Specifications Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.
Context / input limit Not collected No public standalone model contract established. Unknown does not mean unsupported.
Maximum input tokens Not collected No public standalone model contract established. Unknown does not mean unsupported.
Maximum output Not collected No public standalone model contract established. Unknown does not mean unsupported.
Parameters Not collected No public standalone model contract established. Unknown does not mean unsupported.
Release date Not collected No public standalone model contract established. Unknown does not mean unsupported.
Knowledge cutoff Not collected No public standalone model contract established. Unknown does not mean unsupported.
Tool calling Not collected No public standalone model contract established. Unknown does not mean unsupported.
Structured output Not collected No public standalone model contract established. Unknown does not mean unsupported.
Streaming Not collected No public standalone model contract established. Unknown does not mean unsupported.
Batch processing Not collected No public standalone model contract established. Unknown does not mean unsupported.
Fine-tuning Not collected No public standalone model contract established. Unknown does not mean unsupported.
Reasoning Not collected No public standalone model contract established. Unknown does not mean unsupported.
Access & pricing Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.
API model ID Not collectedDescriptive catalog label, not a documented request selector.
Access Historical integrated generation. Current access and version pinning unverified.
Regions Exact model processing and storage region not established. Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms Public privacy policy describes service-related processing and purpose-dependent retention. Model-specific training use, PHI retention, processing region and contractual protections require the applicable enterprise agreement; no blanket no-training or zero-retention guarantee is inferred.
Read the service policy (opens in a new tab)
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 INPUT Process & retain The system processes eligible input and retains reusable state.
02 / LATER REQUEST Check available state Reuse depends on matching input, session state and the cache policy.
03 / CACHE HIT Reuse & generate Reusing state can reduce repeated work. Any charges follow the billing rules below.
Hippocratic AI enterprise platform Documented Internal serving optimization, not a customer cache API.
Support evidence (opens in a new tab) Minimum reusable input Not collected Public customer cache controls, thresholds, expiry and rates are not established.
Lifetime & refresh Not collected Public customer cache controls, thresholds, expiry and rates are not established.
Billing rules Not collected Public customer cache controls, thresholds, expiry and rates are not established.
Limits & data boundaries Not collected Public customer cache controls, thresholds, expiry and rates are not established.
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 constellation or named component. It is not asserted to be one independently identifiable private checkpoint.
Classification evidence (opens in a new tab) Sources reviewed Model notes Five system generations, four documented core families, contextual ASR and four managed components reviewed. Supervisor labels retained without asserting independent checkpoint identities. Remaining component and commercial details are unresolved.
Enterprise-integrated healthcare technology. Public descriptions do not establish a standalone inference API, model selector or downloadable checkpoint.
Provider benchmark and safety claims describe evaluated systems and conditions, not independent clinical guarantees for each component.
The AWS Marketplace listing offers a private commercial agreement. Its $0.001 Basic Plan contract dimension is not a per-token, per-call or per-minute inference rate.
Provider training and internal continuous batching do not establish customer fine-tuning or discounted Batch API support. Internal structured messages do not establish public schema-constrained generation.
Historical generation documented by the provider; present-day version pinning and continued access are unverified. Historical does not assert a retirement date.
Article and blog index show different September 2024 publication dates, so no exact model release date is asserted.
A 4K-token latency workload is an example, not the input or context ceiling.
Check against your workload Try representative inputs, measure task success and total cost, then check the exact endpoint’s data policy.
Read our methodology
Also from Hippocratic AI Polaris 1.0 Constellation Polaris 1.0 Primary Model Polaris 2.0 Primary Model Polaris 3.0 Constellation Polaris 4.0 Constellation Polaris 4.0 Core 300B Polaris 5.0 Constellation Polaris 5.0 Core 700B Polaris Contextual ASR Polaris Empathetic Voice / Clinical TTS Polaris Single Word Correction Polaris Targeted Clarification 