The application documents a UI model name, not an exact API checkpoint selector.
Access
Local processing in the licensed desktop application. Hardware and app-version restrictions apply.
Regions
Local computer; hardware compatibility applies.
Billing basis
Not collected
Commercial application access; no independent numeric model tariff established. API credit prices do not determine this app’s cost.
Hardware requirements
Dedicated GPU: 8 GB VRAM recommended; 6 GB can work more slowly. Apple Silicon: macOS 14+, at least 16 GB RAM (24 GB recommended). Intel Macs and integrated-only graphics unsupported locally.Source for Hardware requirements (opens in a new tab)
Manual application batch steps are documented; presets are unsupported. The general cloud page says generative batching is unavailable, so this does not promise cloud batch execution.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.
Application plan statement, not a zero-price developer API or a numeric model tariff.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
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.
Topaz Photo desktop
Not verified
No prompt-cache contract established; local model loading is not a token-cache discount.
How it works
Not collected
No prompt-cache contract established; local model loading is not a token-cache discount.
Minimum reusable input
Not collected
No prompt-cache contract established; local model loading is not a token-cache discount.
Lifetime & refresh
Not collected
No prompt-cache contract established; local model loading is not a token-cache discount.
How to enable it
Not collected
No prompt-cache contract established; local model loading is not a token-cache discount.
Usage fields
Not collected
No prompt-cache contract established; local model loading is not a token-cache discount.
Billing rules
Not collected
No prompt-cache contract established; local model loading is not a token-cache discount.
Limits & data boundaries
Not collected
No prompt-cache contract established; local model loading is not a token-cache discount.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 15 Oct 2026
Topaz Photo Cloud Rendering
Not verified
No prompt-cache contract established; local model loading is not a token-cache discount.
How it works
Not collected
No prompt-cache contract established; local model loading is not a token-cache discount.
Minimum reusable input
Not collected
No prompt-cache contract established; local model loading is not a token-cache discount.
Lifetime & refresh
Not collected
No prompt-cache contract established; local model loading is not a token-cache discount.
How to enable it
Not collected
No prompt-cache contract established; local model loading is not a token-cache discount.
Usage fields
Not collected
No prompt-cache contract established; local model loading is not a token-cache discount.
Billing rules
Not collected
No prompt-cache contract established; local model loading is not a token-cache discount.
Limits & data boundaries
Not collected
No prompt-cache contract established; local model loading is not a token-cache discount.
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
Provider documentation identifies this as a Topaz AI model; the proprietary software terms reserve intellectual-property rights. Desktop downloads are licensed processing assets, not evidence of an open weight license.
