API versions identify request/response contracts, not model weights.
Input limits
Current contract: up to 128,000 text characters total, at most 16,000 characters per text part, and up to 20 images. Text is evaluated in overlapping windows.Source for Input limits (opens in a new tab)
An individual maximum does not waive the total request cap. These are documented MB/KB units, not converted to binary units.
Output formats
JSON labels with classifier or similarity type. Decisions: match, not_match or review. Escalation: none, completed or error. Classifier score is 0–1, or null when not scored.Source for Output formats (opens in a new tab)
Fixed service schema; no arbitrary output-schema generation contract.
Access & pricing
Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.
No public checkpoint selector established; a namespace or API date is not a model ID.
Access
Organization API key or short-lived bearer token. No authenticated inference was performed. Current typed-parts contract. Resolve the version by explicit header, account pin, then latest.
Regions
US and other processing countries may apply; verify the customer contract.
Current contract: up to 128,000 text characters total, at most 16,000 characters per text part, and up to 20 images. Text is evaluated in overlapping windows.Source for Input limits (opens in a new tab)
An individual maximum does not waive the total request cap. These are documented MB/KB units, not converted to binary units.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
The April 21, 2026 policy treats customer-submitted service content as processor/service-provider data governed by customer instructions and agreements. Retention of submitted data is contractual. Processing may take place in the United States and other countries where providers operate; no model-specific location, no-training or zero-retention guarantee is established.
No public checkpoint selector established; a namespace or API date is not a model ID.
Access
Organization API key or short-lived bearer token. No authenticated inference was performed. Superseded contract, supported through explicit version header or an account pin.
Regions
US and other processing countries may apply; verify the customer contract.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
The April 21, 2026 policy treats customer-submitted service content as processor/service-provider data governed by customer instructions and agreements. Retention of submitted data is contractual. Processing may take place in the United States and other countries where providers operate; no model-specific location, no-training or zero-retention guarantee is established.
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.
SafetyKit API
Not verified
No reviewed inference-cache contract. Presigned URL expiry, request idempotency, stored data and access-token expiry are not prompt caching.
How it works
Not collected
No reviewed inference-cache contract. Presigned URL expiry, request idempotency, stored data and access-token expiry are not prompt caching.
Minimum reusable input
Not collected
No reviewed inference-cache contract. Presigned URL expiry, request idempotency, stored data and access-token expiry are not prompt caching.
Lifetime & refresh
Not collected
No reviewed inference-cache contract. Presigned URL expiry, request idempotency, stored data and access-token expiry are not prompt caching.
How to enable it
Not collected
No reviewed inference-cache contract. Presigned URL expiry, request idempotency, stored data and access-token expiry are not prompt caching.
Usage fields
Not collected
No reviewed inference-cache contract. Presigned URL expiry, request idempotency, stored data and access-token expiry are not prompt caching.
Billing rules
Not collected
No reviewed inference-cache contract. Presigned URL expiry, request idempotency, stored data and access-token expiry are not prompt caching.
Limits & data boundaries
Not collected
No reviewed inference-cache contract. Presigned URL expiry, request idempotency, stored data and access-token expiry are not prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 16 Oct 2026
SafetyKit API
Not verified
No reviewed inference-cache contract. Presigned URL expiry, request idempotency, stored data and access-token expiry are not prompt caching.
How it works
Not collected
No reviewed inference-cache contract. Presigned URL expiry, request idempotency, stored data and access-token expiry are not prompt caching.
Minimum reusable input
Not collected
No reviewed inference-cache contract. Presigned URL expiry, request idempotency, stored data and access-token expiry are not prompt caching.
Lifetime & refresh
Not collected
No reviewed inference-cache contract. Presigned URL expiry, request idempotency, stored data and access-token expiry are not prompt caching.
How to enable it
Not collected
No reviewed inference-cache contract. Presigned URL expiry, request idempotency, stored data and access-token expiry are not prompt caching.
Usage fields
Not collected
No reviewed inference-cache contract. Presigned URL expiry, request idempotency, stored data and access-token expiry are not prompt caching.
Billing rules
Not collected
No reviewed inference-cache contract. Presigned URL expiry, request idempotency, stored data and access-token expiry are not prompt caching.
Limits & data boundaries
Not collected
No reviewed inference-cache contract. Presigned URL expiry, request idempotency, stored data and access-token expiry are not prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 16 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
Provider-operated classifier or analysis service delivered through its commercial platform/API. Private ownership of every underlying model is not asserted.
