Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Hippocratic AI / Polaris

Polaris 5.0 Constellation

Current healthcare voice system combining a 700B core, clinical speech models and specialized supervisors.

Speech & voice
restrictedClosed-source managed componentSpeech generation
Official documentation (opens in a new tab)Reviewed 16 Oct 2026
5 of 17 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingNot collectedHippocratic AI enterprise platform
Output billingNot collectedNo inferred price

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
2026-04-30Source for Release date (opens in a new tab)
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.

Context caching
Not collected

No public standalone model contract established. Unknown does not mean unsupported.

Input modalities
AudioSource for Input modalities (opens in a new tab)
Output modalities
AudioSource for Output modalities (opens in a new tab)
Model sizes
5 trillion aggregate parameters; current directory describes 5T+.Source for Model sizes (opens in a new tab)
Documented supervisor labels
View all 55 entries
  • Escalation Supervisor Model
  • Medication Recognition Supervisor Model
  • Clarify Supervisor Model
  • Med Stoppage Supervisor Model
  • Safety Escalation Supervisor Model
  • Scope of Practice Supervisor Model
  • Escalations Supervisor Model
  • Motivational Interviewing Supervisor Model
  • Clinical Deep Thinking Form Fill Supervisor Model
  • DME Supervisor Model
  • SDOH Supervisor Model
  • Longitudinal Adherence Supervisor Model
  • Acoustic Bio-Marker Supervisor Model
  • Health Literacy Supervisor Model
  • POC Knowledge Supervisor Model
  • Tangent Supervisor Model
  • Do No Harm Guardrails Supervisor Model
  • Implicit Understanding Supervisor Model
  • Emotional Safety Supervisor Model
  • Angel Supervisor Model
  • Trust Building Supervisor Model
  • Dynamic Personality Engine Supervisor Model
  • Telemed Supervisor Model
  • Common Sense Internalization Supervisor Model
  • Care Coordination Supervisor Model
  • Appointment Upgrade Supervisor Model
  • Mainline Escalation Supervisor Model
  • Anticipatory Guidance Supervisor Model
  • Specialty Appointment Scheduling Supervisor Model
  • Caregiver Rapport Supervisor Model
  • Caregiver SDOH Supervisor Model
  • Caregiver Clarification Supervisor Model
  • AE & PC Supervisor Model
  • Medical Device Report Supervisor Model
  • Clinical Trial Support Supervisor Model
  • Patient Services Supervisor Model
  • Device Support Supervisor Model
  • Medical Affairs Supervisor Model
  • Rep Enablement Supervisor Model
  • Drug Name Pronunciation (TTS) Supervisor Model
  • IVR Supervisor Model
  • Natural Disaster Handling Supervisor Models
  • Probe Further Supervisor Model
  • Provider Match Supervisor Model
  • Interlinked RAG Supervisor Model
  • Caregiver Speech Supervisor Model
  • MCI Supervisor Model
  • Bi-lingual Switch Supervisor Model
  • Multi-lingual Supervisor Model
  • Contextual ASR Supervisor Model
  • Noise Cancellation Supervisor Model
  • Multi-call Memory Supervisor Model
  • Clinical Nutrition Supervisor Model
  • Contextual Understanding Supervisor Model
  • Intuition Supervisor Model
Source for Documented supervisor labels (opens in a new tab)

Website labels, not an independently verified checkpoint count. Several labels may share or contain multiple models.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Hippocratic AI enterprise platform

Provider source (opens in a new tab)
API model ID
Not collected

Descriptive catalog label, not a documented request selector.

Access
Enterprise service by commercial agreement; standalone access to this component is not established.
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 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.

Hippocratic AI enterprise platform

Not verified

Public customer cache controls, thresholds, expiry and rates are not established.

How it works
Not collected

Public customer cache controls, thresholds, expiry and rates are not established.

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.

How to enable it
Not collected

Public customer cache controls, thresholds, expiry and rates are not established.

Usage fields
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