Both Vaquill AI and Midpage sell US primary law as an API.
Midpage began in case law and added codified law in July 2026; Vaquill AI began in codified law and added the federal administrative layer.
Every Vaquill AI figure comes from GET /us/statutes/coverage (measuredAt 2026-09-05T07:23:17+00:00) or the deployed OpenAPI document; every claim about Midpage links to their own documentation, fetched 2026-09-05.
For OpenLaws, see Vaquill AI vs OpenLaws and the three-way comparison.
TL;DR
- Midpage sells one corpus through three interfaces: a REST API, a hosted MCP server and a PostgreSQL read replica.
- Midpage carries 16M+ opinions and 6M+ codified documents, an AI citator and on-demand PACER retrieval. Vaquill AI carries none of those.
- Midpage stores historical versions of every statute and regulation, behind a separate historical entitlement. Vaquill AI reconstructs instead.
- Agency guidance splits: Midpage carries FTC, SEC staff, CBP, DOL Wage and Hour, FDA, EEOC, HUD, OFAC, CMS and IRS private letter rulings; Vaquill AI carries banking supervision, FinCEN, CFTC, export controls, HIPAA, FCC, FERC, DOE, CPSC, NLRB memoranda, SSA and DFARS PGI.
- Vaquill AI publishes per-call prices and issues keys without a sales call. Midpage publishes no data pricing.
- Vaquill AI carries state court rules, state insurance bulletins, Puerto Rico and Statutes at Large back to 1789. Midpage lists none of those.
Data coverage
Section counts are distinct provisions. Midpage figures are from its developer and data-quality pages and its public coverage page, read 2026-09-05. That coverage page is rate-limited to automated fetchers, so its start-year detail is named here rather than linked.
| Corpus | Vaquill AI | Midpage |
|---|---|---|
| US Code | 60,170 sections (50,798 in force) | Yes |
| Code of Federal Regulations | 222,021 | Yes |
| Federal Register agency rules | 196,237 (119,521 final, 76,716 proposed), 1994 to present | Rules, proposed rules and notices; earlier start than 1994 |
| Federal agency guidance | 21,888 across 34 filterable sources | ~40 sources across 12 agency families |
| Statutes at Large and public laws | 137 of 140 volumes, 1789 to 2026 | Public laws, later start |
| Statute compilations (COMPS) | 2,680 compilations, 80,276 sections | Not listed |
| Executive orders | 3,642, 2015 to present | Earlier start than 2015 |
| Federal Rules of Procedure | 589 | Not listed |
| US Sentencing Guidelines | 302 | Not listed |
| Federal administrative adjudication | MSPB and DOJ OLC, 6,832 documents | Select tribunals including MSPB, EEOC and FLRA |
| State statutes | 1,934,232 across 52 jurisdictions | Federal plus 50 states and DC |
| State regulations | 1,464,291 across 52 jurisdictions | Yes, plus state registers |
| State constitutions | 12,762 across 51 jurisdictions | Yes |
| State court rules | 53,628 across 46 jurisdictions | Not listed |
| State agency guidance (insurance bulletins) | 13,177 across 49 jurisdictions | Not listed |
| Case law opinions | Not in the data API | 16M+, with an AI citator |
| Case citation graph | Not applicable | 111M+ links between opinions |
| Court dockets | No | PACER, on demand, fees passed through |
| Reported total | 4,881,150 sections | 6M+ codified documents, 16M+ opinions |
Neither vendor's own pages agree with themselves.
Midpage publishes 6M+ codified documents on its developer page and 4M+ on its data quality page; both agree at 16M+ opinions.
Vaquill AI's figure is on the definition GET /statutes/coverage publishes as sectionCount. Passage counts are omitted for every vendor because none of the three publishes one on a comparable definition.
Both corpora come from official sources. Midpage states that statutes and regulations are collected from GovInfo and official state repositories through 300+ scrapers, with courts visited six times a day. For states whose official code is published only through LexisNexis, LawSites reported that Midpage reconstructs the code from session laws, with Georgia, Tennessee, Mississippi and Arkansas in progress as of 2026-07-23.
Federal agency guidance
The least overlapping part of either corpus. Neither is a superset of the other.
Vaquill AI entries are the source enum in the deployed OpenAPI document; Midpage entries are from its public coverage page, read 2026-09-05.
| Guidance family | Vaquill AI | Midpage |
|---|---|---|
| IRS notices, announcements, revenue rulings and procedures | Yes | Yes |
| IRS private letter rulings and Chief Counsel Advice | No | Yes |
| US tax treaties and technical explanations | 119 documents | Yes |
| FTC advisory opinions, policy statements, HSR interpretations | No | Yes |
| DOJ and FTC Merger Guidelines, Antitrust leniency | Yes | Yes |
| DOJ Antitrust business review letters | No | Yes |
| DOJ Justice Manual | Yes | Yes |
| DOJ guidance documents and ADA guidance | No | Yes |
| SEC no-action letters, interpretive releases, staff accounting bulletins | No | Yes |
| CBP customs rulings (CROSS), directives, compliance publications | No | Yes |
| DOL Wage and Hour opinion letters and Field Operations Handbook | No | Yes |
| EEOC, FDA, HUD, OFAC, CMS guidance | No | Yes |
| USPTO MPEP and TMEP | Yes, full manuals | Yes |
| USCIS Policy Manual | Full manual, all volumes | Yes, later start |
| US Copyright Office circulars | Yes | Yes, plus the Compendium of Office Practices |
| CFPB advisory opinions and circulars | Built, not yet queryable | Yes |
| Federal Reserve SR/CA letters, OCC bulletins and interpretive letters, FDIC FILs | Yes, 4 sources | Not listed |
| FinCEN administrative rulings and guidance | Yes, 2 sources | Not listed |
| CFTC staff letters | Yes | Not listed |
| BIS and DDTC export-control opinions | Yes, 3 sources | Not listed |
| HHS OCR HIPAA guidance, FAQs and resolution agreements | Yes, 3 sources | Not listed |
| FCC declaratory rulings, FERC policy statements, DOE appliance guidance | Yes, 3 sources | Not listed |
| CPSC advisory opinions and compliance guides | Yes, 2 sources | Not listed |
| NLRB General Counsel and Advice memoranda | Yes, 2 sources | Not listed |
| SSA rulings | Yes | Not listed |
| DFARS PGI | Yes | Not listed |
Midpage's set covers tax, antitrust, securities, customs, wage and hour and immigration. The Vaquill AI set covers banking supervision, AML, derivatives, export controls, HIPAA, product safety and labor relations.
Held but not separately filterable
Six federal corpora are in the Vaquill AI index without their own filter token in the deployed OpenAPI document, checked 2026-09-05: Federal Register notices, NLRB Board decisions, SEC Commission opinions, BIA and Attorney General precedent, CFPB enforcement actions, and the Internal Revenue Manual.
Federal Register notices have no corpusType token at all; the other five are retrievable under corpusType=AGENCY_ADJUDICATION or AGENCY_GUIDANCE and lack only the per-body source filter.
Three limits apply to these corpora, set out in the OpenLaws comparison: the Federal Register notices corpus is 2.30% of published notices by design, the Internal Revenue Manual is agency procedure rather than law, and the adjudication corpora carry no verified doctrinal currency.
Statutes at Large is missing volumes 7, 8 and 44, so 137 of 140.
Neither API publishes a machine-readable overruling or supersession signal for administrative adjudication.
Versions and currency
Midpage stores versions and derives currency at request time.
Per its Laws API documentation there is no stored is_current flag: a document is current only if it is not marked historical, its effective_date is not in the future, no newer version is already in force, and it is not a repeal tombstone.
get returns a versions array carrying each version's id, effective date and publication date; an older version is fetched by id.
Two limits are stated in the same document.
Historical access requires an API key with historical entitlement; without it the widening flags and historical id lookups return 403 and versions comes back empty.
effective_date is populated only when the source states it, because several state codes publish session-year history instead.
Vaquill AI reconstructs rather than archives.
?asOf= on a section body rebuilds earlier text from the before-side of the first change observed after that date, and returns an isBounded flag when the answer rests on the start of change capture rather than on the law.
The mechanics are in the OpenLaws comparison.
Vaquill AI holds no historical annual editions of the CFR.
Endpoints and capabilities
Midpage's codified law sits behind three endpoints sharing a base URL and bearer key with its case-law endpoints: /laws/search, /laws/get and /laws/collections.
Its MCP searchLaws and analyzeLaw tools are marked preview, available now with contracts that may change.
| Capability | Vaquill AI | Midpage |
|---|---|---|
| Full-text search | POST /us/statutes/search, hybrid semantic plus keyword | POST /laws/search, with state, collection and date filters |
| Resolve a citation | GET /us/statutes/resolve across statutes, regulations, constitutions and court rules | POST /laws/get by citation, insensitive to punctuation and section-symbol style |
| Register citations | federalRegisterCitations on the section | register_citation lookup for Federal and state register cites |
| Citation aliasing | Annotated U.S.C.A. and U.S.C.S. forms | None; wording must match the canonical form |
| Search within a subtree | chapter and part filters | path_prefix on an ltree path, for example cfr.t21 |
| Browse the hierarchy | GET /us/statutes/divisions | get a container for its children, capped at 250 with no pagination |
| Full section text | GET /us/statutes/section/{id}/body | html, with external link hrefs stripped |
| Structured subsection tree | ?structured=true with pincites per node | Not documented |
| Point-in-time text | ?asOf=, reconstructed, with isBounded | Stored versions, behind a historical entitlement |
| Change timeline | GET /us/statutes/section/{id}/changes | versions array with effective, publication and as-of dates |
| Multi-state survey | GET /us/statutes/section/{id}/cross-state | state_counts, estimated per-state hit counts on a search |
| Neighboring sections | GET /us/statutes/section/{id}/related | Via the parent's children list |
| Reverse cross-references | GET /us/statutes/section/{id}/cited-by | Case-to-case graph only |
| Defined terms | GET /us/statutes/section/{id}/definitions | Not documented |
| Rulemaking metadata | frRegulationIdNumbers (RIN), frDocketIds, frEffectiveOn, frSignificant, frRelatedDocuments | Not documented |
| Statute to regulation joins | statutoryAuthority, implementingRegulations | Not documented |
| Batch metadata | POST /us/statutes/sections, up to 50 | One document per get; batching via the SQL replica |
| Law change alerts | Boards, watches, webhook delivery | Not documented |
| Coverage discovery | GET /us/statutes/coverage, free, with freshness and currency | GET /laws/collections, plus a public coverage page |
| Case law and courts | Not in the data API | /search, /opinions/get, /court/get, with citator treatments |
| Case-law search operators | Not applicable | Lexis and Westlaw style booleans including W/n proximity, plus reranking and facets |
| MCP server | Yes | Pinned v3, API key or OAuth |
| Direct SQL access | No | PostgreSQL read replica |
Midpage's analyzeLaw MCP tool requires a question and returns verified verbatim passages rather than raw text; the REST get returns the markup.
Access and price
| Vaquill AI | Midpage | |
|---|---|---|
| Onboarding | Self-serve API key | Request access; API keys require an eligible organization |
| Data pricing | Metered per call, published | "Tell us what you are building and we will scope access, volume, and pricing" |
| Entry price | $5 of credits, 500 minimum at $0.01 each | Not published for data |
| Application tiers | Not applicable | Starter $30/mo, Pro $80/mo on annual billing, Legal Engineer custom |
| Free trial | Credits only | Two-week trial on application plans |
| Bulk or replica | Not offered | SQL read replica, price on request |
Vaquill AI per-call prices are published at GET /api-credits/pricing: search $0.04, full section text $0.06, citation resolve $0.02, change timeline $0.01.
Coverage, boards and watch management are free; a watch change diff is $0.04.
No crossover can be computed against Midpage, because no data price is published.
Data model
Vaquill AI scopes by corpusType (17 tokens) plus a 2-letter state, and an optional source for corpora folding several bodies of law into one token.
Each section has a stable actId.
Midpage exposes two PostgreSQL schemas: opinions (courts, cases, docket entries, citations, content, opinion relations) and laws (collections, documents as an ltree, version relations).
Summary
- Midpage uniquely serves case law, an AI citator, a case citation graph, PACER dockets, stored historical versions, and a SQL read replica.
- Midpage uniquely serves FTC, SEC staff guidance, CBP customs rulings, DOL Wage and Hour, FDA, EEOC, HUD, OFAC, CMS, IRS private letter rulings and DOJ business review letters. Its Federal Register and executive-order ranges start earlier than the Vaquill AI ranges.
- Vaquill AI uniquely serves rulemaking metadata (RIN, docket IDs, statute-to-regulation joins), law change alerts with webhooks, state court rules, state insurance bulletins, Puerto Rico, Statutes at Large back to 1789, and banking, FinCEN, CFTC, export-control, HIPAA, FCC, FERC, DOE, CPSC, NLRB memoranda, SSA and DFARS PGI guidance.
- Vaquill AI publishes per-call prices and a free coverage endpoint, and issues keys without a sales call. Midpage publishes no data pricing.
- Both serve the US Code, CFR, state statutes, state regulations, constitutions, the Federal Register and a shared subset of federal agency guidance, and both source from official government publishers.
FAQ
Is Midpage a data API or an application?
Both. The application sells at $30/mo Starter and $80/mo Pro on annual billing, with a Legal Engineer tier priced on request. The data business sells through a REST API, an MCP server and a SQL replica, and publishes no price.
Does Midpage cover statutes and regulations?
Yes, added in July 2026 for federal plus all 50 states and DC, covering statutes, regulations, constitutions and agency guidance. The REST laws endpoints share a base URL and bearer key with the case-law endpoints. The MCP laws tools are marked preview.
Which one has point-in-time law?
Midpage. It stores historical versions for every statute and regulation, gated behind a separate historical entitlement. Vaquill AI reconstructs earlier text from observed changes and flags whether the answer is bounded by when change capture began.
Does Vaquill AI have case law or a citator?
No, and neither is in the data API roadmap. Raw US opinions are available free in bulk from CourtListener and the Harvard Caselaw Access Project.
Which is cheaper?
Not computable. Vaquill AI is $0.04 a search with a $5 minimum purchase. Midpage publishes no data pricing, so a quote is required to compare.
How fresh is each corpus?
Midpage states that every statute and regulation collection is re-scanned weekly, court websites are visited six times a day, and new opinions appear the same day they are published. Vaquill AI returns cadence and currency inside GET /us/statutes/coverage, which carries currentThrough strings and a freshness list naming paused jurisdictions and the reason. On 2026-09-05 that named six paused state statute corpora.
Does either support MCP?
Both. Midpage pins a v3 tool contract with a changelog, and supports a shared API key or per-user OAuth.
Where does Midpage's data come from?
Official court and government sources through 300+ custom scrapers, with statutes and regulations from GovInfo and official state repositories.
Get started
See the API overview and quickstart, then create a key.
Sources, all fetched 2026-09-05: Midpage home, developer data, data quality, pricing, docs introduction, Cases API, Laws API and MCP tools, plus its public coverage page at app.midpage.ai/coverage/us; LawSites, 2026-07-23; Vaquill AI figures from GET /us/statutes/coverage and the deployed OpenAPI document.
New legal AI guides, weekly.
Further Reading
OpenLaws vs Midpage vs Vaquill AI: US legal data API comparison
Read postVaquill AI vs OpenLaws: US legal data API comparison
Read postTop Legal Data APIs for Developers in 2026
Read postLexisNexis and Westlaw API Alternatives for Developers
Read postState Constitutions API: 51 Jurisdictions With Article and Section Structure
Read postState Court Rules API: 46 Jurisdictions, and an Honest Map of the Six Gaps
Read post
Co-Founder & CTO
Priyansh leads engineering and AI at Vaquill, from the matter workbench to drafting, document comparison, document matrix, and citation-verified research.