Compact vision-language model for document understanding, OCR and visual question answering, with a documented single-A10 BF16 deployment configuration.
No exhaustive language list or per-language quality guarantee supplied.
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.
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.
WideLabs on Oracle Cloud Infrastructure
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
ChartQA
WideLabs · vendor-reported
86.5reported score
Provider technical-sheet score. Dataset versions, splits, prompts, shot counts and evaluation dates are not supplied; the published numeric scale is preserved without treating it as independently reproduced accuracy. Scores from other providers may not be directly comparable.
Provider technical-sheet score. Dataset versions, splits, prompts, shot counts and evaluation dates are not supplied; the published numeric scale is preserved without treating it as independently reproduced accuracy. Scores from other providers may not be directly comparable.
Provider technical-sheet score. Dataset versions, splits, prompts, shot counts and evaluation dates are not supplied; the published numeric scale is preserved without treating it as independently reproduced accuracy. Scores from other providers may not be directly comparable.
Provider technical-sheet score. Dataset versions, splits, prompts, shot counts and evaluation dates are not supplied; the published numeric scale is preserved without treating it as independently reproduced accuracy. Scores from other providers may not be directly comparable.
Provider technical-sheet score. Dataset versions, splits, prompts, shot counts and evaluation dates are not supplied; the published numeric scale is preserved without treating it as independently reproduced accuracy. Scores from other providers may not be directly comparable.
Provider technical-sheet score. Dataset versions, splits, prompts, shot counts and evaluation dates are not supplied; the published numeric scale is preserved without treating it as independently reproduced accuracy. Scores from other providers may not be directly comparable.
Provider technical-sheet score. Dataset versions, splits, prompts, shot counts and evaluation dates are not supplied; the published numeric scale is preserved without treating it as independently reproduced accuracy. Scores from other providers may not be directly comparable.
Provider technical-sheet score. Dataset versions, splits, prompts, shot counts and evaluation dates are not supplied; the published numeric scale is preserved without treating it as independently reproduced accuracy. Scores from other providers may not be directly comparable.
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
WideLabs calls this a proprietary model family. Its model license covers weights and parameters and restricts redistribution, sublicensing and reverse engineering; licensed customer deployments do not constitute a public weight release.
