LongCat is the budget pick: 720p text-to-video with a fast tier cheap enough to treat like a sketchpad.
LongCat is the least expensive text-to-video card in the catalog. Its fast tier is cheap enough to draft motion for an entire script in one sitting.
Like every model in Hiroska, its output lands on the timeline: trim the drafts, lay music and captions, and swap individual shots for premium renders as the edit firms up.
At a glance
Type: Text-to-video
Resolution: 720p
Tiers: Quality · Fast (distilled)
Cost: Cheapest text-to-video in the catalog (fast tier)
What it is best at
Rock-bottom per-shot cost on the fast tier
Motion drafts for a full script in one sitting
Same timeline, transitions and export as every other model
What it costs
From 23 tokens ($0.23) per clip; 85 tokens ($0.85) at the default settings.
Quality tier
Settings
Tokens
Price
Per clip
85
$0.85
Fast tier
Settings
Tokens
Price
Per clip
23
$0.23
Prices come from the live catalog at $0.0100 per token, the pay-as-you-go rate; subscriptions include tokens at a lower rate. The exact price is shown before you generate, and a failed generation is refunded.
Questions
What is LongCat good for?
Quantity: previsualising scripts, filler b-roll and testing prompt ideas. It is the model you use forty times before using a flagship once.
How cheap is LongCat?
The fast tier is the lowest-priced video render in the catalog. The token price appears in the picker before you commit.
Can I mix LongCat shots with shots from other models?
Yes. Every generation lands in the same Assets and timeline. A common cut mixes LongCat b-roll with Kling or Seedance hero shots.