Plain-English Summary
A conversational video model for generating and editing video through natural-language interaction.
Gemini Omni Flash
A conversational video model for generating and editing video through natural-language interaction.
Gemini Omni
Video
Preview
Open weights: No
API: Yes
Technical Notes
Multimodal model supporting iterative video generation and editing from conversational instructions.
Best For
Conversational video creation, iterative edits, creative prototyping
Watch Out For
Preview availability; rendering cost, latency, and output limits may be significant.
Model Specs
- Maker
- Country
- Not listed
- Family
- Gemini Omni
- Type
- Video
- Release date
- 2026-06-30
- Date confidence
- Exact / latest update
- Status
- Preview
- Context window
- Varies
- Max output
- Not listed
- Parameters
- Not disclosed
- Active parameters
- Not disclosed
- Architecture
- Proprietary multimodal video model
- Reasoning
- Yes — instruction planning
- Tool calling
- Endpoint-specific
- Structured output
- No
- API available
- Yes
- Open weights
- No
- Self-hostable
- No
- License
- Proprietary
- Inputs
- Text, image, video
- Outputs
- Video
- Approx. price
- See provider pricing
- How to access
- Provider website or API
- Model / API ID
- gemini-omni-flash
- Knowledge cutoff
- Not publicly disclosed
- Fine-tuning
- Prompting / RAG
- Completeness
- 81 %
- Verified
- Jul 18, 2026
- Snapshot date
- Jul 18, 2026
- Source
- Official source