The Gemini API now supports direct registration of files stored in Google Cloud Storage buckets as well as files accessible via HTTPS or signed URLs. This eliminates the need for redundant uploads, facilitating seamless data integration from various online and cloud sources. Inline data size limits have also increased from 20MB to 100MB to accommodate larger inputs.
These changes are intended to accelerate AI model development by removing previous bottlenecks in data ingestion, particularly for large files such as videos or extensive documents. The updates enable faster prototyping and smoother production scaling by leveraging persistent cloud storage locations without ephemeral delays.
Source & further reading
Increased file size limits and expanded inputs support in Gemini API ↗Source published 2026-01-12. This report was prepared with AI assistance from the linked primary-source material. Claims and limitations should be checked against the original announcement or research.