Google's official Gemini API changelog for November 18 announced multimodal file processing and slicing: Microsoft Office and OpenDocument files (Word, PowerPoint and Excel) can now be passed to the Gemini API directly, and documents, spreadsheets, videos and audio can be sliced in user prompts and function responses. Developers pick page ranges, worksheet tabs, cell ranges, time intervals or content layers such as page images, extracted text, formulas or video transcripts, and only process and pay for that content.
Key Takeaways
- ✓Since November 18 the Gemini API accepts Office and OpenDocument files such as .docx, .pptx, .xlsx, .doc/.ppt/.xls and .odt/.odp/.ods directly, processed the same way as PDFs
- ✓Add processing (type static) on a document block to slice: page_options sets start/end pages and content layers (page_image / page_text), spreadsheet_options sets sheet_index and an A1 cell range such as A1:H50
- ✓With processing set, only the selected pages, sheets and content layers are counted and billed; page images cost about 280 / 560 / 1,120 tokens per page by resolution, medium by default
- ✓Video can be clipped with start_offset / end_offset and limited to frames, audio or transcript layers, audio supports interval clipping, and tools can return slices inside function results
- ✓Limits: 50 MB per file, up to 2,000 pages or slides per Office file and 50,000 cells per sheet, and the limits still apply to the whole file when slicing
Key Decision Metrics at a Glance
Turn your technical choice into a development budget
Compare 40 dev plans & simulate token costs vs $20/mo subscriptions
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
Background
Much enterprise knowledge lives in Word, PowerPoint and Excel, and developers often had to convert files to PDF or CSV first and pay for the whole file. The official Gemini API changelog for November 18 announced multimodal file processing and slicing: Office and OpenDocument files can be passed directly, and you pay only for what you use. Accounts such as StatsWire highlighted the update on X.
How it works
Per the document understanding guide, set processing (static) on a document block. Documents and presentations use page_options for page ranges and content layers (page images or extracted text); spreadsheets use spreadsheet_options for sheet_index and an A1 cell range. Video can be clipped with start_offset / end_offset and limited to layers such as transcript, audio supports interval clipping, and tools can return slices in function results. The model also receives page counts and sheet names so it can ask for narrower ranges later.
Numbers that matter
Google published no benchmarks. Page images cost about 280, 560 (default) or 1,120 tokens per page by resolution, and with processing set only the selected pages, sheets and layers are billed. Files are capped at 50 MB, 2,000 pages or slides per Office file and 50,000 cells per sheet.
What it means for developers
Scan large files cheaply with page_text first, then request high-resolution page_image only for pages with charts; for spreadsheets, send just the sheet and cell range you need. It fits agent workloads such as contract review, financial model analysis and meeting-recording search while cutting context and cost.
Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.