Claude in Microsoft Foundry speaks the standard Messages API — same request shape, same usage object in responses, same model IDs (claude-opus-4-8, claude-sonnet-5, and so on, with no prefix). For a straightforward chat or tool-use workload, code written against the first-party API ports with little more than a client swap to AnthropicFoundry. The differences appear at the edges: whole API endpoints that do not exist on Foundry, features that depend on which hosting option you deployed, and operational conveniences that quietly are not there. As of July 2026, here is the map.
Not available on Foundry at all
Anthropic's Foundry documentation lists these as unsupported, full stop:
- Message Batches API — the asynchronous bulk endpoint with 50% discounted pricing. There is no batch mechanism for Claude on Foundry; high-volume offline jobs must run as rate-limited synchronous traffic or on a platform that supports batching.
- Models API — no programmatic model listing; you call the deployment names you created.
- Admin API and Compliance API — organization management is Azure's job here (RBAC, subscriptions, policy), not Anthropic's endpoints.
- Claude Managed Agents and the Advisor tool.
- Server-side fallback (the
fallbacksparameter) — retry-on-another-model logic stays in your client code. - Fast mode (a first-party research preview) and the
inference_geodata-residency parameter — though a US Data Zone Standard deployment is documented as equivalent toinference_geo: "us", keeping inference within the United States.
One operational gap deserves its own line: Foundry does not return Anthropic's anthropic-ratelimit-* response headers. Client-side limiters that read them must fall back to Azure-side monitoring and exponential backoff on 429s.
Available, but beta — and hosting-option dependent
PDF input, adaptive and extended thinking, prompt caching, citations, and 1M context are generally available on Foundry. Several other advanced features exist on Foundry in beta: structured outputs, token counting, web search, web fetch, code execution, tool search, the bash/text-editor/memory tools, Agent Skills, programmatic tool calling, the MCP connector, and the Files API (beta here, in contrast to Batches, which is absent). The caveats that come with the label are covered in beta feature caveats on Foundry.
The subtler axis is the hosting option chosen at deployment time — "Hosted on Azure" (recommended default, GA models) versus "Hosted on Anthropic infrastructure." Several features are only available on Anthropic-hosted deployments: structured outputs, the server-side tools (web search, web fetch, code execution, tool search), the MCP connector, Agent Skills, programmatic tool calling, and the Files API. Sending such a request to an Azure-hosted deployment returns 400 Bad Request by design. Note the trade-off is not free: on Anthropic-hosted deployments, data may be processed outside Azure and your selected region, under Anthropic's data processing terms — a point your security review will care about.
| If your workload needs… | On Foundry | Practical route |
|---|---|---|
| Messages, streaming, tool use | GA | Use Foundry as-is |
| Batch processing at discount | Not available | First-party API or Claude Platform on AWS |
| Files API, structured outputs, server-side tools | Beta, Anthropic-hosted only | Deploy the Anthropic-hosted model version; review data-flow implications |
| Rate-limit headers, Admin/Usage APIs | Not available | Azure Monitor, Cost Management, RBAC instead |
"When will X arrive?" — how to actually track it
Neither Microsoft nor Anthropic publishes a feature roadmap for Claude on Foundry, so treat any expected dates you hear as rumor. What you can do is watch the authoritative status surfaces: Anthropic's Claude-on-Foundry page (which maintains the supported/unsupported lists quoted here), Anthropic's platform availability matrix, and Microsoft Learn's Claude model pages, which record per-model, per-hosting-option capabilities and lifecycle stages. The general pattern visible in the docs is that new capabilities tend to reach the Anthropic-hosted option first and Azure-hosted later — so if a missing feature is blocking you, the Anthropic-hosted model version is the first thing to test.
Where to go next
See beta feature caveats for what the beta label costs you in practice, and the feature matrix for how Foundry compares with Bedrock, Vertex AI, and Claude Platform on AWS.