Gemini Omni 1.1 Flash

Video generation and editing. Google describes it as a high-performance model for fast, conversational video generation and editing: text and images to video, refinement of generated video through natural-language conversation via the Interactions API, plus video extension, resolution upscaling and interpolation. Status ga on two first-party statements read 2026-09-01 — the model page Versions block reads 'Stable: gemini-omni-1.1-flash' (with 'Preview: gemini-omni-flash-preview' listed separately as the sibling endpoint until 2026-10-22; on the 2026-10-23 read that line reads 'Shut down: gemini-omni-flash-preview'), and the pricing page calls it 'now generally available to developers on the paid tier of the Gemini API'. Paid tier only: Google states 'Not available' on the free tier for both axes. Input $1.50 per 1M, one rate that the pricing page labels text / image / video / audio, although the model page spec table lists only Text, Image and Video (up to 10s for editing and extension) as supported inputs — that disagreement between two Google surfaces is recorded here rather than resolved. Two output rates: text and thinking tokens $9.00/1M, video tokens $17.50/1M — price_output_per_mtok holds the video rate, the model's product, the same convention gemini-3.1-flash-image uses for its image rate. Google states billing is on total output token consumption at 5,792 tokens per second of 720p video, an effective ~$0.10 per second under Standard pricing. Limits: the model page read 2026-11-07 states Input token limit 131,072 and Output token limit 65,536 tokens, output video 3s-10s at 360p/720p/1080p/4K, 24 FPS. Until 2026-11-07 this row carried a 1,048,576-token context window and a null max output (read 2026-09-01, when the page published no output token limit); the page today states the smaller figures, and whether Google changed them or the earlier read was wrong is not stated, so this is recorded as a correction without a changelog event. No context caching rate is published. Released August 27, 2026 per Google's deprecations table. Until the 2026-11-05 changelog that table stated 'No shutdown date announced' for it; it now gives shutdown December 3, 2026 with recommended replacement gemini-omni-1.2-flash ('Effective December 3, 2026, the endpoint is automatically routing API requests to gemini-omni-1.2-flash'), and the pricing page calls it the 'Previous generation' model, billed at gemini-omni-1.2-flash rates after that date. Status stays ga: Google does not call it deprecated, lists it outside the table's 'Deprecated models' section, and the model page still reads 'Stable: gemini-omni-1.1-flash (routes to gemini-omni-1.2-flash on December 3, 2026)'. Signal used for retires_on/replacement: Google's dated changelog entry of November 5, 2026 plus the deprecations table row — no gray marker, so nothing is retired. Added 2026-09-01: this row was missing from the catalog since launch, one of four Google models that check-google-prices.mjs could not report under 'on the page, not in the catalog' because every one of its price cells holds more than one rate (LEARNINGS #105).

Source: Google official documentation ↗

Explore more

Gemini Omni 1.1 Flash — questions & answers