Tip
If you can't find answers to your questions in this FAQ, ask the Azure Vision API community on Stack Overflow or contact Help and Support on UserVoice
How can I increase the transactions-per-second (TPS) allowed by the service?
The free (S0) tier only allows 20 transactions per minute. Upgrade to the S1 tier to get up to 20 transactions per second. If you're seeing the error code 429 and the "Too many requests" error message, submit an Azure support ticket to raise your TPS to 50 or higher with a brief business justification. Azure Vision pricing.
The service is throwing an error because my image file is too large. How can I work around this?
The file size limit for most Azure Vision features is 4 MB for the 3.2 version of the API and 20MB for the 4.0 version, and the client library SDKs can handle files up to 6 MB. For more information, see the Image Analysis input limits.
Can I send multiple images in a single API call to the Azure Vision service?
This function isn't currently available.
How many languages are supported for Azure Vision services?
See the Language support page for the list of languages covered by Image Analysis and OCR.
Can I deploy the OCR (Read) capability on-premises?
Yes, the Azure Vision 3.2 OCR (Read) cloud API is also available as a Docker container for on-premises deployment. Learn how to deploy
Can I access Azure Vision by using Azure-assigned managed identity?
Yes. Follow the instructions in the Authentication guide to use Azure-assigned managed identity to access Foundry Tools such as Azure Vision.
Can I train Azure Vision API to use custom tags? For example, I would like to feed in pictures of cat breeds to 'train' the AI, then receive the breed value on an AI request.
Yes. See Model customization, a feature of Image Analysis 4.0.