenance & community 86, Transparency & trust 83 · total over the 7 assessed categories
- Why: Reliability, Azure status page with post-incident reviews, listing Azure OpenAI Service, Foundry Models and Foundry Agent Service as components (20). · Schema & documentation, 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 t… · Agent ergonomics, Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). · Security & auth, Model reading. · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, Model reading. · Transparency & trust, Closed service under the Microsoft Product Terms, with the v1 spec under MIT and the OpenAI SDKs under Apache-2.0 (15).
- Sources: 23, open questions: 9, both in the full twin
- Capabilities: inference.llm, inference.open-weights
- JSON: https://www.anchorterminal.com/api/v1/tools/azure-openai.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/azure-openai.svg` or a link to https://www.anchorterminal.com/tools/azure-openai 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, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.
- Support: https://azure.microsoft.com/en-us/support/; https://support.microsoft.com/en-us; more in the full twin

## Before you call it

1. Point the OpenAI SDK at https://<resource>.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

```bash
pip install openai azure-identity   # or: npm i openai @azure/identity
```

```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":"<your-deployment-name>","input":"hello"}'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Vertex AI (Gemini Enterprise Agent Platform) | AA | 88.7 | inference.llm, inference.open-weights | https://www.anchorterminal.com/tools/vertex-ai.min.md |
| Amazon Bedrock | A | 81.7 | inference.llm, inference.open-weights | https://www.anchorterminal.com/tools/amazon-bedrock.min.md |
| GroqCloud | BB | 74.5 | inference.llm, inference.open-weights | https://www.anchorterminal.com/tools/groq.min.md |
| Fireworks AI Inference | B | 69.3 | inference.llm, inference.open-weights | https://www.anchorterminal.com/tools/fireworks-inference.min.md |
| Cloudflare Workers AI | B | 69.2 | inference.llm, inference.open-weights | https://www.anchorterminal.com/tools/cloudflare-workers-ai.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)