Google DeepMind

Gemini Omni 1.2 Flash

Generally availableProprietary131K contextReasoning

Summary

Gemini Omni 1.2 Flash is a proprietary video generation model from Google DeepMind, released on 5 Nov 2026. It accepts text, images and PDFs and generates video, with a 131K-token context window and up to 261K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $1.50 per million input tokens and $9 per million output tokens (OpenRouter), across 2 providers we track.

Omni-modal model for text, vision, audio, and multimodal agent tasks

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperGoogle DeepMind
Release date5 Nov 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsProprietary (API only) [models.dev]
Context window131K (131,072 tokens) [models.dev]
Max output261K tokens [models.dev]
InputText, images and PDFs [models.dev]
OutputVideo [models.dev]
Reasoning modeYes [models.dev]
Tool callingNo [models.dev]
Structured outputNo [models.dev]

Gemini Omni 1.2 Flash API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
OpenRouter
google/gemini-omni-1.2-flash
$1.50$9–131KOpenRouter, 18 Nov 2026
Vercel AI Gateway
google/gemini-omni-1.2-flash
$1.50$9–131Kmodels.dev, 18 Nov 2026

Frequently asked questions

What is the context window of Gemini Omni 1.2 Flash?

Gemini Omni 1.2 Flash has a context window of 131,072 tokens (131K) and can generate up to 260,640 tokens in a single response, according to models.dev.

How much does the Gemini Omni 1.2 Flash API cost?

Gemini Omni 1.2 Flash is listed from $1.50 per million input tokens and $9 per million output tokens (OpenRouter). Prices last verified 18 Nov 2026.

Is Gemini Omni 1.2 Flash open source?

No. Gemini Omni 1.2 Flash is a proprietary model; Google DeepMind has not released its weights. It is available through APIs including OpenRouter, Vercel AI Gateway.

When was Gemini Omni 1.2 Flash released?

Google DeepMind released Gemini Omni 1.2 Flash on 5 Nov 2026, according to models.dev.

Which providers offer Gemini Omni 1.2 Flash?

We track Gemini Omni 1.2 Flash on 2 providers: OpenRouter, Vercel AI Gateway.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
MiniMax H3 MaxMiniMax26 Aug 2026–––Closed
Seedance 2.5ByteDance Seed31 Jul 2026–––Closed
Wan 2.6Alibaba (Qwen)3 Dec 2025400K––Closed
Seedance 2.0ByteDance Seed12 Feb 20264K––Closed
Grok Imagine Video 1.5 LitexAI1 Oct 20261K––Closed
MiniMax H3MiniMax31 Jul 2026–––Open

Change history

  • Output modalities changed from text, video to video
  • Input modalities changed from text, image, video to text, image, pdf
  • Max output changed from 66K to 261K
  • Max output changed from 261K to 66K
  • Output modalities changed from video to text, video
  • Input modalities changed from text, image, pdf to text, image, video
  • Input modalities changed from text, image, video to text, image, pdf
  • Max output changed from 66K to 261K
  • Output modalities changed from text, video to video
  • Input modalities changed from text, image, pdf to text, image, video
  • Structured output changed from none to no
  • Output modalities changed from video to text, video
  • Max output changed from 261K to 66K
  • Now listed on OpenRouter
  • Added to the directory
  • Now listed on Vercel AI Gateway

Sources