AICost Industry Solutions

Health plans and payers

3 AI automations this industry runs today, each with the process, the AICost engine chain that prices and governs it, and the evidence behind it.

Cost engine Governance engine Each step priced and controlled. Click any engine to open its calculator or playground.

Prior authorization (utilization management) automation Member services: agent assist and call wrap-up Risk adjustment chart review and payment integrity

Prior authorization (utilization management) automation

Owner: Utilization Management / Clinical Operations (UM nurses, medical directors), with IT interoperability teams

See a chain run live Build this chain for our stack

Scale: Prior authorization AI is a $100M+ market growing about 10x year over year (Menlo Ventures 2025)

How the work runs

Receive the PA request (ePA / FHIR API, portal, fax)
Extract clinicals and match them to medical policy or criteria
Auto-approve when criteria are clearly met
Route non-approvals to a nurse or medical director with an AI summary
Issue the decision with a specific denial reason within CMS timeframes; post status through the API

AICost engine chain

5 cost engines 4 governance engines

Each step priced and controlled. Click any engine to open its calculator or playground.

Where cost leaks

Long clinical attachments (hundreds of pages) summarized per request and per resubmission
Running full LLM review on requests the rules engine could auto-approve
Duplicated AI on the provider side and payer side

Where risk sits

AI-driven denials (litigation and state law); Elevance draws a line against AI denials
Missing CMS decision clocks
Bias in criteria application across populations

Rules that apply

CMS-0057-F (72-hour expedited and 7-day standard decisions from 2026; Prior Auth API by Jan 1, 2027)
CMS MA rule CMS-4201-F (algorithms cannot be the sole basis for MA medical-necessity denials)
California SB 1120 (licensed professional must decide medical necessity)
HIPAA
Colorado ADMT law (SB 26-189, effective 2027) and EU-style state UR bills

Runs on

Cohere HealthAvailityInterQual (Optum)MCGHealthEdgeFacets / QNXTSalesforce Health CloudEpic Payer Platform

Evidence

medcitynews.com ↗medicaleconomics.com ↗morganlewis.com ↗

Member services: agent assist and call wrap-up

Owner: Member Services / contact center operations, customer experience

See a chain run live Build this chain for our stack

Scale: Elevance: AI wrap-ups on about 1 million interactions per month (MedCity News, Feb 2026)

How the work runs

Member contacts by phone, chat or app
Virtual assistant answers benefits, cost-estimate and find-a-doctor questions
Agent assist pulls eligibility, claims and benefits from multiple systems
Auto-generate the post-call summary and disposition
Analyze calls for root causes and quality

AICost engine chain

5 cost engines 2 governance engines

Each step priced and controlled. Click any engine to open its calculator or playground.

Where cost leaks

Summarizing every call, including short ones that need no summary
Long multi-system context per turn
Analytics re-processing of the same transcripts

Where risk sits

Wrong benefit or cost answers leading to member harm and grievances
PHI leakage across members
Inaccurate call records used in appeals

Rules that apply

HIPAA
CMS Medicare Advantage marketing and communications rules
state AI disclosure laws

Runs on

Salesforce Health CloudGenesysNICEAmazon ConnectFacets / QNXTHealthEdge HealthRules

Evidence

medcitynews.com ↗citiustech.com ↗

Risk adjustment chart review and payment integrity

Owner: Risk Adjustment / Medicare Advantage finance and coding; Payment Integrity / SIU

See a chain run live Build this chain for our stack

How the work runs

Retrieve medical records (chart chase)
NLP/LLM identifies HCC-supported diagnoses with MEAT evidence
Coder validates adds and deletes (two-way review)
Submit to CMS (encounter data / RAPS)
Payment integrity: pre- and post-pay claim review for FWA and coding errors

AICost engine chain

3 cost engines 3 governance engines

Each step priced and controlled. Click any engine to open its calculator or playground.

Where cost leaks

Processing whole charts (often 100+ pages) for every member each year
Re-running models after each CMS-HCC model version change
OCR plus LLM double processing

Where risk sits

One-way (add-only) coding that creates RADV and FCA exposure
Unsupported HCCs without MEAT evidence
False fraud flags on providers

Rules that apply

CMS RADV audits (expanded 2025) and the RADV final rule on overpayments
False Claims Act
HIPAA

Runs on

RAAPIDOptumCotivitiShift TechnologyEdifecsInovalonFacets

Evidence

medcitynews.com ↗raapidinc.com ↗shift-technology.com ↗

Reference chains are a starting point. Your volumes, models and vendors change the numbers; the engines recompute them from live prices.

Your process is not on the list, or runs differently? These chains are a starting point. We assemble the right engines for your workflow, your models and your vendors, and you run it over MCP or in the calculators.

Business solutions → Build my chain

Vendor / Model	Field	Why it’s inferred
Anthropic — Claude Sonnet 4.6	`cachedInput`	Derived at 10% of input rate — Anthropic publishes 90% cache-hit discount on this tier.
Anthropic — Claude Sonnet 4.5	`cachedInput`	Derived at 10% of input rate; same 90% cache-hit convention as Sonnet 4.6.
Anthropic — Claude Sonnet 4.5	`batchInput`	Derived at 50% of standard input — Anthropic documents uniform 50% Batch discount.
Anthropic — Claude Sonnet 4.5	`batchOutput`	Derived at 50% of standard output — Anthropic documents uniform 50% Batch discount.
Anthropic — Claude Haiku 4.5	`cachedInput`	Derived at 10% of input rate — Anthropic 90% cache-hit discount convention.
OpenAI — GPT-5.4 Mini	`cachedInput`	Derived at 10% of input — OpenAI documents automatic 90% discount on cache hits across GPT-5.x tier.
OpenAI — GPT-5.4 Nano	`cachedInput`	Derived at 10% of input — OpenAI 90% cache-hit convention.
OpenAI — GPT-5.4 Nano	`batchInput`	Derived at 50% of input — OpenAI Batch API uniform 50% discount.
OpenAI — GPT-5.4 Nano	`batchOutput`	Derived at 50% of output — OpenAI Batch API uniform 50% discount.
OpenAI — GPT-5.4 Pro	`cachedInput`	Derived at 10% of input — OpenAI 90% cache-hit convention.
OpenAI — GPT-5.4 Pro	`batchInput`	Derived at 50% of input — OpenAI Batch API uniform 50% discount.
OpenAI — GPT-5.4 Pro	`batchOutput`	Derived at 50% of output — OpenAI Batch API uniform 50% discount.
OpenAI — GPT-5.2	`cachedInput`	Derived at 10% of input; no residency uplift.
OpenAI — GPT-5.2	`batchInput`	Derived at 50% of input.
OpenAI — GPT-5.2	`batchOutput`	Derived at 50% of output.
OpenAI — GPT-5	`cachedInput`	Derived at 10% of input.
OpenAI — GPT-5	`batchInput`	Derived at 50% of input.
OpenAI — GPT-5	`batchOutput`	Derived at 50% of output.
OpenAI — GPT-5.5 Pro	`cachedInput`	Derived at 10% of input — OpenAI does not publish a cached rate for *-pro models; using the family convention.
OpenAI — GPT-5.5 Pro	`batchInput`	Derived at 50% of input.
OpenAI — GPT-5.5 Pro	`batchOutput`	Derived at 50% of output.
OpenAI — GPT-5.2 Pro	`cachedInput`	Derived at 10% of input — pro-tier convention.
OpenAI — GPT-5.2 Pro	`batchInput`	Derived at 50% of input.
OpenAI — GPT-5.2 Pro	`batchOutput`	Derived at 50% of output.
OpenAI — GPT-5.1	`batchInput`	Derived at 50% of input.
OpenAI — GPT-5.1	`batchOutput`	Derived at 50% of output.
OpenAI — GPT-5 Pro	`batchInput`	Derived at 50% of input.
OpenAI — GPT-5 Pro	`batchOutput`	Derived at 50% of output.
OpenAI — GPT-5 Nano	`cachedInput`	Derived at 10% of input.
OpenAI — GPT-5 Nano	`batchInput`	Derived at 50% of input.
OpenAI — GPT-5 Nano	`batchOutput`	Derived at 50% of output.
Google — Gemini 3 Flash	`cachedInput`	Derived at 10% of input — Google caching discount convention ~90%.
Google — Gemini 3.1 Flash-Lite	`cachedInput`	Derived at 10% of input — Google caching convention.
Google — Gemini 3.1 Flash-Lite	`batchInput`	Derived at 50% of input — Google Batch API uniform 50% discount.
Google — Gemini 3.1 Flash-Lite	`batchOutput`	Derived at 50% of output — Google Batch API uniform 50% discount.
Google — Gemini 2.5 Pro	`cachedInput`	Derived at 10% of input.
Google — Gemini 2.5 Flash	`cachedInput`	Derived at 10% of input.
Google — Gemini 2.5 Flash-Lite	`cachedInput`	Derived at 10% of input — Google caching convention.
Google — Gemini 2.5 Flash-Lite	`batchInput`	Derived at 50% of input — Google Batch API uniform 50% discount.
Google — Gemini 2.5 Flash-Lite	`batchOutput`	Derived at 50% of output — Google Batch API uniform 50% discount.
xAI — Grok 4 (legacy)	`cachedInput`	Extrapolated at 25% of base.

Vendor / Model

Field

Why it’s inferred

Anthropic — Claude Sonnet 4.6

cachedInput

Derived at 10% of input rate — Anthropic publishes 90% cache-hit discount on this tier.

Anthropic — Claude Sonnet 4.5

cachedInput

Derived at 10% of input rate; same 90% cache-hit convention as Sonnet 4.6.

Anthropic — Claude Sonnet 4.5

batchInput

Derived at 50% of standard input — Anthropic documents uniform 50% Batch discount.

Anthropic — Claude Sonnet 4.5

batchOutput

Derived at 50% of standard output — Anthropic documents uniform 50% Batch discount.

Anthropic — Claude Haiku 4.5

cachedInput

Derived at 10% of input rate — Anthropic 90% cache-hit discount convention.

OpenAI — GPT-5.4 Mini

cachedInput

Derived at 10% of input — OpenAI documents automatic 90% discount on cache hits across GPT-5.x tier.

OpenAI — GPT-5.4 Nano

cachedInput

Derived at 10% of input — OpenAI 90% cache-hit convention.

OpenAI — GPT-5.4 Nano

batchInput

Derived at 50% of input — OpenAI Batch API uniform 50% discount.

OpenAI — GPT-5.4 Nano

batchOutput

Derived at 50% of output — OpenAI Batch API uniform 50% discount.

OpenAI — GPT-5.4 Pro

cachedInput

Derived at 10% of input — OpenAI 90% cache-hit convention.

OpenAI — GPT-5.4 Pro

batchInput

Derived at 50% of input — OpenAI Batch API uniform 50% discount.

OpenAI — GPT-5.4 Pro

batchOutput

Derived at 50% of output — OpenAI Batch API uniform 50% discount.

OpenAI — GPT-5.2

cachedInput

Derived at 10% of input; no residency uplift.

OpenAI — GPT-5.2

batchInput

Derived at 50% of input.

OpenAI — GPT-5.2

batchOutput

Derived at 50% of output.

OpenAI — GPT-5

cachedInput

Derived at 10% of input.

OpenAI — GPT-5

batchInput

Derived at 50% of input.

OpenAI — GPT-5

batchOutput

Derived at 50% of output.

OpenAI — GPT-5.5 Pro

cachedInput

Derived at 10% of input — OpenAI does not publish a cached rate for *-pro models; using the family convention.

OpenAI — GPT-5.5 Pro

batchInput

Derived at 50% of input.

OpenAI — GPT-5.5 Pro

batchOutput

Derived at 50% of output.

OpenAI — GPT-5.2 Pro

cachedInput

Derived at 10% of input — pro-tier convention.

OpenAI — GPT-5.2 Pro

batchInput

Derived at 50% of input.

OpenAI — GPT-5.2 Pro

batchOutput

Derived at 50% of output.

OpenAI — GPT-5.1

batchInput

Derived at 50% of input.

OpenAI — GPT-5.1

batchOutput

Derived at 50% of output.

OpenAI — GPT-5 Pro

batchInput

Derived at 50% of input.

OpenAI — GPT-5 Pro

batchOutput

Derived at 50% of output.

OpenAI — GPT-5 Nano

cachedInput

Derived at 10% of input.

OpenAI — GPT-5 Nano

batchInput

Derived at 50% of input.

OpenAI — GPT-5 Nano

batchOutput

Derived at 50% of output.

Google — Gemini 3 Flash

cachedInput

Derived at 10% of input — Google caching discount convention ~90%.

Google — Gemini 3.1 Flash-Lite

cachedInput

Derived at 10% of input — Google caching convention.

Google — Gemini 3.1 Flash-Lite

batchInput

Derived at 50% of input — Google Batch API uniform 50% discount.

Google — Gemini 3.1 Flash-Lite

batchOutput

Derived at 50% of output — Google Batch API uniform 50% discount.

Google — Gemini 2.5 Pro

cachedInput

Derived at 10% of input.

Google — Gemini 2.5 Flash

cachedInput

Derived at 10% of input.

Google — Gemini 2.5 Flash-Lite

cachedInput

Derived at 10% of input — Google caching convention.

Google — Gemini 2.5 Flash-Lite

batchInput

Derived at 50% of input — Google Batch API uniform 50% discount.

Google — Gemini 2.5 Flash-Lite

batchOutput

Derived at 50% of output — Google Batch API uniform 50% discount.

xAI — Grok 4 (legacy)

cachedInput

Extrapolated at 25% of base.

Health plans and payers

Prior authorization (utilization management) automation

Member services: agent assist and call wrap-up

Risk adjustment chart review and payment integrity

Methodology

Primary sources

Inferred values (marked with * in calculator tables)

Immediate steps you can take

📋 Health plans and payers

Prior authorization (utilization management) automation

Member services: agent assist and call wrap-up

Risk adjustment chart review and payment integrity

Methodology

Primary sources

Inferred values (marked with * in calculator tables)

Immediate steps you can take

Health plans and payers