Not established for this exact historical model. Image-generation capabilities do not establish a general language-model token budget or API contract.
Architecture
A trained layout model produces structured regions, followed by pixel rendering. The research describes continued pretraining and post-training of open Qwen language models; exact upstream versions and parameter counts are not specified.Source for Architecture (opens in a new tab)
Region-level position, size, description and optional reference/color attributes are represented in a hierarchical layout. This is an image workflow, not a general-purpose JSON-schema response guarantee.Source for Image layout controls (opens in a new tab)
Historical path and authentication contract not recovered from an accessible first-party schema.
Request quotas
Not collected
Exact historical request and concurrency quotas not established.
Image layout controls
The announced API separates layout creation, modification and rendering. Layout operations were experimental. Exact request/response schemas and tariffs were not recovered.Source for Image layout controls (opens in a new tab)
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 web (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
Reve API (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.
