Learn how Analyzer in Acrobat consumes generative credits when you upload documents and extract information.
Analyzer uses credits to ingest documents and extract attribute values. Credit consumption depends on the operation and the number of documents processed.
Consumption rates
| Operation | Credits consumed |
|---|---|
| Document ingestion | 150 credits per ingestion |
| Attribute extraction | 50 credits per attribute per extraction |
Strict and Interpretive extraction consume the same number of credits (50). See Create custom attributes using Analyzer in Acrobat for information about extraction modes.
Shared Credits is a product offering that provides an expanded pool of generative credits for eligible users to draw from as needed. This shared pool allows high-volume users to continue consuming credits beyond their individual monthly allocation without requiring credits to be assigned to them individually in advance.
For information about organization-level Shared Credits, see the Shared Credit product description.
To configure Shared Credits for your organization, see Enable Shared Credits for your organization.
How consumption is calculated
Document ingestion and attribute extraction are charged separately. When you upload a document and run an extraction operation, the total consumption includes both charges.
- Consumption for document ingestion is calculated per document file.
- Individual file limits are 150 MB or 400 pages per document.
- Consumption for attribute extraction is calculated per attribute per extraction.
| Example | Calculation | Total consumption |
|---|---|---|
| Upload 10 documents | 10 × 150 | 1,500 credits |
| Run strict extraction on 10 documents with one attribute each | 10 × 50 | 500 credits |
| Run interpretive extraction on 10 documents with one attribute each | 10 × 50 | 500 credits |
| Upload 10 documents, with one attribute each, and run extraction | (10 x 150) + (10 x 50) | 2,000 credits |
| Refresh one document, with 10 attributes, twice | (10 × 50) × 2 | 1,000 credits |
| Upload one document with 5 attributes, run extraction, and one refresh | 150 + (5 x 50) + (5 x 50) | 650 credits |
Document ingestion
Document ingestion prepares an uploaded file for use in Analyzer. A file can be uploaded manually, through a linked connector, or via API.
Each uploaded file is treated as a separate document for consumption purposes, even when its contents match a previously uploaded file.
Rate: 150 credits per uploaded document file.
For example, uploading the same file 10 times consumes 1,500 credits.
Refreshing attributes
Refreshing attributes updates previously extracted values only when the attribute definition has changed.
A refresh runs a new extraction and consumes 50 credits per attribute per document refreshed.
See Refresh a collection's attributes in Analyzer in Acrobat for information about refreshing extracted values.
Testing attributes
Testing an attribute in the Create attribute flow consumes credits at the same rate as attribute extraction: 50 credits per attribute per document tested.
See Test attributes in Analyzer in Acrobat for information about testing and refining attributes.
Consumption rules
- Document ingestion and attribute extraction are charged separately.
- Ingestion consumption is calculated per uploaded file, whether it is uploaded manually, through a linked connector, or via API. It is not calculated per collection.
- Each upload incurs document-ingestion consumption.
- Uploading a duplicate file incurs a new ingestion charge. Analyzer treats each upload as a distinct file.
- Removing and uploading the same file again incurs a new ingestion charge.
- Credit rates don't vary by file type, page count, or file size.
- Attribute extraction consumes 50 credits per attribute per extraction.
- Strict and Interpretive extractions consume the same number of credits.
- Testing an attribute consumes credits at the same rate as extraction.
- Refreshing attributes after the attribute definition changes consumes additional credits for each attribute extracted again.
- Credit consumption is calculated for each attribute extracted from each file. Starting an extraction may process many attributes across many files, and each attribute-file combination is charged separately.
- For example, extracting five attributes from 10 files results in 50 billable extractions, even when the same five attributes are applied to every file.
