Gemini Omni 1.2 Flash

Gemini Omni 1.2 Flash is a multimodal model designed for video, image, and text tasks. Omni 1.2 Flash is optimized for video generation, editing, extension, and standalone video upscaling, generating or editing video output with synchronized audio up to 15 seconds at 360p, 720p, 1080p, or 4K resolution alongside text responses in a single model.

Try in Agent Studio View in Model Garden Deploy example app Pricing

Note: "Deploy example app" requires a Google Cloud project with billing and Agent Platform API enabled.

Model ID	gemini-omni-1.2-flash
Modalities	description Text Input and output photo Image Input only mic_off Audio Not supported videocam Video Input and output
Token limits	Maximum input tokens	131,072
	Maximum output tokens	260,640
Capabilities	Thinking Supported System instructions Not supported Structured output Not supported Context caching Not supported RAG Engine Not supported Tuning Not supported Image generation Not supported Edit images Not supported Interleaved images and text Not supported Generate videos from text Supported Generate videos from an image Supported Generate videos from references Supported Videos from first and last frames Supported Sound generation Speech, music, sound effects Supported Video editing Supported Extend videos Supported Upscale videos Supported Content Credentials (C2PA) Supported Agentic video understanding Not supported
Tools	Grounding Not supported Code execution Not supported Function calling Not supported URL context Not supported Computer use Not supported
APIs	GenerateContent API Not supported Interactions API Supported Gemini Live API Not supported Count Tokens API Supported Chat Completions API Not supported
Consumption options	Provisioned Throughput Supported Batch inference Not supported Pay-as-you-go Standard PayGo Supported Fixed quota Supported
Technical specifications	Image	Maximum images per prompt: 10 Maximum file size per file for inline data or direct uploads through the console: 20 MB Maximum file size per file from Google Cloud Storage: 30 MB Supported MIME types: image/png, image/jpeg, image/webp, image/heic, image/heif
	Text	Maximum file size per file for the API or Cloud Storage imports: 50 MB Maximum file size per file for direct uploads through the console: 7 MB Supported MIME types: text/plain
	Video	Maximum video length (with audio): 15 seconds Maximum video length (without audio): 15 seconds Maximum input video length (video understanding): 10 minutes Maximum input video length (editing): 15 seconds Maximum input video length (extension): Any duration (uses up to the last 10 seconds) Maximum input video length (upscaling): 15 seconds Output video duration (generation and editing): 3 to 15 seconds (3 to 10 seconds for first and last frames) Output video duration (extension): 3 to 10 seconds (concatenated onto up to the last 30 seconds of the input video) Maximum number of videos per prompt: 3 Supported aspect ratios: 16:9, 9:16 Supported resolutions: 360p, 720p, 1080p, 4k Supported MIME types: video/x-flv, video/quicktime, video/mpeg, video/mpegs, video/mpg, video/mp4, video/webm, video/wmv, video/3gpp
	Parameter defaults	Temperature: 0.0-2.0 (default 1.0) topP: 0.0-1.0 (default 0.95) candidateCount: 1
Supported regions	Model availability	Global: global
	Provisioned Throughput	Global: global
	Standard PayGo	Global: global
Versions	gemini-omni-1.2-flash Launch stage: GA Release date: November 5, 2026 Retirement date^†: November 5, 2027 or later
Security controls	Online prediction	Data residency CMEK VPC-SC AXT
	See Security controls for more information.

^† Listed retirement dates refer to retirement of support in Gemini Enterprise Agent Platform. Models may remain accessible through the Gemini API after these dates have passed. The Gemini API is not a Google Cloud offering and is subject to its own terms of service. For details, see the Gemini API documentation.