Oshi Health × Superscript
What an integration could look like
•
Other pricing solutions are either not instant or not accurate enough. They are limited to copays, and they fail on deductibles and coinsurance, or when the benefit application gets complex.
We specialize in patient cost shares. Not a copay estimate: the deductible, the coinsurance, and all their combinations that the industry stops short of. Medicine is emergent, so we also predict, price and explain variance in care.
With accumulators and a price for every appointment, a patient can be shown the cost of their whole journey, deductible and out-of-pocket maximum spend included, not just an estimate for the first appointment.
Over four years of pricing in the market, we have come to understand the value of clear price explanations. Often it is the opaque nature of healthcare costs that drives patients away, not the cost itself. Every price carries a plain-language explanation of the benefit behind it.
We predict what could change in the appointment itself: what the visit may be billed as, and what may be added to it. Every one is priced at the patient's own cost share before the visit.
More conversions, a better collections rate, a better patient experience.
Oshi Health's own pages, rebuilt as a mock-up by Superscript. Not built or endorsed by Oshi Health.
•Best-in-class pricing accuracy that keeps self-improving.
{
"id": "pr_8f21c4a0", "status": "completed",
"appointment": { "label": "Initial GI provider visit", "week": 1 },
"patient_responsibility": 23943,
"base": { "items": [
{ "cpt": "99204", "label": "Initial GI provider visit", "allowed": 23943,
"adjustments": [ { "type": "deductible", "amount": 23943,
"explanation": "$350 of the deductible is left, more than this visit" } ] } ] },
"x_axis": [
{ "cpt": "99205", "swaps": "99204", "relation": "severity", "likelihood": 0.09,
"reason": "An extended first visit", "patient_responsibility": 33709 },
{ "cpt": "99203", "swaps": "99204", "relation": "severity", "likelihood": 0.03,
"reason": "A shorter first visit", "patient_responsibility": 19898 } ],
"y_axis": [
{ "cpt": "G2211", "relation": "addition", "likelihood": 0.04, "billed_by": "provider",
"reason": "Complex visit add-on", "patient_responsibility": 1827 },
{ "cpt": "36415", "relation": "addition", "likelihood": 0.013, "billed_by": "external",
"reason": "Blood draw, ordered and run at a lab", "patient_responsibility": 915 } ],
"insurances": [ { "payer": "Aetna", "plan": "Choice POS II",
"accumulators": { "deductible_remaining": 35000, "oop_remaining": 180000 } } ],
"disclosure": "Exact, subject to our data inputs."
}
•One call returns the price, what the visit may bill as instead, what may be added to it, and where the patient stands for the year.
•A Four-Engine Agentic Solution to Healthcare's Most Complex Data Problem.
We spent four years in R&D building Healthcare's First Pricing Protocol.
AIM (Appointment Inference Model)
Multilabel models trained on each practice's own adjudicated claims predict the CPTs a scheduled visit will be billed as, from more than 40 features about the patient, the appointment and the practice, tuned on three years of selecting treatments in the wild.
ABE (Algorithmic Balancing Engine)
Financial, actuarial models built on adjudication outcomes to resolve payer/plan bundling logic and CPT nuance. Over 1TB of data ETL per practice.
AIR (Accessing Insurance Resources)
Interprets X12 271 eligibility responses across EB segment hierarchies and free-text MSG fields using LLMs to normalize payer coverage logic complexity.
ART (Adjudicating Real-time Transactions)
Reads every 835 remittance and maps each pricing discrepancy. 8,700+ weekly adjustments generate labeled training examples with unambiguous outcome signals, so the system self-corrects without human annotation or reward model drift.
•Superscript builds pricing infrastructure for US healthcare, from New York, since 2021.
SOC 2 Type II · HIPAA business associate · Founded in New York in 2021. hello@superscript.nyc →
+ MORE







