Input billingNot collectedLexica web (historical identity)
Output billingNot collectedNo inferred price
Specifications
Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.
Context / input limit
Not collected
Not established for this exact Aperture version. Image output and a four-image web request do not establish a language token budget or asynchronous Batch API.
Maximum input tokens
Not collected
Not established for this exact Aperture version. Image output and a four-image web request do not establish a language token budget or asynchronous Batch API.
Maximum output
Not collected
Not established for this exact Aperture version. Image output and a four-image web request do not establish a language token budget or asynchronous Batch API.
Maximum prompt characters
Not collected
Not established for this exact Aperture version. Image output and a four-image web request do not establish a language token budget or asynchronous Batch API.
Reasoning
Not collected
Not established for this exact Aperture version. Image output and a four-image web request do not establish a language token budget or asynchronous Batch API.
Tool calling
Not collected
Not established for this exact Aperture version. Image output and a four-image web request do not establish a language token budget or asynchronous Batch API.
Structured output
Not collected
Not established for this exact Aperture version. Image output and a four-image web request do not establish a language token budget or asynchronous Batch API.
Streaming
Not collected
Not established for this exact Aperture version. Image output and a four-image web request do not establish a language token budget or asynchronous Batch API.
Batch processing
Not collected
Not established for this exact Aperture version. Image output and a four-image web request do not establish a language token budget or asynchronous Batch API.
Fine-tuning
Not collected
Not established for this exact Aperture version. Image output and a four-image web request do not establish a language token budget or asynchronous Batch API.
Context caching
Not collected
Not established for this exact Aperture version. Image output and a four-image web request do not establish a language token budget or asynchronous Batch API.
Knowledge cutoff
Not collected
Not established for this exact Aperture version. Image output and a four-image web request do not establish a language token budget or asynchronous Batch API.
Release date
Not collected
Not established for this exact Aperture version. Image output and a four-image web request do not establish a language token budget or asynchronous Batch API.
Parameters
Not collected
Not established for this exact Aperture version. Image output and a four-image web request do not establish a language token budget or asynchronous Batch API.
Architecture
Not collected
Not established for this exact Aperture version. Image output and a four-image web request do not establish a language token budget or asynchronous Batch API.
Languages
Not collected
Not established for this exact Aperture version. Image output and a four-image web request do not establish a language token budget or asynchronous Batch API.
Published client dimension presets, not a verified backend maximum or an upscaled export limit. For historical versions these are retained client tables, not proof of current access.
Images created on Starter or Pro are public. Max images are private unless shared. Exact storage retention and training-use policy were not established.Source for Creation privacy (opens in a new tab)
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
Starter and Pro images are public and may appear in search. Max images are private unless shared. Commercial image use depends on plan and team size. Output-image licensing does not disclose model weights, retention periods or a training opt-out.
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.
Lexica web (historical identity)
lexica-aperture-v2
Not verified
No reviewed prompt caching contract or discounted cache tariff. Image search and stored generation history are not prompt-cache billing.
How it works
Not collected
No reviewed prompt caching contract or discounted cache tariff. Image search and stored generation history are not prompt-cache billing.
Minimum reusable input
Not collected
No reviewed prompt caching contract or discounted cache tariff. Image search and stored generation history are not prompt-cache billing.
Lifetime & refresh
Not collected
No reviewed prompt caching contract or discounted cache tariff. Image search and stored generation history are not prompt-cache billing.
How to enable it
Not collected
No reviewed prompt caching contract or discounted cache tariff. Image search and stored generation history are not prompt-cache billing.
Usage fields
Not collected
No reviewed prompt caching contract or discounted cache tariff. Image search and stored generation history are not prompt-cache billing.
Billing rules
Not collected
No reviewed prompt caching contract or discounted cache tariff. Image search and stored generation history are not prompt-cache billing.
Limits & data boundaries
Not collected
No reviewed prompt caching contract or discounted cache tariff. Image search and stored generation history are not prompt-cache billing.
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 describing its model training work and distinguishing its Aperture model from public Stable Diffusion images, its subscription-only generation service, and no matching weight distribution established in the reviewed first-party sources. This is not an explicit weight-license statement. Exact upstream architecture and derivative ancestry remain unresolved; the output image license is not a weight license.