November 18, 2026 · Google Gemini API
Gemini API accepts Office and OpenDocument files, with slicing of documents, video and audio
- Multimodal file processing and slicing: You can now pass Microsoft Office and OpenDocument files (Word, PowerPoint, and Excel) directly to the Gemini API, and slice documents, spreadsheets, videos, and audio in user prompts and function responses. Select specific page ranges, worksheet tabs, cell ranges, time intervals, or content layers (such as page images, extracted text, formulas, or video transcripts) so you only process and pay for the content you need.
To get started, see Document understanding, Video understanding, and Audio understanding.
Related updates
Agentic video understanding for Gemini 3.7 Flash uses up to 88% fewer tokens
Gemini API accepts Cloud Storage and pre-signed URLs as input, file limit now 100MB
Gemini 2.5 Flash preview 05-20 released, with multi-tool use and URL context tool
Gemini Decision 1 and Decisions API released, with zero output tokens
Amazon Bedrock Data Automation now supports DOC/DOCX and H.265 files · AWS