Service quotas and limits

This article contains both a quick reference and detailed description of Azure AI Document Intelligence service Quotas and Limits for all pricing tiers. It also contains some best practices to avoid request throttling.

Model usage

Quota	Free (F0)1	Standard (S0)
Transactions Per Second limit	1	15 (default value)
Adjustable	No	Yes 2
Max document size	4 MB	500 MB
Adjustable	No	No
Max number of pages (Analysis)	2	2000
Adjustable	No	No
Max size of labels file	10 MB	10 MB
Adjustable	No	No
Max size of OCR json response	500 MB	500 MB
Adjustable	No	No
Max number of Template models	500	5000
Adjustable	No	No
Max number of Neural models	100	500
Adjustable	No	No

Detailed description, Quota adjustment, and best practices

Before requesting a quota increase (where applicable), ensure that it's necessary. Document Intelligence service uses autoscaling to bring the required computational resources on-demand, keep the customer costs low, and deprovision unused resources by not maintaining an excessive amount of hardware capacity.

If your application returns Response Code 429 (Too many requests) and your workload is within the defined limits: most likely, the service is scaling up to your demand, but has yet to reach the required scale. Thus the service doesn't immediately have enough resources to serve the request. This state is transient and shouldn't last long.

General best practices to mitigate throttling during autoscaling

To minimize issues related to throttling (Response Code 429), we recommend using the following techniques:

• Implement retry logic in your application
• Avoid sharp changes in the workload. Increase the workload gradually
  Example. Your application is using Document Intelligence and your current workload is 10 TPS (transactions per second). The next second you increase the load to 40 TPS (that is four times more). The Service immediately starts scaling up to fulfill the new load, but likely it can't do it within a second, so some of the requests get Response Code 429.

The next sections describe specific cases of adjusting quotas. Jump to Document Intelligence: increasing concurrent request limit

Increasing transactions per second request limit

By default the number of transactions per second is limited to 15 transactions per second for a Document Intelligence resource. For the Standard pricing tier, this amount can be increased. Before submitting the request, ensure you're familiar with the material in this section and aware of these best practices.

Increasing the Concurrent Request limit does not directly affect your costs. Document Intelligence service uses "Pay only for what you use" model. The limit defines how high the Service can scale before it starts throttle your requests.

Existing value of Concurrent Request limit parameter is not visible via Azure portal, Command-Line tools, or API requests. To verify the existing value, create an Azure Support Request.

Have the required information ready

• Document Intelligence Resource ID

• Region

• Base model information:

  • Sign in to the Azure portal
  • Select the Document Intelligence Resource for which you would like to increase the transaction limit
  • Select -Properties- (-Resource Management- group)
  • Copy and save the values of the following fields:
    • Resource ID
    • Location (your endpoint Region)

Create and submit support request

Initiate the increase of transactions per second(TPS) limit for your resource by submitting the Support Request:

• Ensure you have the required information
• Sign in to the Azure portal
• Select the Document Intelligence Resource for which you would like to increase the TPS limit
• Select -New support request- (-Support + troubleshooting- group). A new window appears with autopopulated information about your Azure Subscription and Azure Resource
• Enter -Summary- (like "Increase Document Intelligence TPS limit")
• Select "Quota or usage validation" for problem type field.
• Select -Next: Solutions-
• Proceed further with the request creation
• Enter the following information in the -Description- field, under the Details tab:
  • a note, that the request is about Document Intelligence quota.
  • Provide a TPS expectation you would like to scale to meet.
  • Azure resource information you collected.
  • Complete entering the required information and select -Create- button in -Review + create- tab
  • Note the support request number in Azure portal notifications. Look for Support to contact you shortly for further processing.

Example of a workload pattern best practice

This example presents the approach we recommend following to mitigate possible request throttling due to Autoscaling being in progress. It isn't an exact recipe, but merely a template we invite to follow and adjust as necessary.

Let us suppose that a Document Intelligence resource has the default limit set. Start the workload to submit your analyze requests. If you find that you're seeing frequent throttling with response code 429, start by implementing an exponential backoff on the GET analyze response request. By using a progressively longer wait time between retries for consecutive error responses, for example a 2-5-13-34 pattern of delays between requests. In general, we recommended not calling the get analyze response more than once every 2 seconds for a corresponding POST request.

If you find that you're being throttled on the number of POST requests for documents being submitted, consider adding a delay between the requests. If your workload requires a higher degree of concurrent processing, you then need to create a support request to increase your service limits on transactions per second.

Generally, we recommended testing the workload and the workload patterns before going to production.

Next steps