/ Ricoh / Ricoh-13B Ricoh / Ricoh LLM
Ricoh-13B Japanese and English adaptation of Llama 2 13B, designed for customer-specific private language models.
historical Closed weights Text generation
Context window Not collected Awaiting source review
Maximum output Not collected Awaiting source review
Input billing Not collected Ricoh private cloud (historical)
Output billing Not collected No inferred price
Specifications Access & pricing Caching Evaluation Sources & lifecycle
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
Maximum input tokens Not collected
Maximum output Not collected
Reasoning Not collected
Tool calling Not collected
Structured output Not collected
Streaming Not collected
Batch processing Not collected
Knowledge cutoff Not collected
Architecture Not collected Context caching Not collected No model-specific prompt-cache contract, lifetime or cached-input price verified. Quantization and image-token compression are not prompt caching.
Published price Not collected No numeric model-specific production rate verified. Private deployment does not establish free inference.
Access & pricing Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.
API model ID Not collectedPublished model name is not a verified API request selector.
Access Provider reports private-cloud LLM service from April 2024. Exact base-checkpoint availability today remains unverified.
Regions Customer-selected private environment; region and residency depend on the deployment agreement. 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 INPUT Process & retain The system processes eligible input and retains reusable state.
02 / LATER REQUEST Check available state Reuse depends on matching input, session state and the cache policy.
03 / CACHE HIT Reuse & generate Reusing state can reduce repeated work. Any charges follow the billing rules below.
Ricoh private cloud (historical) Not verified
How it works Not collected
Minimum reusable input Not collected
Lifetime & refresh Not collected
How to enable it Not collected
Usage fields Not collected
Billing rules Not collected
Limits & data boundaries Not collected No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 14 Oct 2026
What the measurements say
Four-category Japanese evaluation average Ricoh · vendor-reported 67% January 4, 2024 provider evaluation. Category means and overall mean from the original table; not independent measurements.
Evaluation source (opens in a new tab)
Japanese multiple-choice QA Ricoh · vendor-reported 72.7% January 4, 2024 provider evaluation. Category means and overall mean from the original table; not independent measurements.
Evaluation source (opens in a new tab)
Japanese natural language inference Ricoh · vendor-reported 50.4% January 4, 2024 provider evaluation. Category means and overall mean from the original table; not independent measurements.
Evaluation source (opens in a new tab)
Japanese question answering Ricoh · vendor-reported 56.3% January 4, 2024 provider evaluation. Category means and overall mean from the original table; not independent measurements.
Evaluation source (opens in a new tab)
Japanese reading comprehension Ricoh · vendor-reported 88.5% January 4, 2024 provider evaluation. Category means and overall mean from the original table; not independent measurements.
Evaluation source (opens in a new tab)
ELYZA-tasks-100 without instruction tuning Ricoh · vendor-reported 1.19score / 5 June 2024 provider comparison of the base with two separately tuned variants.
Evaluation source (opens in a new tab) 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 identifies this separately trained model for research or private deployment. No matching public derivative was verified in the two provider-linked weight inventories. Closed-weight classification is inferred for this exact revision, not its public upstream base; private distribution terms remain to be confirmed.
Classification evidence (opens in a new tab) Lifecycle dates Sources reviewed 