Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Ricoh / Ricoh LLM

Llama-3.3-Ricoh-70B-20250325

March 2025 revision of Ricoh’s private 70B Japanese model, announced publicly in April.

Language models (LLMs)
historicalClosed weightsText generation
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
8 of 20 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingNot collectedRicoh private deployment
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
Maximum input tokens
Not collected
Maximum output
Not collected
Input modalities
TextSource for Input modalities (opens in a new tab)
Output modalities
TextSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
Not collected
Fine-tuning
SupportedSource for Fine-tuning (opens in a new tab)

Provider describes customer-specific training or adaptation for private deployment, not a public self-service fine-tuning API.

Knowledge cutoff
Not collected
Release date
2025-04-03Source for Release date (opens in a new tab)

Public announcement date, not a date inferred from the model ID.

Parameters
70BSource for Parameters (opens in a new tab)
Architecture
Not collected
Languages
JapaneseSource for Languages (opens in a new tab)

Documented focus; not an exhaustive supported-language list.

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.

Base model
Llama-3.3-Swallow-70B-v0.4Source for Base model (opens in a new tab)
Published training method
Model merging with Meta and Ricoh Chat VectorsSource for Published training method (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Ricoh private deployment

Provider source (opens in a new tab)
API model ID
Not collected

Published model name is not a verified API request selector.

Access
Provider-arranged enterprise deployment. Confirm availability of this exact revision, serving configuration and commercial terms with Ricoh.
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 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.

Ricoh private deployment

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

Japanese MT-Bench

Ricoh · vendor-reported
8.62score / 10

March 25, 2025 provider evaluation, gpt-4o-2024-08-06 judge. ELYZA values are explicitly multiplied by two; do not compare 9.06 to a five-point score.

Evaluation source (opens in a new tab)

ELYZA-tasks-100 (doubled)

Ricoh · vendor-reported
9.06score / 10

March 25, 2025 provider evaluation, gpt-4o-2024-08-06 judge. ELYZA values are explicitly multiplied by two; do not compare 9.06 to a five-point score.

Evaluation source (opens in a new tab)

Mean of MT-Bench and doubled ELYZA score

Ricoh · vendor-reported
8.84score / 10

March 25, 2025 provider evaluation, gpt-4o-2024-08-06 judge. ELYZA values are explicitly multiplied by two; do not compare 9.06 to a five-point score.

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

Model announced3 Apr 2025Source (opens in a new tab)

Sources reviewed