Azure AI Foundry¶

An openai-compat subclass carrying Azure's parameter renames and its two authentication modes.

streaming structured output tool calls health discovery

Setup with an API key¶

client = ai.Client([
    ai.ProviderSettings.of(
        "azure-foundry",
        base_url="https://<resource>.services.ai.azure.com/openai/v1",
        api_key="env://AZURE_AI_KEY",
    ),
])
result = client.generate(prompt, target="azure-foundry:gpt-5")

Setup with Entra¶

pip install "anyinfer[azure]"
az login

ai.ProviderSettings.of(
    "azure-foundry",
    base_url="https://<resource>.services.ai.azure.com/openai/v1",
    # no api_key: DefaultAzureCredential is used
)

Aliases: azure, foundry.

Differences from vanilla openai-compat¶

	Azure
Output-token parameter	`max_completion_tokens`
Reasoning effort	flat `reasoning_effort` field
Auth header	`api-key`, or `Authorization: Bearer` for Entra
API version	optional `api-version` query parameter

Sending max_tokens to Azure is rejected outright, which is why the subclass exists.

API versions¶

ai.ProviderSettings.of("azure-foundry", base_url=..., api_version="2024-10-21")

Only needed for deployments that still require it; the newer /openai/v1 surface does not. The parameter is applied per instance, so it cannot leak onto other adapters.

Troubleshooting¶

could not acquire an Entra token — run az login, or configure a service principal in the environment. The error names the scope it tried.

azure-foundry requires the base URL of your Foundry resource — the resource endpoint is deployment-specific and cannot be defaulted.

Wire contract¶

For the exact request/response fields this adapter depends on, see contracts/azure-foundry.md.