Published model/product name, not a reviewed standalone API selector.
Access
Managed Harvey workspace deployment. Confirm enabled model/component version and availability with the account configuration.
Regions
Harvey lists US, EU, Switzerland and Australia processing options across providers; actual availability varies by subprocessor and selected service. No universal region guarantee for this component.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
The default platform agreement prohibits training on customer content/data and restricts subprocessor retention or human-review logging, with a cloud-storage exception. September 16, 2026 service terms override conflicting general terms for optional Covered AI Services: subprocessors may retain data, conduct specified reviews, or process it in different locations. Workspace retention settings also have feature exceptions. The exact rules for this component require its service configuration and customer agreement; do not infer universal zero retention.
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.
Harvey platform
Not verified
No model-specific prompt-cache contract established. Saved preferences, vector storage, document retention and parametric memory are not inference-cache billing.
How it works
Not collected
No model-specific prompt-cache contract established. Saved preferences, vector storage, document retention and parametric memory are not inference-cache billing.
Minimum reusable input
Not collected
No model-specific prompt-cache contract established. Saved preferences, vector storage, document retention and parametric memory are not inference-cache billing.
Lifetime & refresh
Not collected
No model-specific prompt-cache contract established. Saved preferences, vector storage, document retention and parametric memory are not inference-cache billing.
How to enable it
Not collected
No model-specific prompt-cache contract established. Saved preferences, vector storage, document retention and parametric memory are not inference-cache billing.
Usage fields
Not collected
No model-specific prompt-cache contract established. Saved preferences, vector storage, document retention and parametric memory are not inference-cache billing.
Billing rules
Not collected
No model-specific prompt-cache contract established. Saved preferences, vector storage, document retention and parametric memory are not inference-cache billing.
Limits & data boundaries
Not collected
No model-specific prompt-cache contract established. Saved preferences, vector storage, document retention and parametric memory are not inference-cache billing.
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
Managed commercial Harvey product component. This record does not assert closed weights for its research backbones or convert open-weight ancestry into a proprietary foundation model.
