US Medicare Providers: Physician Master + Prescribing + Pharma Payments (CMS)
9.67M US healthcare providers (NPPES master) joined with Medicare utilization, Part D prescribing (28M drug rows) and Open Payments pharma-payment networks (16.1M transactions) — 1.42M enriched physician profiles built from official CMS bulk data.
- Records
- 9,671,889 records
- Refresh
- Annual refresh (CMS cycle); provider master monthly
- Formats
- CSV + JSONL + Parquet
- Coverage
- United States
- Packages
- 39
- Total volume
- 17.9 GB
Pricing
On request
Request access — approval required
Request access / Get a sampleThis dataset requires approval — request access and we reply within one business day.
What you get
- 9,671,889 provider master records (NPPES full dissemination)
- 1,416,884 physician profiles: prescribing volume × utilization × pharma payments
- 16,131,857 Open Payments general-payment transactions + 4,851,697 payment-network edges
- 28,023,893 Part D prescriber-drug rows and 9,781,674 utilization service rows
- 20,126 facility records (hospitals, nursing homes) with Compare ratings
Free sample not yet available for this dataset — request one via the contact form.
Full package inventory
Every package registered in the delivery catalog for this dataset — 39 packages, 17.9 GB total , 147,095,991 rows. Sizes, row counts and SHA-256 checksums come straight from the packaging pipeline.
| Package | Date | Rows | Size | sha256 | Access |
|---|---|---|---|---|---|
| medicare-providers-full.tar.zst | — | — | 8.9 GB | B2B only | |
| payments_general.jsonl.gz | — | 16,131,856 | 1.0 GB | Gated | |
| prescriber_drugs.jsonl.gz | — | 28,023,892 | 898.2 MB | Gated | |
| payments_general.csv.gz | — | 16,131,857 | 801.1 MB | Gated | |
| providers.jsonl.gz | — | 9,671,888 | 725.6 MB | Gated | |
| prescriber_drugs.csv.gz | — | 28,023,893 | 628.2 MB | Gated | |
| payments_general.parquet | — | — | 591.3 MB | B2B only | |
| utilization_services.jsonl.gz | — | 9,781,673 | 553.1 MB | Gated | |
| providers.csv.gz | — | 9,671,889 | 532.8 MB | Gated | |
| prescriber_drugs.parquet | — | — | 496.9 MB | B2B only | |
| providers.parquet | — | — | 434.4 MB | B2B only | |
| utilization_services.csv.gz | — | 9,781,674 | 413.7 MB | Gated | |
| utilization_services.parquet | — | — | 362.7 MB | B2B only | |
| physician_profiles.jsonl.gz | — | 1,416,883 | 229.7 MB | Gated | |
| prescriber_totals.jsonl.gz | — | 1,416,883 | 167.5 MB | Gated | |
| physician_profiles.csv.gz | — | 1,416,884 | 159.8 MB | Gated | |
| physician_profiles.parquet | — | — | 156.5 MB | B2B only | |
| utilization_totals.jsonl.gz | — | 1,296,739 | 130.4 MB | Gated | |
| prescriber_totals.csv.gz | — | 1,416,884 | 120.0 MB | Gated | |
| prescriber_totals.parquet | — | — | 118.3 MB | B2B only | |
| utilization_totals.csv.gz | — | 1,296,740 | 93.0 MB | Gated | |
| utilization_totals.parquet | — | — | 91.7 MB | B2B only | |
| payment_edges.parquet | — | — | 60.2 MB | B2B only | |
| payment_edges.jsonl.gz | — | 4,851,696 | 59.7 MB | Gated | |
| payment_edges.csv.gz | — | 4,851,697 | 52.9 MB | Gated |
How to get this data
All packages are hosted on the Hugging Face Hub: free/open packages live in a public dataset repo (direct downloads, no signup); paid or restricted editions are delivered from a private repo with token access after approval.
Hugging Face Hub — private repo Restricted
This dataset is delivered from a private Hugging Face repo — access is granted with a token after a short approval step.
Request access →Or get a free sample first.
DataForge (this site)
# Machine-readable package index (size / sha256 / rows / channels)
curl -s https://data.zalize.com/datasets/us-medicare-providers-payments-dataset/packages.json | jq '.packages[0]'
# Request a free sample (signed link sent to your email)
curl -X POST https://dl.zalize.com/api/sample \
-H 'Content-Type: application/json' \
-d '{"dataset":"us-medicare-providers-payments-dataset","email":"you@company.com"}'Protocol access (hf://, resolve links, token auth for private repos) is documented in the developer docs →
Pricing
Packages for this dataset are being prepared. Grab the free sample below and contact us for current pricing and delivery.
AI-training use requires the AI-Training tier (1.5× base); redistribution licensing is quoted individually. Annual subscriptions get 2 months free. License details →
Update frequency & delivery
- Sources: official CMS bulk files — NPPES, Medicare Physician & Other Practitioners, Part D Prescribers, Open Payments, Hospital/Nursing Home Compare.
- Completeness gated per source against official CMS stats API totals (≥99.9%).
- Physician-level public data only; no patient-level data. Delivery is approval-gated — request access.
Compliance & provenance
Collected only from publicly accessible pages and endpoints — no login-required data, no CAPTCHA solving, no forged authentication. Collection is rate-limited with an identified User-Agent, and collection logs are retained. PII is removed or pseudonymized. Every record carries its source URL and collection timestamp. Sold under a tiered commercial license.
FAQ
How is the data delivered?
Request a quote from the pricing table and we reply within one business day. Once your order is confirmed, packages are delivered via a time-limited download link from our delivery service (dl.zalize.com). Gated and B2B editions add a short approval step.
Can I use this data for AI training?
Yes — with the AI-Training license tier (1.5× the base price). See the License page for details.
What if I need a custom slice?
Custom cuts of the Medicare providers data (by geography, time window or category) are available on request — contact us for a quote within one business day.
Related datasets
Clinical Trials & Approvals
635K+ registered clinical trials with sponsors, conditions and interventions — plus a pharma-intelligence pack (1.06M rows) linking trials to FDA drug approvals.
- Records
- 1,058,262
- Refresh
- Monthly
- From
- $299
FDA Regulatory Intelligence
25.9M records of FDA regulatory activity — 25.4M MAUDE device adverse events, 328K recall timeline events, warning letters, 510(k)/PMA/De Novo clearances and drug shortages — linked into 92,022 company risk profiles with a crosswalk to clinical trials.
- Records
- 25,368,161
- Refresh
- On
- From
- Contact
Business POI & Locations
808K+ business points of interest built from government open-data registries — US city business licenses and the UK Food Hygiene Rating Scheme — with addresses, geocodes and category labels. License-clean (no ODbL contamination in the self-serve packs).
- Records
- 808,397
- Refresh
- Monthly
- From
- $299