OpenLaws, Midpage and Vaquill AI all sell US primary law as an API.
This is a factual, side-by-side comparison of coverage, versioning, search, alerts, access and price.
Every Vaquill AI figure comes from GET /us/statutes/coverage (measuredAt 2026-09-05T07:23:17+00:00) or the deployed OpenAPI document; every competitor claim links to their own documentation, fetched 2026-09-05.
Two-way detail: Vaquill AI vs OpenLaws and Vaquill AI vs Midpage.
TL;DR
- Case law, an AI citator and PACER dockets: Midpage only. OpenLaws carries 10.3M opinions in beta as an add-on.
- Stored point-in-time text: Midpage only. OpenLaws no longer advertises it; Vaquill AI reconstructs.
- Federal Register and rulemaking metadata: Vaquill AI and Midpage. OpenLaws does not carry the Federal Register.
- Flat unmetered billing and bulk export licensed for model training: OpenLaws only, at $2,500/mo and $15,000/mo.
- Self-serve keys and published per-call pricing: Vaquill AI only.
- Semantic search: Vaquill AI and Midpage. OpenLaws lists it as in user research.
- Agency guidance does not rank: Midpage leans tax, antitrust, securities and customs; Vaquill AI leans banking, AML, export controls and HIPAA; OpenLaws carries none yet.
Data coverage
Section counts are distinct provisions. Midpage start-year detail is from its public coverage page, which is rate-limited to automated fetchers and so is named rather than linked.
| Corpus | Vaquill AI | OpenLaws | Midpage |
|---|---|---|---|
| US Code | 60,170 (50,798 in force) | 100% claimed | Yes |
| Code of Federal Regulations | 222,021 | 100% claimed | Yes |
| Federal Register agency rules | 196,237, 1994 to present | Not in the API | Rules and proposed rules, earlier start |
| Federal agency guidance | 21,888 across 34 sources | Working toward it | ~40 sources, a different set |
| Statutes at Large and public laws | 137 of 140 volumes, 1789 to 2026 | Not listed | Public laws, later start |
| Federal administrative adjudication | MSPB and OLC, 6,832 documents | Not listed | MSPB, EEOC, FLRA and others |
| State statutes | 1,934,232 across 52 jurisdictions | 50 states, DC, PR | Federal plus 50 states and DC |
| State regulations | 1,464,291 across 52 jurisdictions | 99% claimed | Yes |
| State constitutions | 12,762 across 51 jurisdictions | Yes | Yes |
| State court rules | 53,628 across 46 jurisdictions | 3 live, 3 on roadmap | Not listed |
| State insurance bulletins | 13,177 across 49 jurisdictions | Not listed | Not listed |
| Case law | Not in the data API | 10.3M, beta, an add-on | 16M+, with a citator |
| Court dockets | No | No | PACER, on demand |
| Reported total | 4,881,150 sections | 4,554,349 sections | 6M+ codified, 16M+ opinions |
None of the three vendors' own pages agree with themselves.
OpenLaws publishes 4,554,349 on its home page and "approximately 4.51 million" in its docs.
Midpage publishes 6M+ codified documents on its developer page and 4M+ on its data quality page.
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.
Search, versions and alerts
| Vaquill AI | OpenLaws | Midpage | |
|---|---|---|---|
| Semantic search shipped | Yes | In user research | Yes |
| Keyword method | BM25, blended with vectors and reranked | BM25 only | Keyword, semantic, hybrid, with reranking |
| Boolean and proximity operators | any / all / phrase | or / and / phrase | Lexis and Westlaw style including W/n, on case law |
| Point-in-time text | Reconstructed, with an isBounded flag | Not currently advertised | Stored versions, behind a historical entitlement |
| Currency model | Derived status per section | current_as_of per division, from the $5,000/mo tier | Derived per request from four conditions |
| Change detection | /changes per section, plus watches | Divisions changed in the last 90 days, Enterprise | versions array with dates |
| Alerts and webhooks | Boards and watches, free to manage | Law change feed on the $5,000/mo tier | Not documented |
| MCP server | Yes | Upcoming | Pinned v3, API key or OAuth |
| Direct SQL access | No | No | PostgreSQL read replica |
Midpage derives currency at request time with no stored is_current flag, so a future-dated amendment becomes current on its own effective day with no data change.
Vaquill AI reconstructs rather than archives, and the deployed spec defines the flag it returns as:
TRUE means: we observed no change affecting your date, and that is NOT the same as there having been none.
Vaquill AI holds no historical annual editions of the CFR. OpenLaws advertised historical versions and redline diffs for federal law until its API page was redesigned, and made no such claim as of 2026-09-05.
Access and price
| Vaquill AI | OpenLaws | Midpage | |
|---|---|---|---|
| Model | Metered per call | Flat monthly, unmetered | Quote-only for data |
| Entry | $5 of credits, 500 minimum at $0.01 | $2,500/mo | $30/mo application; data on request |
| Next tier | Pay as you go | $5,000/mo Enterprise, adds the law change feed | $80/mo Pro on annual billing, then custom |
| Startup plan | Not published | $6,000 once for 12 months; under $1M raised, under $1M revenue, 10 or fewer staff | Not published |
| Bulk | Not offered | $15,000/mo, S3, AI and ML training permitted | SQL replica, on request |
| Attribution required | No | Yes on the $2,500 tier | Not published |
| Onboarding | Self-serve key | Access request plus a 25-minute session | Access request, scoped by sales |
Vaquill AI per-call prices are published at GET /api-credits/pricing: search $0.04, section text $0.06, citation resolve $0.02, change timeline $0.01. Coverage, boards and watch management are free; a change diff is $0.04.
At $0.04 a search, the OpenLaws $2,500/mo tier is cheaper above roughly 62,500 searches a month; at $0.10 for a search plus full text, roughly 25,000; on the OpenLaws startup plan, roughly 12,500. No crossover can be computed against Midpage, because no data price is published.
Published limits
Vaquill AI. No case law in the data API, no dockets, no bulk export, no stored historical editions.
No FTC, SEC staff guidance, CBP customs rulings, DOL Wage and Hour, FDA, EEOC, HUD, OFAC, CMS or IRS private letter rulings.
Six federal corpora are in the index without their own filter token. Federal Register notices carry no corpusType token and cannot be searched at all; NLRB Board decisions, SEC Commission opinions, BIA and Attorney General precedent, CFPB enforcement actions and the Internal Revenue Manual are retrievable under corpusType=AGENCY_ADJUDICATION or AGENCY_GUIDANCE but are not separately selectable.
Three further limits apply to what is live, set out in the OpenLaws comparison.
OpenLaws. No Federal Register, no federal agency guidance yet, court rules in three jurisdictions, semantic search not shipped, case law in beta and sold as an add-on. Its coverage page names Arkansas and Missouri regulations offline since June 2025, Mississippi partial, West Virginia at 98%, and Puerto Rico regulations out of scope.
Midpage. No documented alerting or webhooks, no published data price, no structured rulemaking metadata, no state court rules or insurance bulletins, and no Puerto Rico. Public laws, the USCIS Policy Manual and private letter rulings start later than the rest of its corpus, and it lists none of the banking, AML, export-control or HIPAA guidance families. Its MCP laws tools are marked preview.
Summary
- Midpage uniquely serves case law, an AI citator, a case citation graph, PACER dockets, stored historical versions and a SQL read replica, plus tax, antitrust, securities, customs and wage-and-hour guidance.
- OpenLaws uniquely serves flat unmetered billing at a published price, a startup plan, and bulk S3 exports licensed for AI and ML training.
- Vaquill AI uniquely serves rulemaking metadata and 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, AML, export-control and HIPAA guidance. It is the only one of the three that is self-serve with published per-call pricing.
- All three serve the US Code, CFR, state statutes, state regulations, constitutions and Bluebook citation resolution, and all three source from official government publishers.
FAQ
Which US legal data API is best?
They are not substitutes. Midpage carries case law, a citator, dockets and stored historical versions. OpenLaws carries flat unmetered billing and bulk export with training rights. Vaquill AI carries the federal administrative layer, law change alerts and self-serve access.
Which is cheapest?
Vaquill AI below roughly 62,500 searches a month, at $0.04 a search with a $5 minimum. OpenLaws above that, at $2,500/mo unmetered, or $6,000 for twelve months on its startup plan. Midpage publishes no data pricing.
Which ones have case law?
Midpage, with 16M+ opinions and its own citator. OpenLaws serves 10.3M opinions in beta as an add-on, through a collaboration with CourtListener and the Harvard Caselaw Access Project. Vaquill AI does not sell case law in its data API.
Which ones have the Federal Register?
Vaquill AI and Midpage. OpenLaws does not list it. Vaquill AI carries 196,237 agency rules from 1994 onward plus RIN links joining a proposed rule to its final rule and any correction.
Which one has point-in-time law?
Midpage, and only Midpage. It stores historical versions for every statute and regulation, gated behind a separate historical entitlement. OpenLaws retired the claim from its API page. Vaquill AI reconstructs from observed changes and flags a bounded answer.
Which ones are self-serve?
Vaquill AI only. OpenLaws requires an access request and a 25-minute session; Midpage scopes data access through sales.
Do any of them support MCP?
Vaquill AI and Midpage today. OpenLaws lists an MCP as upcoming. Midpage pins a v3 tool contract with a changelog and supports API key or per-user OAuth.
Can I train a model on this data?
OpenLaws permits AI and ML training at its $15,000/mo bulk tier. Vaquill AI serves US public-domain primary law from official government sources, so no upstream publisher licence attaches to the text; plan terms govern redistribution. Midpage does not publish its terms.
Should I use more than one?
The overlap between the three is the US Code, CFR and state codes. Case law, dockets, stored versions, the federal administrative layer, alerting and bulk export each sit with one vendor only.
Get started
See the API overview and quickstart, then create a key.
Sources, all fetched 2026-09-05: OpenLaws home, API, pricing, coverage, capabilities and getting started; Midpage home, developer data, data quality, pricing, Laws API, Cases API and MCP tools, plus its public coverage page at app.midpage.ai/coverage/us; Vaquill AI figures from GET /us/statutes/coverage and the deployed OpenAPI document.
New legal AI guides, weekly.
Further Reading
Vaquill AI vs Midpage: 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.