Intelligence API
LiveA read-only Indian legal-data API — clause benchmarks, judgment search, statute search — metered per key.
Plan availability. The Intelligence API is built and the endpoints respond, but this is not switched on in any of our four published plans. Starter, Pro, Business and Enterprise all resolve to the same feature set and this one is off in all of them, so a subscription will not unlock it — it has to be enabled for your organisation by arrangement. Ask us before you plan around it. In particular it is not included on Business, which this page previously claimed.
- ✓Clause benchmark — dispute rate with a Wilson confidence interval and sample size, per court or aggregated
- ✓Clause outcome — outcome distribution and average duration for a clause type and court
- ✓Judgment search with cursor pagination and truncated headnotes, or full headnotes on request
- ✓Statute search over section titles and text with excerpts
What it is.
Four data endpoints behind a per-organisation API key: clause dispute-rate benchmarks with a Wilson confidence interval and sample size, outcome distributions by clause type and court, judgment search, and statute search. Plus a key-status endpoint reporting your monthly call quota and how much of it you have used.
It is a data product, not a remote control for the app. There is no endpoint that scans a document, runs a Nexus query, reads your audit log or touches billing — the page used to say there was, and there is not. Alongside the data endpoints sits webhook management: create, read, update, delete a subscription, read its delivery log, and rotate its signing secret.
Three steps.
End to end.
Minted for your organisation by an administrator. The secret is shown once.
Standard REST, bearer auth, JSON out. Judgment and statute search take a query with cursor pagination.
The key-status endpoint reports your monthly call limit, calls used and calls remaining.
What you get.
- ✓Clause benchmark — dispute rate with a Wilson confidence interval and sample size, per court or aggregated
- ✓Clause outcome — outcome distribution and average duration for a clause type and court
- ✓Judgment search with cursor pagination and truncated headnotes, or full headnotes on request
- ✓Statute search over section titles and text with excerpts
- ✓Key status — monthly call limit, used and remaining
- ✓Webhook subscription management with a delivery log and secret rotation
- ✓Monthly call quota per key, enforced race-safely, returning too-many-requests when exhausted
Quick answers.
No. There is no scan endpoint, and no search, audit or billing endpoint either. It exposes the legal-data corpus, not the application.
No. Keys carry no scope or permission field — every key can call every endpoint. If scoped keys matter to you, say so; it is not there.
It is quota-limited rather than rate-limited: a monthly call allowance by tier, not a requests-per-second ceiling.
Not served in production — the schema endpoints are disabled there. Ask us for the spec and we will send it.
No. The key-status endpoint gives quota counters; there is no per-endpoint usage breakdown.
More in Platform & Deployment.
Storage and processing default to AWS ap-south-1 (Mumbai). Model inference leaves India — that is disclosed, not hidden.
Tax invoices numbered consecutively within the financial year, with the CGST/SGST or IGST split, or zero-rated under LUT.
Right-click any PDF or Gmail attachment → "Scan with LexVio".
Air-gapped install via Helm chart. No outbound telemetry when AIR_GAPPED=true.