Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Fujitsu / Takane

Takane 2.0 112B Vision

Multimodal Takane model based on Command A Vision, with Japanese adaptation, a reasoning mode and enterprise agent optimizations.

availableClosed weightsGeneral purposeText generationImage captioningDocument understanding
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
10 of 23 specification fields collected
Image input limitNot collectedAwaiting source review
Output typesTextSee specification notes below
Input billingNot collectedFujitsu enterprise Takane Vision
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
Reasoning
SupportedSource for Reasoning (opens in a new tab)

Explicitly described reasoning mode. Controls, billing and budget are unverified.

Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected

The platform chart, dated September 2025, plans November release. The December presentation calls three models released under a July header. Exact Vision launch date is ambiguous.

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

Documented focus, not an exhaustive list of supported languages.

Context caching
Not collected
Development partners
Fujitsu and CohereSource for Development partners (opens in a new tab)
Published price
Not collected

No numeric per-token price verified for this exact model. Enterprise service quotes and limited platform trials do not establish free production inference.

Base model
Cohere Command A VisionSource for Base model (opens in a new tab)
Hardware requirements
Two-GPU deploymentSource for Hardware requirements (opens in a new tab)

No universal GPU-memory minimum or speed guarantee inferred.

Model aliases
Takane-2.0-112B Vision, Takane 2.0-112B MMSource for Model aliases (opens in a new tab)

Platform guide uses MM for the planned multimodal tier. Mapping to the later Vision release is inferred from matching generation, size and multimodal description. Neither string is an API selector.

Access & pricing

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

Fujitsu enterprise Takane Vision

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

The published display name is not a verified API request selector. Tenant endpoint URLs and keys are issued by the provider.

Access
Released enterprise model documented by Fujitsu Research; private-deployment access and model selector require provider confirmation.
Regions
Service, contract and deployment determine location and access.

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.

Fujitsu enterprise Takane Vision

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.

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

Takane is a Fujitsu-specific enterprise model developed with Cohere, offered through private services and deployments. No matching public Takane checkpoint release was verified. Classification is inferred for the named Takane product, not for public Command-family weights or every Fujitsu research model.

Classification evidence (opens in a new tab)

Lifecycle dates

Documented as released in Fujitsu Research presentation23 Dec 2025Source (opens in a new tab)

Sources reviewed