II.
Provider overview
Reference · liveprovider:azure-foundry
Azure AI Foundry overview
Inspect the raw attributes, linked wiki pages, and inbound or outbound graph edges for provider:azure-foundry.
Attributes
displayName
Azure AI Foundry
versionRange
>=2024-05-01
authMethods
- api-key
- oauth
authMethodNotes
Azure AI Foundry deployments authenticate with an Azure API key
in the `api-key` header or a Microsoft Entra ID bearer token in
`Authorization: Bearer <token>`. Per-deployment endpoints are of
the form `https://<resource>.services.ai.azure.com/models`.
endpoints
pricing
Per-model pay-as-you-go rates published in Azure Pricing
Calculator; reserved-capacity (PTU) pricing also available.
pricingTiers
- namepay-as-you-gorateLimitPer-deployment TPM/RPM quotaspriceMultiplier1descriptionDefault per-token billing.
- nameprovisioned-throughputrateLimitReserved PTUs (provisioned throughput units)priceMultiplier1descriptionReserved-capacity throughput at fixed monthly cost.
rateLimitSignalingProtocol
Azure returns `x-ratelimit-remaining-requests`,
`x-ratelimit-remaining-tokens`, and 429 with `retry-after`.
dataResidencyOptions
- us
- eu
- asia
vendorFeatures
slaTier
azure-99.9
regions
- eastus
- westus
- westeurope
- swedencentral
- japaneast
Outgoing edges
realizes1
- layer:2-provider·LayerProvider
serves2
- model:phi-3-medium@current·ModelVersionPhi-3 Medium
- model:phi-3-mini@current·ModelVersionPhi-3 Mini
Incoming edges
served_by3
- model-transport:azure-foundry·ModelTransportProtocolAzure AI Foundry Chat Completions
- model:phi-3-medium@current·ModelVersionPhi-3 Medium
- model:phi-3-mini@current·ModelVersionPhi-3 Mini