Azure
The gateway speaks Azure OpenAI natively and holds the resource api-key.
What's specific to Azure
| Property | Value |
|---|---|
| Provider id | azure-openai |
| Gateway speaks | Azure OpenAI REST ({resource}.openai.azure.com/openai) |
| Credential | api-key + resource name + deployment id + api version |
| Signing | None (api-key header) |
| Client base URL | OPENAI_BASE_URL → http://<gateway>:8787/v1 |
Everything shared — self-hosting, the config-based redirect, how credentials are stored — is documented once in the gateway.
Configure the provider
Console → Providers → add azure-openai:
- API key — your Azure OpenAI resource key
- Resource name — the resource subdomain (
{resource}.openai.azure.com) - Deployment ID — the deployment to target
- API version — e.g.
2024-02-01
Or seed it from the environment with ANYRAY_PROVIDER_KEY_AZURE_OPENAI. Entra ID, managed
identity, and workload identity are supported via request headers; the console form covers
static api-key auth.
Route requests to it
export OPENAI_BASE_URL=http://<gateway>:8787/v1
# requests carry: x-anyray-provider: azure-openai
Azure addresses models by deployment id, not a catalog model name — there's no fixed model list; you call whatever you've deployed in your resource.