Google

Gemini Omni Flash Preview

CTX131K

Preview

98Quality

Video generation · Vision

Input$1.50/M

Output$17.50/M

Video generation and editing model for fast, conversational text- and image-to-video workflows

PaidProprietary934/1040

Drag to turn

GoogleVideoRarePreview

Gemini Omni Flash Preview

Video generation and editing model for fast, conversational text- and image-to-video workflows

gemini-omni-flash-preview

Type: Video
Quality: 98 · Top 2% on the LMArena Text to Video
Context window: 131,072 tokens
Max output: 65,536 tokens
Input price: $1.50 / 1M tokens
Output price: $17.50 / 1M tokens
Cache read: —
Cache write: —
Released: Jun 30, 2026
Knowledge cutoff: —
Takes in: Text, Image, Video
Puts out: Video
Reasoning: Yes
Tool calling: No
Structured output: No
File attachments: Yes
Access: Paid
License: Proprietary
Rarity: Rare
Set number: 934/1040

Open Google docs Quality 98 Where to run it 2 Meet its creature Battle cosmos-transfer2.5-2b

Weights aren’t public. Use is governed by Google’s terms. Specs from models.dev, last changed Oct 18, 2026. Official source: ai.google.dev.

How good is it?

Public leaderboard scores for Gemini Omni Flash Preview, refreshed daily from Epoch AI and LMArena.

Top 2% of the 48 models on the LMArena Text to Video: #2.

Quality is the share of a leaderboard’s models this one beats, from 0 to 100. Chat models are rated on Epoch AI’s Capabilities Index when it lists them, otherwise on LMArena; image and video models on LMArena’s image and video arenas.

Leaderboards

LMArena Text to Video#2 of 48
Two clips from the same prompt; people pick the better one.1,513 rating
Listed as gemini-omni-flash
LMArena Image to Video#6 of 48
Two clips animating the same image; people pick the better one.1,465 rating
Listed as gemini-omni-flash

Scores from LMArena, licensed CC BY 4.0. Boards list models under their own names, so a close match is shown with the name it was scored under. Credits

Where to run it

2 providers sell Gemini Omni Flash Preview through an API. Prices are per million tokens, cheapest first.

CheapestVercel AI Gateway$1.50 in · $9.00 out
From the labGoogle$1.50 in · $17.50 out

API providers

Provider	Input	Output	Context
Vercel AI GatewayCheapest paid`google/gemini-omni-flash-preview`	$1.50	$9.00	1M
GoogleOfficial`gemini-omni-flash-preview`	$1.50	$17.50	131K

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

Face off

Current video models from other labs at a similar output price.

vs cosmos-transfer2.5-2bNVIDIA · Free out per 1M