Exact architecture, parameter count and source checkpoint are not published in this reference. The advertised 10-second turnaround is not a measured latency guarantee.
Languages
Not collected
Not established for this exact hosted revision. A video API does not imply language-model capabilities or token limits.
Context caching
Not collected
Not established for this exact hosted revision. A video API does not imply language-model capabilities or token limits.
Published per-video-second charge. Input-versus-output accounting, minimum duration, rounding and failure/refund treatment are not specified on this model page.Source for Billing basis (opens in a new tab)
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 15 Oct 2026
Category
Usage
Rate
Unit
Historical video editing
720p video editing1
$0.04
video second
Rate conditions
Historical tariff: Fal endpoint is no longer supported. Input/output duration accounting and billing rounding are not established. No text-token estimate.
Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.
Caching
Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.
01 / INITIAL INPUTProcess & retain
The system processes eligible input and retains reusable state.
02 / LATER REQUESTCheck available state
Reuse depends on matching input, session state and the cache policy.
03 / CACHE HITReuse & generate
Reusing state can reduce repeated work. Any charges follow the billing rules below.
Fal
decart/lucy-edit/fast
Not verified
No model inference-cache policy or discounted cache price collected. File uploads and queue results are separate mechanisms.
How it works
Not collected
No model inference-cache policy or discounted cache price collected. File uploads and queue results are separate mechanisms.
Minimum reusable input
Not collected
No model inference-cache policy or discounted cache price collected. File uploads and queue results are separate mechanisms.
Lifetime & refresh
Not collected
No model inference-cache policy or discounted cache price collected. File uploads and queue results are separate mechanisms.
How to enable it
Not collected
No model inference-cache policy or discounted cache price collected. File uploads and queue results are separate mechanisms.
Usage fields
Not collected
No model inference-cache policy or discounted cache price collected. File uploads and queue results are separate mechanisms.
Billing rules
Not collected
No model inference-cache policy or discounted cache price collected. File uploads and queue results are separate mechanisms.
Limits & data boundaries
Not collected
No model inference-cache policy or discounted cache price collected. File uploads and queue results are separate mechanisms.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 15 Oct 2026
What the measurements say
No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.
Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.
The record behind the model
Why it is included
Hosted model identity and proprietary API terms, with no matching checkpoint in the reviewed official public-weight inventory. The provider distinguishes hosted Pro from downloadable Lucy Edit Dev. Closed-weight status for this exact hosted variant is an evidence-based inference, not a claim about the open Dev releases.
