Skip to content
Source
Sign inSign up
TanStack/ai

feat(ai-gemini): add Gemini Omni 1.2 Flash (gemini-omni-1.2-flash) #2065

Send to my agent
Closedtombeckenham opened this issue 0 comments
tombeckenhamcommented

Google released Gemini Omni 1.2 Flash (gemini-omni-1.2-flash). Docs: https://aistudio.google.com/docs/omni

Omni 1.1 stays available for four weeks, then from 2026-12-03 Google routes it to 1.2 and bills at 1.2 rates.

What changes in 1.2

  • Duration range is 3 to 15 seconds (1.1 is 3 to 10). Default 10.
  • Pricing: $12.00 per 1M video output tokens, about $0.07 per second at 720p (1.1 is $17.50 and $0.10). 360p $0.023/s, 1080p $0.104/s, 4k $0.209/s.
  • New generation_config.video_config.task: 'extend' appends 3 to 10 seconds per turn, up to 30 seconds total.
  • Reference limits: up to 6 reference images (3 per character, 2 characters). Up to 3 reference videos of 3 seconds for 3 to 10 second outputs, only 1 for 11 to 15 second outputs, none with edit or extend. First/last frame pair only for 3 to 10 seconds.
  • Audio input and voice editing are still unsupported.
  • Control strings <FIRST_FRAME>, <LAST_FRAME>, <IMAGE_REF_0>, <VIDEO_REF_0> are deprecated. The adapter does not emit them.

Work

  • packages/ai-gemini/src/model-meta.ts: add GEMINI_OMNI_1_2_FLASH next to 1.1 with the new pricing, add it to GEMINI_VIDEO_MODELS and GEMINI_INTERACTIONS_VIDEO_MODELS, mark 1.1 as deprecated in its doc comment.
  • packages/ai-gemini/src/video/video-provider-options.ts: duration entries for 1.2 with max 15, mention extend in the Omni provider options comment.
  • scripts/sync-provider-models.ts: add gemini-omni- to NON_CHAT_MODEL_PREFIXES so the daily sync stops inserting Omni as a chat model. The sync PR #2063 already inserted a bogus chat entry for 1.2 that must be removed.
  • Docs: docs/adapters/gemini.md and docs/media/video-generation.md model tables, the Omni section in docs/media/video-generation-advanced.md (15 second limit, extend, reference count rules), docs/config.json dates.
  • E2E fixture and spec for the new model id, changeset for @tanstack/ai-gemini.
  1. tanstack-source added labelsfeature

  2. AlemTuzlak closed this

Sign in to join this conversation.