Primary use stated or inferred cautiously from official documentation.
G
GOOGLE / gemini-omni-1.2-flash
Gemini Omni 1.2 Flash
Generally available since November 5 for generating, editing and extending video with synchronized audio. The Interactions API takes text, images and video and returns video and text. The model card describes audio inputs, but the API contracts reviewed do not document standalone audio input.
01 / SUMMARY
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
02 / TECHNICAL SHEET
Limits and integration
| API ID | gemini-omni-1.2-flash |
|---|---|
| Model type | Video · Multimodal |
| Access model | Paid proprietary |
| License | Proprietary |
| Deployment | Hosted API |
| Release | 05 NOV 2026 |
| Knowledge cutoff | Not published |
| Entrance | Text · Image · Video |
| Exit | Video with audio · Text |
| Context window | 131,072 input tokens |
| maximum output | 3–15 s video; up to 65,536 output tokens on Gemini API |
| Reasoning | Not published |
| Published tools | |
| Structured Outings | Not published |
| Batch processing | Not published |
| Prompt cache | Not published |
| Fine-tuning | Not published |
| Verified platforms | Gemini API · Google Cloud · Google AI Studio |
Video drafts, variations based on references and successive edits to a clip. Generation and editing allow 3 to 15 seconds; frame interpolation and each extension are capped at 10 seconds. Record resolution and operation because they affect limits and billing.
Gemini API lists a 65,536-token output limit, versus 260,640 for Agent Platform. Both allow up to 131,072 input tokens. Do not transfer limits between channels. Upscaling to 1080p or 4K is distinct from native generation at that resolution. Standalone image or audio generation is not supported.
03 / CAPABILITIES
What it can do
Orientation
Video drafts, variations based on references and successive edits to a clip. Generation and editing allow 3 to 15 seconds; frame interpolation and each extension are capped at 10 seconds. Record resolution and operation because they affect limits and billing.
Context
131,072 input tokens · 3–15 s video; up to 65,536 output tokens on Gemini API
Tools and integration
Not published
Access
Paid Gemini API · Google Cloud
Input modalities
TextImageVideo
04 / PRICES
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | 1.50 USD / 1M input tokens | Standard API rate |
| Cached input | Not published | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | 9 USD text · 12 USD video / 1M tokens | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
Paid Gemini API rates are USD 1.50 input, USD 9 text output and USD 12 video output per million tokens. At 720p this is about USD 0.07 per generated second before input charges. Resolution and usage affect cost; text and video have separate output rates.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
05 / EVALUATIONS
How to read the results
“
Google describes better consistency and editing, but the sources reviewed do not provide a numeric video-quality score for this version. Inferama has not run its own test. A comparison should fix duration, resolution, references and seed and measure continuity, synchronization and cost per usable clip.
i No verified numeric score for the exact version.
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
06 / VERSIONS
Chronology
Gemini Omni 1.2 Flash
Version added to Inferama's verified catalog.
07 / SOURCES