Gemini Omni 1.1 Flash pricing, plans and limits

Replacing Google's May 2026 preview, this model brings chat-driven editing and chained scene extension, and Google lists an unusually large context window for a video model. It suits teams iterating fast on social and ad clips, while Google's Veo line remains the pick for native high-resolution cinematic takes.

Gemini Omni 1.1 Flash is Google's video generation and editing model, generally available in the Gemini API since August 27, 2026. Each pass makes a short 24 FPS clip with synchronized audio, extensions chain into a longer scene, and the model sits below the board leader on Artificial Analysis' text-to-video chart with audio as of October 2026.

Provider: Google · Family: Gemini Omni

More about Google on HokAI

Context window: 1,048,576 tokens

Input modalities: text, image, video · Output: video, audio

About Gemini Omni 1.1 Flash

Built by Google inside Google DeepMind, Gemini Omni 1.1 Flash is a multimodal video generation and editing model. It reached general availability on August 27, 2026, replacing the gemini-omni-flash-preview endpoint, which Google's deprecations page lists for shutdown on October 22, 2026. It belongs to the Gemini Omni family, first previewed in May 2026 at Google I/O. Google's deprecations page also names it as the replacement for the Veo 3.1 preview endpoints that retire on the same date, although Veo 3.1 remains the better fit for cinematic single takes. Unlike Google's text-first Gemini models, Omni Flash takes text, images and short reference videos and returns video with synchronized audio.

Because the model generates video rather than text, it is not scored on SWE-bench or MMLU. Google instead submits it to the crowd-sourced Artificial Analysis Video Arena, where human raters compare blind clip pairs. On the board's current text-to-video version (AA-Video-T2V v2.0, with audio), checked on October 7, 2026, Gemini Omni Flash 1.1 holds an Elo of 1113. Wan 3.0 leads that board at 1156, and MiniMax H3, Seedance 2.5 and FLUX 3 all sit above it. Artificial Analysis' image-to-video board lists the original Gemini Omni Flash rather than the 1.1 release, so HokAI stores no image-to-video score for 1.1.

Google's model page lists a 1,048,576-token context window and output of 3 to 10 seconds per generation at 24 FPS, with resolution options from 360p up to 4K. Google's docs label the higher tiers as upscaled output from the default render. Extension adds a continuation of up to 10 seconds to a clip, up to a total length of 40 seconds. Video references are limited to 3 clips of up to 3 seconds each, and any audio in a reference video is ignored. Google's limitations list says uploading audio references is not supported in the current API version, so audio is something the model generates, not something you feed it.

Gemini API pricing follows Google's per-token structure: one input rate across modalities and separate output rates for generated video and generated text. Video output cost scales with duration, since Google converts rendered seconds into a fixed number of output tokens before billing. There is no free tier for this model; access is paid from the first generation. The exact rates are in the pricing FAQ below.

Access runs through Google AI Studio and the Gemini API, with the model also available through Vertex AI, the Gemini Enterprise Agent Platform and Flow, Google's video-editing product. Google AI Plus, Pro and Ultra subscribers can use scene extension in the consumer Gemini app. Provisioned throughput is not supported, and system instructions, temperature, top_p, stop sequences and negative prompts are not available either. Users in the European Economic Area, Switzerland and the United Kingdom cannot edit or extend uploaded videos, though editing or extending clips the model generated still works. Every output carries mandatory SynthID watermarking.

The model fits teams doing fast, iterative video work: social clips, ad drafts and workflows built around refining a result through chat rather than one perfect upfront prompt. Teams that need a genuine native high-resolution deliverable should look at Veo 3.1 instead, and teams that want the top Arena score in the current text-to-video board should weigh Wan 3.0 and MiniMax H3, each of which Artificial Analysis rates higher. The Gemini Omni Flash guide covers which jobs it suits. Kling 3.0 is another option for teams comparing 2026 video generators. Google's own documentation says English is the only fully evaluated prompt language, and it has not published a training-data cutoff for this model. The model's maker is profiled on the Google page.

Pricing

Input (text, image, video; Google's pricing table also names audio) is $1.50 per 1M tokens. Video output is $17.50 per 1M tokens, converted at a fixed 5,792 tokens per second of 720p video, about $0.10 per second. Text output during conversational editing bills separately at $9.00 per 1M tokens. Google's pricing page lists a Standard tier only, with no free tier. See also [Gemini Omni Flash for video work](/guides/what-gemini-omni-flash-is-for).

What a real job costs

Budgets: 20-page PDF = 30k in / 1k out · Support reply = 2k in / 300 out · Coding agent run = 200k in / 20k out. Computed from the vendor's per-token prices at render time; cached-input discounts are not applied.

Key Features

• Scene Extension to 40 Seconds: Chains 10-second generation passes up to a 40-second cumulative scene, analyzing up to 10 seconds of prior footage per extension.
• First-and-Last-Frame Interpolation: Generates a continuous transition clip between two supplied keyframes, giving direct control over how a shot starts and ends.
• Native Synchronized Audio: Generates audio in sync with the video from the same prompt, billed separately from video tokens.
• Resolution Control, 360p Drafts to 4K Upscale: Renders fast 360p previews for iteration, then upscales the same generation to 1080p or 4K; native output tops out at 720p.
• Reference Video Input: Accepts as many as three short reference clips, capped at 3 seconds each, so a scene keeps consistent characters, style, or camera movement across edits.
• Conversational Multi-Turn Editing: Refines a generated clip through follow-up chat instructions in AI Studio or the Gemini app instead of one single upfront prompt.

Pros

• Chat-based re-editing removes the need to rewrite one perfect prompt: users nudge a generated clip through follow-up turns instead of restarting from scratch.
• The chained scene-extension feature reaches a longer cumulative clip than a single take from Google's own Veo line, useful for anything needing more than one short shot.
• Mandatory SynthID watermarking on every clip gives compliance teams a built-in provenance check with no extra integration work.
• Accepts text, images and up to three short reference videos in one call, more input flexibility than a text-and-image-only rival.

Cons

• No free tier: every generation costs money from the first clip, with no AI Studio quota to test on before committing budget.
• Higher-resolution outputs are upscales of a lower native render rather than true higher-resolution generations, a gap Google's own Veo line does not have.
• Speech editing on uploaded video is disabled, limiting one class of conversational edit some users will expect from a video-editing model.
• Google has not published a training-data cutoff, an architecture description, or a fixed rate limit for this model, less transparency than its text-model system cards provide.

Benchmarks

• AA Text To Video Arena Elo With Audio: 1113 cited: Artificial Analysis · 07 Oct 2026

A benchmark is an exam, not the job. Scores transfer unevenly between tasks, so weigh the one closest to your workload and read every figure with its source.

Visit Gemini Omni 1.1 Flash Official Page