Guidelines and quotas - Amazon Comprehend

Guidelines and quotas

Important notice

Amazon Comprehend Medical is not a substitute for professional medical advice, diagnosis, or treatment. Amazon Comprehend Medical provides confidence scores that indicate the level of confidence in the accuracy of the detected entities. Identify the right confidence threshold for your use case, and use high confidence thresholds in situations that require high accuracy. For certain use cases, results should be reviewed and verified by appropriately trained human reviewers. Use Amazon Comprehend Medical in patient care scenarios only after trained medical professionals have reviewed results for accuracy and sound medical judgment.

Keep in mind the following information when using Amazon Comprehend Medical.

Supported regions

For a list of AWS Regions where Amazon Comprehend Medical is available, see AWS Regions and Endpoints in the Amazon Web Services General Reference.


For information about throttling and quotas for Amazon Comprehend Medical, and to request a quota increase, see AWS Service Quotas.

Overall quotas

Character encoding for Amazon Comprehend Medical is in UTF-8. Amazon Comprehend Medical operations have the following quotas:

Description Quota
Maximum document size (UTF-8 characters) for DetectEntities, DetectEntities-v2, InferRxNorm and DetectPHI operations. 20,000 bytes
Maximum document size (UTF-8 characters) for InferICD10-CM operation 10,000 bytes
Maximum size of text analysis batch jobs (all files) 10 Gb
Maximum size of ontology linking batch analysis jobs (all files) 5 Gb
Minimum size of batch jobs (all files) 1 byte
Maximum individual file size for batch jobs 40 Kb
Maximum number of files for batch jobs 5 million

Amazon Comprehend Medical processes one block of each text document at a time, synchronously. Only documents in English (EN) are supported.