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.
Reve preview (historical)
Not verified
No reviewed prompt-cache contract or cache tariff. Layout reuse is not evidence of a billed prompt cache.
How it works
Not collected
No reviewed prompt-cache contract or cache tariff. Layout reuse is not evidence of a billed prompt cache.
Minimum reusable input
Not collected
No reviewed prompt-cache contract or cache tariff. Layout reuse is not evidence of a billed prompt cache.
Lifetime & refresh
Not collected
No reviewed prompt-cache contract or cache tariff. Layout reuse is not evidence of a billed prompt cache.
How to enable it
Not collected
No reviewed prompt-cache contract or cache tariff. Layout reuse is not evidence of a billed prompt cache.
Usage fields
Not collected
No reviewed prompt-cache contract or cache tariff. Layout reuse is not evidence of a billed prompt cache.
Billing rules
Not collected
No reviewed prompt-cache contract or cache tariff. Layout reuse is not evidence of a billed prompt cache.
Limits & data boundaries
Not collected
No reviewed prompt-cache contract or cache tariff. Layout reuse is not evidence of a billed prompt cache.
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
Private hosted-model classification is inferred from the provider identifying its own trained image models and reserving model rights under service terms. No matching weight release was established in this review. The layout research discloses continued training of open Qwen models; those upstream weights do not establish public availability of Reve derivatives or its renderer. Exact checkpoint provenance remains incomplete.
