google/gemini-omni-1.2-flash

模型发布 OpenRouter 模型 原文语言:中文

OpenRouter 于 2026-11-06 收录该模型(收录时间不等于模型正式发布日期);上下文:131,072 tokens;输入价:$1.5000/百万 tokens;输出价:$9.0000/百万 tokens;定位(来源描述):Gemini Omni 1.2 Flash is Google's native multimodal video generation and editing model, the…

全文

Google: Gemini Omni 1.2 Flash

google/gemini-omni-1.2-flash

BenchmarksCompare

Gemini Omni 1.2 Flash is Google's native multimodal video generation and editing model, the successor to Gemini Omni 1.1 Flash. It generates clips up to 15 seconds long with native audio in 16:9 or 9:16, from 360p drafts up to 4K, and supports text-to-video, image-to-video, first and last frame interpolation, subject and video references with improved reference management, and editing or extending an uploaded video. Multi-turn editing and extension of a prior generation is supported through previous_job_id.

Note: video generation is only supported through the Video Generation API. See the guide: https://openrouter.ai/docs/guides/overview/multimodal/video-generationOpens in new tab

Modalities

In / out price

$1.50 / $9per 1M

Context

131K

Released

Nov 5, 2026

BenchmarksCompare

Playground

Providers

This model is hosted by one provider. OpenRouter forwards every request without routing.

End-to-end latency

$1.50$9.00$0.02317239.49s9.1 s/min

31.52%

ProviderInput / Output /M

Input $1.50 / Output $9.00

39.49s latency31.52% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$1.50/M tokens

Output

$9/M tokens

Gemini Omni 1.2 Flash — Price history

Price history

No effective price data for this selection

$1.50$9.000.0%100.0%

ProviderInput / Output /M

Token share

Effective in $1.50 / Effective out $9.00

Token share

100.0%

Performance

Generation time is how long a video takes from submission to completion (lower is better). Speed is seconds of video generated per minute of generation time (higher is better).

End-to-end latency

39.49s

P50, best provider

Speed

9.1s/min

P50, best across providers

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)The model was reachable. Request routed to a provider.

100.00%

Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.

52.78%

Availability over the last 3 days

Last 72 hours

Availability 52.78%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

41.58%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

1.

model.lol

new

21.5Mtokens

2.

Caltech Tools Wayback Repair

new

3.72Mtokens

3.

WriteSumo

new

2.03Mtokens

4.

Open WebUI

Open WebUI is a self-hosted AI platform providing a chat interface for Large Language Models.

1.76Mtokens

5.

aikoolitus.eu

new

1.52Mtokens

Rest of OpenRouter

4.34M

Top 5 Apps

5K

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Not currently available through EU in-region routing. In-region routing docs

Frequently asked questions

Gemini Omni 1.2 Flash is Google's native multimodal video generation and editing model, the successor to Gemini Omni 1.1 Flash. It generates clips up to 15 seconds long with native audio in 16:9 or 9:16, from 360p drafts up to 4K, and supports text-to-video, image-to-video, first and last frame interpolation, subject and video references with improved reference management, and editing or...

Gemini Omni 1.2 Flash costs $1.50/M input tokens and $9.00/M output tokens, with separate rates for Video (with audio) at from $0.02317/second at 360p to $0.2085/second at 4K.

Gemini Omni 1.2 Flash has a 131,072 token context window. It supports up to 65,536 completion tokens.

No. Gemini Omni 1.2 Flash does not accept tools, so function calling is unavailable. It does not support response_format, so JSON output is not enforced.

Gemini Omni 1.2 Flash accepts text, images, and video as input and returns text and video.

Gemini Omni 1.2 Flash is served by 1 provider on OpenRouter: Google AI Studio.

Gemini 4 Hydrogen, Gemini Decision 1, Gemini 4 Carbon and 31 more are other text models from Google.

Gemini Omni 1.2 Flash was released on November 5, 2026.

正文以来源语言显示。

参考来源

← 返回每日简报