Azure Document Intelligence Rate Limits
Azure AI Document Intelligence enforces tier-specific transactions per second (TPS) ceilings. F0 (Free) is capped at 1 transaction per second; S0 (Standard) defaults to 15 TPS and can be raised on request via Azure support. Per-document size caps and per-call page caps depend on model and API version.
Azure Document Intelligence Rate Limits is the machine-readable rate-limit profile for Azure AI Document Intelligence on the APIs.io network, in the API Commons Rate Limits shape.
It captures 4 rate-limit definitions, measuring tps, MB, and pages.
Limit state is signalled in the Retry-After and x-ms-ratelimit-remaining-requests response headers, and an exhausted limit returns HTTP 429.
This profile was written by API Evangelist and has not been verified against a page the provider published; treat every limit as unconfirmed until a dated transcription replaces it.
The profile also includes 2 backoff/retry policies defined and response codes documented for throttled.
Tagged areas include AI, Document AI, Azure, IDP, and OCR.
Retry-Afterx-ms-ratelimit-remaining-requests
generated, dated 2026-05-08.
Limits
Policies
Sources
- https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/service-limits
- https://docs.azure.cn/en-us/ai-services/document-intelligence/service-limits
Work with this as data
Every rate limit here is available over the APIs.io API and to AI agents over MCP.