No public checkpoint selector established; a namespace or API date is not a model ID.
Access
Private model described in the official case study. Current access to this exact historical derivative remains unverified.
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 platform
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
Official OpenAI documentation identifies a SafetyKit reinforcement-fine-tuned o3-mini derivative. No public derivative weights or independently selectable model ID are established.
