Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Ambience Healthcare / Clinical documentation and coding

Ambience ICD-10 RFT (o3-mini)

Documented private o3-mini derivative trained to recommend medical billing codes from clinical encounter context.

historicalClosed weightsText analysis
Official documentation (opens in a new tab)Reviewed 16 Oct 2026
7 of 18 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingNot collectedAmbience Healthcare clinical 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 model-specific public inference contract established. Unknown does not mean unsupported.

Maximum input tokens
Not collected

No model-specific public inference contract established. Unknown does not mean unsupported.

Maximum output
Not collected

No model-specific public inference contract established. Unknown does not mean unsupported.

Parameters
Not collected

No model-specific public inference contract established. Unknown does not mean unsupported.

Release date
2025-05-27Source for Release date (opens in a new tab)

Public announcement date, not a training completion date or a public API release.

Knowledge cutoff
Not collected

No model-specific public inference contract established. Unknown does not mean unsupported.

Tool calling
Not collected

No model-specific public inference contract established. Unknown does not mean unsupported.

Structured output
Not collected

No model-specific public inference contract established. Unknown does not mean unsupported.

Streaming
Not collected

No model-specific public inference contract established. Unknown does not mean unsupported.

Batch processing
Not collected

No model-specific public inference contract established. Unknown does not mean unsupported.

Fine-tuning
Not collected

No model-specific public inference contract established. Unknown does not mean unsupported.

Reasoning
SupportedSource for Reasoning (opens in a new tab)

Task-specific reasoning derivative; public effort controls and reasoning-token budgets are not established.

Context caching
Not collected

No model-specific public inference contract established. Unknown does not mean unsupported.

Base model
OpenAI o3-miniSource for Base model (opens in a new tab)

Lineage of the published evaluation, not a claim that all current Ambience coding workflows use this backbone.

Architecture
Reinforcement-fine-tuned reasoning model for ICD-10 code selection.Source for Architecture (opens in a new tab)
Output formats
ICD-10 code recommendations. No public output JSON schema or score range established.Source for Output formats (opens in a new tab)

Access & pricing

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

Ambience Healthcare clinical platform

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

No public standalone selector established.

Access
Published private model evaluation and platform announcement. Current access to this exact derivative is unverified.
Regions
Verify deployment and processing locations in the customer agreement.

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Clinical data processing is governed by customer agreements and applicable BAAs. The public policy allows de-identified uses and disclosures subject to law and contractual commitments; it does not establish universal no-training or zero-retention terms. Model-specific retention periods and processing regions were not established. The website-linked February 2023 end-user terms give the customer MSA precedence in conflicts.

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.

Ambience Healthcare clinical platform

Not verified

No reviewed inference-cache contract. Patient history, EHR synchronization and saved templates are not prompt caching.

How it works
Not collected

No reviewed inference-cache contract. Patient history, EHR synchronization and saved templates are not prompt caching.

Minimum reusable input
Not collected

No reviewed inference-cache contract. Patient history, EHR synchronization and saved templates are not prompt caching.

Lifetime & refresh
Not collected

No reviewed inference-cache contract. Patient history, EHR synchronization and saved templates are not prompt caching.

How to enable it
Not collected

No reviewed inference-cache contract. Patient history, EHR synchronization and saved templates are not prompt caching.

Usage fields
Not collected

No reviewed inference-cache contract. Patient history, EHR synchronization and saved templates are not prompt caching.

Billing rules
Not collected

No reviewed inference-cache contract. Patient history, EHR synchronization and saved templates are not prompt caching.

Limits & data boundaries
Not collected

No reviewed inference-cache contract. Patient history, EHR synchronization and saved templates 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 case study identifies an Ambience reinforcement-fine-tuned derivative of private OpenAI o3-mini. No public derivative weights or standalone selector are exposed.

Classification evidence (opens in a new tab)

Sources reviewed