Amazon Textract vs Unstructured API + MCP

Amazon Textract

IAM policies limit a credential to single operations, CloudTrail logs every call, and page prices start at $1.50 per 1,000 in US East. Multipage files need S3 and an asynchronous job. Text detection covers six languages. Under the AWS Service Terms AWS may store and use documents to improve the service unless an AI services opt-out policy is set.

Unstructured API + MCP

Apache-2.0 library partitions 45+ file types locally at no cost, tagged 11 times since 3 July. No status page, no published rate limits and no SLA.

Amazon Textract

1. Sign with SigV4 for service textract at textract.<region>.amazonaws.com, or call aws textract detect-document-text. The AWS CLI can't send image bytes, so reference an S3 object
2. Use StartDocumentTextDetection or StartDocumentAnalysis for any PDF or TIFF of more than one page, pass a ClientRequestToken, then page Get calls with NextToken (1,000 blocks at most each)
3. Fetch results within 7 days of starting a job, or set OutputConfig to write them to your own S3 bucket
4. Request only the FeatureTypes you need. Forms cost $50 per 1,000 pages against $15 for tables or queries in US East
5. Back off on ProvisionedThroughputExceededException (HTTP 400) and ThrottlingException (HTTP 500). Neither carries Retry-After, and default quotas are 1 call a second in most Regions
6. Set the AI services opt-out policy on the AWS organisation before sending customer documents

Unstructured API + MCP

1. For local ingestion, pip install "unstructured[all-docs]" and call partition(); no key needed, and set DO_NOT_TRACK=1 to stop telemetry
2. Transform returns 202 with a Location header for long parses; poll it, then pass the parse id as parse_id to Extract
3. Uploaded files expire after 24 hours; keep the original and re-upload on a 404
4. Treat 409 parse_expired and 410 result_expired as a signal to rerun the parse, not to retry
5. Check for an existing job ID before resubmitting, since there's no idempotency key