Local development focus; complete supported-language roster not verified.
Context caching
Not collected
No model-specific prompt-cache contract, minimum prefix, retention period or cached-input price verified. Private vLLM deployment does not establish a managed caching feature.
Published price
Not collected
No numeric model-specific API or private deployment price verified. A free web chat or a BYOL marketplace listing is not free inference.
Display names, marketplace image versions and document revision labels are not verified API model selectors.
Access
Launched as part of the PatagonIA family; contact the provider for model-specific enterprise access, licensing, quotas and deployment options.
Regions
Provider and partner describe training and deployment on OCI infrastructure in Chile; customer contract and operating configuration require confirmation.
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.
Display names, marketplace image versions and document revision labels are not verified API model selectors.
Access
Account-based chat is advertised. API integration is promoted, but public model selectors and numerical pricing were not verified.
Regions
Model deployment is described as Chile-based. The linked platform notices allow some international personal-data transfers and contain Brazil-specific template language; they are not a blanket Chile-only data guarantee.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
Linked platform terms say inputs and outputs are not used to train WideLabs models. The privacy notice allows purpose-based retention, legal exceptions and service-provider sharing. No fixed retention period or zero-retention commitment is specified.
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.
WideLabs / ISCI PatagonIA 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
PatagonIA web platform
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
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
The official PatagonIA terms identify WideLabs ownership, prohibit unauthorized copying and reverse engineering of underlying models, and provide platform access rather than public weights. The partner launch separately identifies the language, OCR-focused multimodal and STT models. The role-based Atlas names for these three models are descriptive, not published API selectors.
