Google releases Gemini Omni 1.1 Flash, a generally available video model with 4K output and native audio

Google released Gemini Omni 1.1 Flash on Nov 4, 2026, a native multimodal video generation and editing model that is the generally available successor to Gemini Omni Flash Preview. The model generates clips from 360p drafts up to 4K with native audio, in 16:9 or 9:16.

Key specifications

• Release date: Nov 4, 2026
• Context window: 131K tokens
• Pricing (OpenRouter, Google AI Studio): $1.50 per 1M input tokens, $9.00 per 1M output tokens
• Output resolution: 360p drafts up to 4K
• Aspect ratios: 16:9 and 9:16
• Audio: native audio generated with the video
• Reasoning: listed as supported
• Providers: 1 (Google AI Studio)

Capabilities

According to the OpenRouter listing, Gemini Omni 1.1 Flash supports:

• Text-to-video
• Image-to-video
• First and last frame interpolation
• Subject and video references, with up to three reference clips
• Editing or extending an uploaded video

Multi-turn editing and extension of a prior generation is handled through the previous_job_id parameter, up to 40 seconds of total video.

Access and limits

Video generation is only supported through the Video Generation API. OpenRouter publishes a guide at openrouter.ai/docs/guides/overview/multimodal/video-generation. The model is not currently available through EU in-region routing.

On Nov 5, 2026, OpenRouter showed an end-to-end latency of 23.72s (P50, best provider) for Google AI Studio. No uptime figure was displayed for the model at that time.

Successor already listed

The same OpenRouter page lists Gemini Omni 1.2 Flash as the successor to Gemini Omni 1.1 Flash. It is described as generating clips up to 15 seconds long with native audio in 16:9 or 9:16, from 360p drafts up to 4K. It adds improved reference management for subject and video references. It is listed at 131K context and $1.50 / $9, the same as 1.1 Flash.

Benchmark scores for Gemini Omni 1.1 Flash are not published on the listing.

What this means

The move from Gemini Omni Flash Preview to a generally available release gives developers a production-status video model with a single API surface for generation, reference-based conditioning and editing. The previous_job_id mechanism lets applications refine or extend an earlier generation across multiple turns, within the 40-second total limit. Because video generation works only through the Video Generation API, existing chat-completion integrations cannot call it directly. Teams with EU in-region routing requirements cannot currently use the model through OpenRouter under that constraint. The listing of Gemini Omni 1.2 Flash alongside 1.1 Flash means builders choosing a video model on OpenRouter have two Omni Flash versions to evaluate.