First Luna Crescent launch; later family revisions are not individually named.
Knowledge cutoff
Not collected
No reviewed model-specific inference contract. Unknown does not mean unsupported.
Tool calling
Not collected
No reviewed model-specific inference contract. Unknown does not mean unsupported.
Structured output
Not collected
No reviewed model-specific inference contract. Unknown does not mean unsupported.
Streaming
Not collected
No reviewed model-specific inference contract. Unknown does not mean unsupported.
Batch processing
Not collected
No reviewed model-specific inference contract. Unknown does not mean unsupported.
Fine-tuning
Not collected
No reviewed model-specific inference contract. Unknown does not mean unsupported.
Reasoning
Not collected
No reviewed model-specific inference contract. Unknown does not mean unsupported.
Context caching
Not collected
No reviewed model-specific inference contract. Unknown does not mean unsupported.
Base model
Not collected
The provider describes a capable general-purpose starting model, but does not identify the exact ancestor or version.
Architecture
General-purpose foundation model adapted with proprietary legal training, then repeatedly retrained and gated by benchmark and expert review.Source for Architecture (opens in a new tab)
No public standalone model selector is established; document and task IDs are application identifiers.
Access
Commercial product access under an order form. Fees and document allowances are contractual; no standalone per-token model rate is published in the reviewed sources.
Regions
Customer AWS hosting location is set by order form. Additional Generative Model processing can differ; the current subprocessor page lists direct OpenAI processing in the United States.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
Current Master Agreement v3.1 permits customer-specific Private Learning and product improvement; non-identifying Usage Insights may be retained without customer confidential or personal data. It also authorizes feature-dependent transfers to external model APIs. The subprocessor page distinguishes in-cloud processing from direct OpenAI processing in the US. Security measures describe deletion from primary stores within 30 days and backups within a further 30 days; contract retention and order-form provisions also apply. This is not universal zero retention or an inference-cache lifetime.
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.
Luminance platform
Not verified
No model-specific inference-cache contract. Application memory, precomputed legal data, saved searches and retention are distinct.
How it works
Not collected
No model-specific inference-cache contract. Application memory, precomputed legal data, saved searches and retention are distinct.
Minimum reusable input
Not collected
No model-specific inference-cache contract. Application memory, precomputed legal data, saved searches and retention are distinct.
Lifetime & refresh
Not collected
No model-specific inference-cache contract. Application memory, precomputed legal data, saved searches and retention are distinct.
How to enable it
Not collected
No model-specific inference-cache contract. Application memory, precomputed legal data, saved searches and retention are distinct.
Usage fields
Not collected
No model-specific inference-cache contract. Application memory, precomputed legal data, saved searches and retention are distinct.
Billing rules
Not collected
No model-specific inference-cache contract. Application memory, precomputed legal data, saved searches and retention are distinct.
Limits & data boundaries
Not collected
No model-specific inference-cache contract. Application memory, precomputed legal data, saved searches and retention are distinct.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 16 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 explicitly owns the resulting specialist model and proprietary legal training, while acknowledging a general-purpose base that may be available to others. No public derivative weights or standalone selector are offered in the reviewed sources.
