What are Gemini Omni Flash's documented capabilities, limits, prompting rules, watermarking and price in the Gemini API?

Gemini API docs (captured 2026-10-23): gemini-omni-1.1-flash generates video with audio from text, image (reference/first frame), first+last frame interpolation and subject reference images, edits videos conversationally (multi-turn via the Interactions API) and extends videos at the tail. Output resolution 360p, 720p (default) or 1080p (upscaled); aspect 16:9 or 9:16. Limits: uploaded videos for editing/extension must be 10 s or less; extension appends to the end only; you cannot extend an uploaded talking clip to add dialogue (except via multi-turn on model-generated videos); voice editing and audio references unsupported; video references max 3 clips of up to 3 s each (audio ignored); no multi-video reasoning; no system instructions, temperature, top_p, stop sequences or negative-prompt field (write "Do not do X" in the prompt); YouTube URLs not accepted; editing/extending uploaded videos unavailable in the EEA, Switzerland and UK, and images with minors not supported there; certain recognizable people cannot be edited. All outputs carry SynthID watermarking (invisible, programmatically detectable). Prompting: by default it creates several shots and a narrative; ask for "a single unbroken scene / single continuous shot / no scene cuts" when needed; use short negatives like "No dialogue". Price (paid tier, standard): $1.50 per 1M input tokens; video output $17.50 per 1M tokens at 5,792 tokens per second of 720p video, about $0.10 per second (consistent with AA's ~$9.12/min at 1080p list, C3-B369-01); no free tier. Supersedes the B343 note that a dedicated docs page was missing (that URL guess 404ed; the page is /gemini-api/docs/omni). Curator correction 2026-10-24 (discovery C3-B978-01; sources re-fetched 2026-10-24, excerpts re-located by curator GET): C3-B382-01 (captured 2026-10-23) says "Output resolution 360p, 720p (default) or 1080p (upscaled)" and its uncertainty says max output duration was not found. At re-check 2026-10-24 the Gemini Omni docs resolution table lists four values: 360p, 720p (default), 1080p (upscaled) and 4k (upscaled). The gemini-omni-1.1-flash model page gives output video of 3s-10s (360p/720p/1080p/4K, 24 FPS) with "Latest update August 2026", so the 4K option predates the 2026-10-23 capture: the Gemini API changelog entry dated August 27, 2026 (Gemini Omni Flash GA) says the new resolution parameter "supports `360p`, `720p` (default), `1080p`, and `4k` outputs. 1080p and 4K outputs are generated using upscaling." The 3s-10s output length is undated beyond the model page's "Latest update August 2026". The Gemini pricing page states a per-second equivalent only for 720p (5,792 tokens per second of 720p video, about $0.10 per second); no 1080p or 4K token rate was found on that page. Runway also lists gemini_omni_flash_1.1 at 4K (30 credits per second). Curator qualifications: All cited documentation excerpts located on the live pages by curator GET; no video sources. Provider documentation as served 2026-10-23; models, limits and prices change without notice. Limitations: Max output duration not found in lines read. Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.

{
  "citations": [
    {
      "url": "https://ai.google.dev/gemini-api/docs/omni",
      "note": "Limitations bullet 4; Limitations bullet 3; Technical details; prompt guide: Single scene; Gemini Omni Flash pricing"
    },
    {
      "url": "https://ai.google.dev/gemini-api/docs/pricing",
      "note": "Limitations bullet 4; Limitations bullet 3; Technical details; prompt guide: Single scene; Gemini Omni Flash pricing"
    }
  ]
}