Amazon Comprehend Pricing Calculator - NLP, PII, Topic Modeling & Custom Models
Estimate Amazon Comprehend costs for standard NLP APIs, targeted sentiment, PII detection, prompt safety, toxicity detection, topic modeling, and custom classification or entity models.
Reference pricesExample monthly cost in US East (N. Virginia)
1 million documents of 1,000 characters each analyzed for entities per month, priced by this calculator at AWS list prices.
Estimated total: $1,000.00 per month
| Breakdown | Monthly cost |
|---|---|
| Text API requests (10,000,000 BU) | $1,000.00 |
| ↳ 1,000,000 x 10 @ $100.00/M | $1,000.00 |
Priced on 15 Oct 2026 from CloudBurn's AWS price data. Prices in USD, excluding tax.
Free price alerts · Platform launching early 2027
Get an email when Comprehend prices change
CloudBurn re-checks AWS prices every week and emails you when a price behind this calculator changes.
30% founding-member discount
Only waitlist members get it. Join now and keep 30% off for as long as you keep your plan.
Alert emails only arrive when a price changes; the waitlist sends two a month at most. Unsubscribe anytime. Privacy policy
Tick the box to also save your spot on CloudBurn Platform:
- Price your whole stack in minutesThe AWS Simple Pricing Calculator puts Comprehend and the rest of your AWS services in one estimate, ready to export.
- Know the cost before you deployThe GitHub App estimates what your Terraform, CDK or CloudFormation changes will cost before they ship.
- Find the waste, then fix itScans of your live AWS accounts show what is costing money for nothing, with clear steps to fix each finding.
Frequently Asked Questions
How does Amazon Comprehend bill text APIs?
Most Amazon Comprehend text APIs bill in 100-character units with a 300-character minimum per request. This calculator applies that minimum before multiplying by your monthly request count.
How do realtime custom Comprehend endpoints get priced?
Realtime custom classification and custom entity endpoints are priced by the number of inference units you keep provisioned and how long the endpoint stays active. One inference unit provides 100 characters per second of throughput.
Why is there an optional Textract line item for custom entities?
AWS notes that scanned PDFs require Amazon Textract DetectDocumentText before custom entity recognition can process the extracted text. This calculator can include that OCR passthrough cost when you model scanned-PDF pipelines.
Related tools