Multimodal function responses for Gemini API
In brief
Gemini API function responses now support Office/OpenDocument files, audio, video, and file URIs, letting tools return richer data to the model.
How it works
In GenerateContent API, function response parts accept audio, video, and Office/OpenDocument files via inline data or Files API URIs. Video parts support mediaProcessing modes. Interactions API function_result steps accept document, audio, and video blocks by data or URI.
Developers building agents that need to return multimodal content from tools.
Availability
Sources
6 merged into this card- 1Document understandingHow-to guide · aistudio.google.com
- 2Function calling with the Gemini APIHow-to guide · aistudio.google.com
- 3Gemini Omni FlashHow-to guide · aistudio.google.com
- 4Generate and edit videos with Gemini Omni FlashHow-to guide · aistudio.google.com
- 5Rate limitsHow-to guide · aistudio.google.com
- 6Gemini API release notes — November 5, 2026Release notes · aistudio.google.com · 05.11
More from Google
Gemini CLI adds standalone theme.json support
Google's gemini-cli v0.69.0 adds support for a standalone theme.json configuration file. Users can now define custom themes in a dedicated file.
Gemini CLI /stats heatmap subcommand
Google added a /stats heatmap subcommand to Gemini CLI v0.69.0 to track daily token usage. It lets developers monitor their token consumption directly from the command line.
