← Sunday, September 27, 2026ArchitectureCase study

Scribd classified 400 million documents with Gemini batch inference

cloud.google.com by Travis Martin, Sachin Sebastian 5 min read Editor score 8/10

Scribd processed more than 400 million documents spanning 12 billion pages in months; native PDF input avoided OCR for more than 99% of the corpus, and batch pricing was 50% below interactive pricing. The case shows how input format and batch economics shape corpus-scale classification.

What: Scribd used Gemini Enterprise batch prediction and Gemini’s native PDF understanding to classify its user-generated content corpus.
How: The run covered more than 400 million documents and 12 billion pages; native PDF input avoided OCR, rendering, and screenshot pipelines for over 99% of the corpus.
Why it matters: Native multimodal PDF processing and discounted batch prediction made corpus-scale classification viable without building a document-conversion pipeline.

PDFs pass through Gemini processing into batch prediction for trust and safety classification. Sketched from the article's own text.

Read on cloud.google.com →

Discussion

Discussion is not switched on yet. Use Note above to keep your own thoughts on this story.

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.