Vaquill

io.github.Vaquill-AI/vaquill-mcpVersion 0.5.0

Search US and Indian statutes, regulations, constitutions, and court rules.

Status

Responds171 msNov 14, 2026, 14:44 UTCAnswered our handshake without sign-in.

Registry data may be out of date

We could not refresh it, so this page shows the last copy.

Last checked: Nov 14, 2026, 14:44 UTC
Latency: 171 ms
Remotes responding: 3 of 3
Sign-in: OAuth sign-in, API key, No sign-in
Hosting: Hosted outside the EU (detected)
Registry data as of: Nov 14, 2026, 22:14 UTC

Data from the official MCP Registry, checked by run.zero. How we check

Connect

Streamable HTTP

https://mcp.vaquill.ai/in/mcpResponds356 msNov 14, 2026, 14:44 UTC

No sign-in

Claude Code

claude mcp add --transport http vaquill-mcp https://mcp.vaquill.ai/in/mcp --header 'Authorization: Bearer <YOUR_TOKEN>'

Replace <YOUR_TOKEN> before running.

Claude Desktop and claude.ai

Settings > Connectors > Add custom connector
Name: vaquill-mcp
Remote MCP server URL: https://mcp.vaquill.ai/in/mcp
This server expects the header Authorization.

Cursor

{
  "mcpServers": {
    "vaquill-mcp": {
      "url": "https://mcp.vaquill.ai/in/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

Replace <YOUR_TOKEN> before running.

VS Code

code --add-mcp '{"name":"vaquill-mcp","type":"http","url":"https://mcp.vaquill.ai/in/mcp","headers":{"Authorization":"Bearer <YOUR_TOKEN>"}}'

Replace <YOUR_TOKEN> before running.

Streamable HTTP

https://mcp.vaquill.ai/mcpSign-in required171 msNov 14, 2026, 14:43 UTC

OAuth sign-in

Claude Code

This server asks for sign-in. Your client opens the sign-in when it connects.

claude mcp add --transport http vaquill-mcp https://mcp.vaquill.ai/mcp

Claude Desktop and claude.ai

1
2
3

Settings > Connectors > Add custom connector
Name: vaquill-mcp
Remote MCP server URL: https://mcp.vaquill.ai/mcp

Cursor

{
  "mcpServers": {
    "vaquill-mcp": {
      "url": "https://mcp.vaquill.ai/mcp"
    }
  }
}

VS Code

code --add-mcp '{"name":"vaquill-mcp","type":"http","url":"https://mcp.vaquill.ai/mcp"}'

Streamable HTTP

https://reg-mcp.vaquill.ai/mcpResponds338 msNov 14, 2026, 14:43 UTC

No sign-in

Claude Code

claude mcp add --transport http vaquill-mcp https://reg-mcp.vaquill.ai/mcp

Claude Desktop and claude.ai

1
2
3

Settings > Connectors > Add custom connector
Name: vaquill-mcp
Remote MCP server URL: https://reg-mcp.vaquill.ai/mcp

Cursor

{
  "mcpServers": {
    "vaquill-mcp": {
      "url": "https://reg-mcp.vaquill.ai/mcp"
    }
  }
}

VS Code

code --add-mcp '{"name":"vaquill-mcp","type":"http","url":"https://reg-mcp.vaquill.ai/mcp"}'

Built your own server? run.zero hosts MCP servers on European infrastructure.

Host your own MCP server on run.zero

Tools

53 tools

Tools of Vaquill
	Description		Read-only	Idempotent	Open world
`create_document`Starts translating a file you uploaded with `POST /in/translation/files`. Charged in pages, when the translation finishes. Submitting costs nothing. The job spends one translation page per physical page of the document, once, on completion, and a job that fails spends nothing. Authentication: a `vq_key_` key holding `translate:write`. A wildcard (`*`) key includes it. ## Asynchronous You get `202 Accepted`, a `documentId` and a `Location` header. Poll `GET /in/translation/documents/{id}` until `status` is `completed` (or `failed`), then download with `GET /in/translation/documents/{id}/content`. Documents take from seconds to several minutes depending on length. ## What is checked before the job is queued Everything refusable is refused before anything is queued: an unsupported language (read `GET /in/translation/languages`), an unknown `outputFormat`, `courtStyle` or `engine`, an unknown or foreign `fileId` (404) and an insufficient balance (402). The balance check uses the page count recorded at upload. For `pdf` and `docx` that is exact. For images and plain text the count is not known until the job runs, so the check only confirms you hold at least one page; if the real count is higher than your balance the job ends `failed` with `INSUFFICIENT_TRANSLATION_PAGES` and you are not charged. Reading a scanned document is included in those translation pages: this route never spends pages from the separate OCR pool. ## Formatting the output `courtStyle` renders the translation to an Indian court's mandated paper, font, margins and line spacing (Supreme Court and nine High Courts). Omit it for the compact reader-friendly layout, which is about 45% fewer pages. The font mandate applies when `targetLanguage` is English; an Indic target is always set in Noto Sans, because the mandated Latin faces carry no Devanagari, while paper size, margins and spacing still apply. Tables, figures and document structure are preserved on every job. That is the default p	Starts translating a file you uploaded with `POST /in/translation/files`. Charged in pages, when the translation finishes. Submitting costs nothing. The job spends one translation page per physical page of the document, once, on completion, and a job that fails spends nothing. Authentication: a `vq_key_` key holding `translate:write`. A wildcard (`*`) key includes it. ## Asynchronous You get `202 Accepted`, a `documentId` and a `Location` header. Poll `GET /in/translation/documents/{id}` until `status` is `completed` (or `failed`), then download with `GET /in/translation/documents/{id}/content`. Documents take from seconds to several minutes depending on length. ## What is checked before the job is queued Everything refusable is refused before anything is queued: an unsupported language (read `GET /in/translation/languages`), an unknown `outputFormat`, `courtStyle` or `engine`, an unknown or foreign `fileId` (404) and an insufficient balance (402). The balance check uses the page count recorded at upload. For `pdf` and `docx` that is exact. For images and plain text the count is not known until the job runs, so the check only confirms you hold at least one page; if the real count is higher than your balance the job ends `failed` with `INSUFFICIENT_TRANSLATION_PAGES` and you are not charged. Reading a scanned document is included in those translation pages: this route never spends pages from the separate OCR pool. ## Formatting the output `courtStyle` renders the translation to an Indian court's mandated paper, font, margins and line spacing (Supreme Court and nine High Courts). Omit it for the compact reader-friendly layout, which is about 45% fewer pages. The font mandate applies when `targetLanguage` is English; an Indic target is always set in Noto Sans, because the mandated Latin faces carry no Devanagari, while paper size, margins and spacing still apply. Tables, figures and document structure are preserved on every job. That is the default p	No	No	Not declared	No
`fetch`Fetch one Indian enactment by the `id` from a `search` result, returning `{id, title, text, url, metadata}`. Also accepts a source URL or a bare path. NOTE: the India corpus serves an enactment as publisher links rather than inline text, so `text` carries the title and `metadata` carries the PDF, HTML and plain-text URLs to read. Prefer `get_act_text` if you can call it.	Fetch one Indian enactment by the `id` from a `search` result, returning `{id, title, text, url, metadata}`. Also accepts a source URL or a bare path. NOTE: the India corpus serves an enactment as publisher links rather than inline text, so `text` carries the title and `metadata` carries the PDF, HTML and plain-text URLs to read. Prefer `get_act_text` if you can call it.	No	Yes	Not declared	No
`get_act_amendments`The amendment history recorded against one enactment: substitutions, insertions and omissions, each with the amending Act and its effective date (e.g. 'Subs. by Act 22 of 2023, s. 44 (w.e.f. 13-11-2025)'). Use to check whether a provision still reads as enacted before relying on its text. An empty list means no amendment was recorded, NOT that the Act was never amended. Cost: 5 credits.	The amendment history recorded against one enactment: substitutions, insertions and omissions, each with the amending Act and its effective date (e.g. 'Subs. by Act 22 of 2023, s. 44 (w.e.f. 13-11-2025)'). Use to check whether a provision still reads as enacted before relying on its text. An empty list means no amendment was recorded, NOT that the Act was never amended. Cost: 5 credits.	No	Yes	Not declared	No
`get_act_section`Metadata for one provision, including its citation, position in the act, structural features and references. Use when identifying or inspecting a provision without fetching its wording. Text is not included. Use get_act_section_body to read it. wordCount covers all passages, and actsReferenced normalizes whitespace before deduplication so publisher line breaks do not create duplicate acts. Cost: 2 credits.	Metadata for one provision, including its citation, position in the act, structural features and references. Use when identifying or inspecting a provision without fetching its wording. Text is not included. Use get_act_section_body to read it. wordCount covers all passages, and actsReferenced normalizes whitespace before deduplication so publisher line breaks do not create duplicate acts. Cost: 2 credits.	No	Yes	Not declared	No
`get_act_section_body`The publisher's full text for one provision, taken directly from the act document without synthesized search headers. Use when reading, quoting or citing the provision's wording rather than its metadata. Amendments are not applied to this text. Check get_section_history for recorded changes before treating the wording as current law. Cost: 3 credits.	The publisher's full text for one provision, taken directly from the act document without synthesized search headers. Use when reading, quoting or citing the provision's wording rather than its metadata. Amendments are not applied to this text. Check get_section_history for recorded changes before treating the wording as current law. Cost: 3 credits.	No	Yes	Not declared	No
`get_act_status`An act's standing in three separate fields, publisherStatus for India Code's label, servedStatus for API availability and repealClaim for the publisher's sourced repeal record. Use when assessing whether an act remains law or why it is unavailable. These are not one verdict. A repealClaim does not verify that the repealing instrument was brought into force. Cost: 1 credit.	An act's standing in three separate fields, publisherStatus for India Code's label, servedStatus for API availability and repealClaim for the publisher's sourced repeal record. Use when assessing whether an act remains law or why it is unavailable. These are not one verdict. A repealClaim does not verify that the repealing instrument was brought into force. Cost: 1 credit.	No	Yes	Not declared	No
`get_act_structure`An act's table of contents, with chapters and parts where the publisher supplies them and provisions listed beneath. Use when locating a section or planning a traversal of the act. hasHierarchy is false for most acts, where nodes is a flat section list rather than an error. Section numbers sort numerically with alphabetic suffixes attached. Cost: 2 credits.	An act's table of contents, with chapters and parts where the publisher supplies them and provisions listed beneath. Use when locating a section or planning a traversal of the act. hasHierarchy is false for most acts, where nodes is a flat section list rather than an error. Section numbers sort numerically with alphabetic suffixes attached. Cost: 2 credits.	No	Yes	Not declared	No
`get_act_text`Source links for one enactment: the plain-text, PDF and HTML renderings, plus how many sections it holds. Use when the user wants to read or cite the Act itself rather than a matched section. Cost: 3 credits.	Source links for one enactment: the plain-text, PDF and HTML renderings, plus how many sections it holds. Use when the user wants to read or cite the Act itself rather than a matched section. Cost: 3 credits.	No	Yes	Not declared	No
`get_act_versions`Every state of an act's text that the weekly corpus sync has recorded, oldest first, with the one served today marked `isCurrent`. Cost: 1 credit. Refunded when the act is unknown or the version archive cannot be read. Pass a `versionId` to `?version=` on `GET /acts/{actId}/sections/{n}` or `GET /acts/{actId}/sections/{n}/body` to read the provision as it stood in that version. `observedFrom` and `observedTo` are NOT legal effective dates. They are when the corpus sync observed the publisher's text in that state. A provision may have been in force long before we first saw it, and a change we observed on a Sunday may have commenced months earlier. An act the sync has not yet recorded a history for returns one version, `initial`, built from the passages we hold today: `observedFrom` is the earliest time any of them was ingested and `observedTo` is null. `source` says which case you are looking at.	Every state of an act's text that the weekly corpus sync has recorded, oldest first, with the one served today marked `isCurrent`. Cost: 1 credit. Refunded when the act is unknown or the version archive cannot be read. Pass a `versionId` to `?version=` on `GET /acts/{actId}/sections/{n}` or `GET /acts/{actId}/sections/{n}/body` to read the provision as it stood in that version. `observedFrom` and `observedTo` are NOT legal effective dates. They are when the corpus sync observed the publisher's text in that state. A provision may have been in force long before we first saw it, and a change we observed on a Sunday may have commenced months earlier. An act the sync has not yet recorded a history for returns one version, `initial`, built from the passages we hold today: `observedFrom` is the earliest time any of them was ingested and `observedTo` is null. `source` says which case you are looking at.	No	Yes	Not declared	No
`get_changes`The act-level change feed of the weekly corpus sync: which acts were newly loaded, had their text replaced, or had their amendment record or metadata updated, run by run, oldest first. Cost: 1 credit. Refunded when the feed cannot be read, and when no run has published one yet. Page with `cursor`: pass the `nextCursor` of one page as the `cursor` of the next, unchanged. Store the last one you processed and you will see every change exactly once. `since` (YYYY-MM-DD) starts the feed at the first run swept on or after that date. Each `changes` row carries the act's `versionId` after the change; read the prior text with `GET /acts/{actId}/versions` and `?version=`. `withdrawnCandidates` are items the publisher no longer lists. They are reported, never applied: the act is still served until a person decides. Dates are when the sync observed the publisher's text, not legal effective dates.	The act-level change feed of the weekly corpus sync: which acts were newly loaded, had their text replaced, or had their amendment record or metadata updated, run by run, oldest first. Cost: 1 credit. Refunded when the feed cannot be read, and when no run has published one yet. Page with `cursor`: pass the `nextCursor` of one page as the `cursor` of the next, unchanged. Store the last one you processed and you will see every change exactly once. `since` (YYYY-MM-DD) starts the feed at the first run swept on or after that date. Each `changes` row carries the act's `versionId` after the change; read the prior text with `GET /acts/{actId}/versions` and `?version=`. `withdrawnCandidates` are items the publisher no longer lists. They are reported, never applied: the act is still served until a person decides. Dates are when the sync observed the publisher's text, not legal effective dates.	No	Yes	Not declared	No
`get_corresponding_provisions`Map a repealed Indian criminal code to the 2023 code that replaced it, section by section: IPC to BNS and CrPC to BNSS, in force from 1 July 2024. Pass either side ('ipc' or 'bns' both work). Use whenever a source, a pleading or the user cites an old section number, so you answer under the provision actually in force rather than the repealed one. 'iea'/'bsa' return 404 until that mapping lands. Cost: 1 credit.	Map a repealed Indian criminal code to the 2023 code that replaced it, section by section: IPC to BNS and CrPC to BNSS, in force from 1 July 2024. Pass either side ('ipc' or 'bns' both work). Use whenever a source, a pleading or the user cites an old section number, so you answer under the provision actually in force rather than the repealed one. 'iea'/'bsa' return 404 until that mapping lands. Cost: 1 credit.	No	Yes	Not declared	No
`get_coverage`India corpus counts for acts and provisions, broken down by jurisdiction, regulator and status, plus coverage depth. Use when checking whether the corpus supports a question before searching or interpreting an empty result. The depth block distinguishes text coverage from much thinner parsed amendment coverage. actsClaimingAmendmentsWithoutEvents marks missing records, not an absence of amendments. Free.	India corpus counts for acts and provisions, broken down by jurisdiction, regulator and status, plus coverage depth. Use when checking whether the corpus supports a question before searching or interpreting an empty result. The depth block distinguishes text coverage from much thinner parsed amendment coverage. actsClaimingAmendmentsWithoutEvents marks missing records, not an absence of amendments. Free.	No	Yes	Not declared	No
`get_document`Returns the status of a document translation job. Free. Never charged, so poll as often as the rate limit allows. A sensible cadence is every 2 to 5 seconds. Authentication: a `vq_key_` key holding `translate:read`. ## Status \| `status` \| Meaning \| \| --- \| --- \| \| `pending` \| Queued, not started. \| \| `processing` \| Being translated. `progress` runs from 0 to 100. \| \| `completed` \| Done. Download it from `/content`. `pagesCharged` is set. \| \| `failed` \| Not translated and not charged. See `error.code`. \| `pagesCharged` is `null` until the job completes, because pages are charged once, on completion. ## Errors `error.code` is `INSUFFICIENT_TRANSLATION_PAGES` (your balance did not cover the document when it was processed) or `TRANSLATION_FAILED`. Neither charges you. ## Example ```bash curl https://api.vaquill.ai/api/v1/in/translation/documents/$DOCUMENT_ID \ -H "Authorization: Bearer $VAQUILL_API_KEY" ```	Returns the status of a document translation job. Free. Never charged, so poll as often as the rate limit allows. A sensible cadence is every 2 to 5 seconds. Authentication: a `vq_key_` key holding `translate:read`. ## Status \| `status` \| Meaning \| \| --- \| --- \| \| `pending` \| Queued, not started. \| \| `processing` \| Being translated. `progress` runs from 0 to 100. \| \| `completed` \| Done. Download it from `/content`. `pagesCharged` is set. \| \| `failed` \| Not translated and not charged. See `error.code`. \| `pagesCharged` is `null` until the job completes, because pages are charged once, on completion. ## Errors `error.code` is `INSUFFICIENT_TRANSLATION_PAGES` (your balance did not cover the document when it was processed) or `TRANSLATION_FAILED`. Neither charges you. ## Example ```bash curl https://api.vaquill.ai/api/v1/in/translation/documents/$DOCUMENT_ID \ -H "Authorization: Bearer $VAQUILL_API_KEY" ```	No	Yes	Not declared	No
`get_document_content`Downloads the translated file once the job has completed. Free. Never charged, and downloading again never charges again. Authentication: a `vq_key_` key holding `translate:read`. ## Bytes, not a link The file is streamed through this API. The response body IS the file: there is no URL to follow, nothing that expires, and nothing to forward. Send the same `Authorization` header you use for every other call. ## Which file you get By default, the format you asked for in `outputFormat`. A job submitted with `outputFormat=pdf` also produces a Word copy when one could be generated; add `?format=docx` to download it. `?format=pdf` asks for the PDF explicitly. If the format you ask for does not exist for this job the answer is 404. `Content-Type` and `Content-Disposition` (an attachment with a filename) are set from the file. `ETag` is supported (`If-None-Match` gives `304`) and so is `Range` (`206`) for plain, unencrypted files, so an interrupted download can resume. ## Not finished While `status` is not `completed` this is a 404. Poll the status route first. ## Example ```bash curl -o translated.pdf \ https://api.vaquill.ai/api/v1/in/translation/documents/$DOCUMENT_ID/content \ -H "Authorization: Bearer $VAQUILL_API_KEY" ```	Downloads the translated file once the job has completed. Free. Never charged, and downloading again never charges again. Authentication: a `vq_key_` key holding `translate:read`. ## Bytes, not a link The file is streamed through this API. The response body IS the file: there is no URL to follow, nothing that expires, and nothing to forward. Send the same `Authorization` header you use for every other call. ## Which file you get By default, the format you asked for in `outputFormat`. A job submitted with `outputFormat=pdf` also produces a Word copy when one could be generated; add `?format=docx` to download it. `?format=pdf` asks for the PDF explicitly. If the format you ask for does not exist for this job the answer is 404. `Content-Type` and `Content-Disposition` (an attachment with a filename) are set from the file. `ETag` is supported (`If-None-Match` gives `304`) and so is `Range` (`206`) for plain, unencrypted files, so an interrupted download can resume. ## Not finished While `status` is not `completed` this is a 404. Poll the status route first. ## Example ```bash curl -o translated.pdf \ https://api.vaquill.ai/api/v1/in/translation/documents/$DOCUMENT_ID/content \ -H "Authorization: Bearer $VAQUILL_API_KEY" ```	No	Yes	Not declared	No
`get_india_case_body`The judgment's full text, stitched from its stored passages. The header each passage carries is removed and the overlap between adjacent passages appears once. Cost: 3 credits. Refunded when no such judgment exists, when a backend fails, and when the text is served with `complete: false`. A malformed `caseId` is a 422 and is not charged. `complete` is checked against the number of passages the judgment should have. When any are missing the text is still returned, `complete` is false, `missingChunkIndexes` lists them, and the call costs nothing: a judgment with a gap in it is not what you ordered. Send `include=segments` to get the offset of each passage in `text`.	The judgment's full text, stitched from its stored passages. The header each passage carries is removed and the overlap between adjacent passages appears once. Cost: 3 credits. Refunded when no such judgment exists, when a backend fails, and when the text is served with `complete: false`. A malformed `caseId` is a 422 and is not charged. `complete` is checked against the number of passages the judgment should have. When any are missing the text is still returned, `complete` is false, `missingChunkIndexes` lists them, and the call costs nothing: a judgment with a gap in it is not what you ordered. Send `include=segments` to get the offset of each passage in `text`.	No	Yes	Not declared	No
`get_india_case_detail`The case-level record of one judgment: title, court, decision date, case number, reporter citations, bench, disposition, parties, and whether the full text and an archived source file are held. Cost: 1 credit. Refunded when no such judgment exists or a backend fails. A malformed `caseId` is a 422 and is not charged. `links` are relative API paths for the other routes on this judgment. `reportedYear` is the year of the reporter volume and can differ from the year of `decisionDate`. A 404 means neither source holds the judgment. When a source was down and the other did not find it, the answer is a 503, never a 404, because a miss cannot be trusted while a source is unreachable.	The case-level record of one judgment: title, court, decision date, case number, reporter citations, bench, disposition, parties, and whether the full text and an archived source file are held. Cost: 1 credit. Refunded when no such judgment exists or a backend fails. A malformed `caseId` is a 422 and is not charged. `links` are relative API paths for the other routes on this judgment. `reportedYear` is the year of the reporter volume and can differ from the year of `decisionDate`. A 404 means neither source holds the judgment. When a source was down and the other did not find it, the answer is a 503, never a 404, because a miss cannot be trusted while a source is unreachable.	No	Yes	Not declared	No
`get_india_case_file`The judgment's archived source document, usually a PDF, as an attachment. Returns the bytes, not JSON. The storage location is never revealed. Cost: 1 credit. Refunded when no such judgment exists, when none is archived (404 `case_file_unavailable`), and when the archive cannot be read right now (503). A malformed `caseId` is a 422 and is not charged. Check `hasFile` on `GET /cases/{caseId}/detail` first.	The judgment's archived source document, usually a PDF, as an attachment. Returns the bytes, not JSON. The storage location is never revealed. Cost: 1 credit. Refunded when no such judgment exists, when none is archived (404 `case_file_unavailable`), and when the archive cannot be read right now (503). A malformed `caseId` is a 422 and is not charged. Check `hasFile` on `GET /cases/{caseId}/detail` first.	No	Yes	Not declared	No
`get_india_credit_balance`The account-wide spendable credit balance shared by the India and United States APIs. Use for pre-flight checks or low-balance alerts from an India workflow. This returns the same balance as get_credit_balance, not a separate India allowance. Check bySource before assuming credits will last. Subscription credits expire at the period end. Free.	The account-wide spendable credit balance shared by the India and United States APIs. Use for pre-flight checks or low-balance alerts from an India workflow. This returns the same balance as get_credit_balance, not a separate India allowance. Check bySource before assuming credits will last. Subscription credits expire at the period end. Free.	No	Yes	Not declared	No
`get_india_similar_cases`Judgments whose text is semantically closest to this one, best first. The judgment itself is never in the list. Cost: 2 credits. Refunded when the source judgment does not exist (404) or a backend fails (503). A malformed `caseId` or an unknown court is a 422 and is not charged. Similarity is of meaning only. It is not a statement that one judgment relies on, follows or departs from another. `meta.partial` is true when one of the two judgment collections failed and the list was built from the other; a partial list is charged. Narrow with `court`, `courtType`, `decidedFrom` and `decidedTo`.	Judgments whose text is semantically closest to this one, best first. The judgment itself is never in the list. Cost: 2 credits. Refunded when the source judgment does not exist (404) or a backend fails (503). A malformed `caseId` or an unknown court is a 422 and is not charged. Similarity is of meaning only. It is not a statement that one judgment relies on, follows or departs from another. `meta.partial` is true when one of the two judgment collections failed and the list was built from the other; a partial list is charged. Narrow with `court`, `courtType`, `decidedFrom` and `decidedTo`.	No	Yes	Not declared	No
`get_india_tribunal_matter`Everything held about one matter: title, parties, bench, members, case number, decision date and its quality, document availability, the forum's own link, and the order list where the forum has one. Cost: 1 credit. Refunded when no such matter exists in that forum or a backend fails. An unknown forum code is a free 400. This route is the authority on `decisionDate`, and it can differ from the same matter's date in a list or search response. For NCLT it re-reads the forum's own table, which carries `date_of_filing` and `disposal_date` where the shared view does not, and applies the rule those columns make possible: prefer a real disposal date, and withhold a "decision date" that is merely the filing date repeated. 36.8% of NCLT matters are that case. `dateQuality` and `dateBasis` tell you which answer you are holding; a list row says `decision_date` because the view it came from cannot see the difference. It makes no claim about whether the matter is still good law and none about treatment: this is a record of what a forum published, not a citator.	Everything held about one matter: title, parties, bench, members, case number, decision date and its quality, document availability, the forum's own link, and the order list where the forum has one. Cost: 1 credit. Refunded when no such matter exists in that forum or a backend fails. An unknown forum code is a free 400. This route is the authority on `decisionDate`, and it can differ from the same matter's date in a list or search response. For NCLT it re-reads the forum's own table, which carries `date_of_filing` and `disposal_date` where the shared view does not, and applies the rule those columns make possible: prefer a real disposal date, and withhold a "decision date" that is merely the filing date repeated. 36.8% of NCLT matters are that case. `dateQuality` and `dateBasis` tell you which answer you are holding; a list row says `decision_date` because the view it came from cannot see the difference. It makes no claim about whether the matter is still good law and none about treatment: this is a record of what a forum published, not a citator.	No	Yes	Not declared	No
`get_india_tribunal_matter_file`The matter's document, as an attachment. Returns the bytes, not JSON. The storage location is never revealed and this route never redirects. Cost: 1 credit. Refunded when no such matter exists, when no document is held for it (404 `matter_file_unavailable`), and when the document cannot be read right now (503). Check `hasFile` on the matter first. "Not held" is routine for one forum and rare elsewhere: 27,407 of NCLT's 63,487 matters have no document, against 3.5% across the whole corpus. `GET /forums` gives the per-forum figure. One document per matter, in every forum, including the two that also publish an order list. A `fileSource` of `publisher` does not mean we lack a copy; it records where the scraper found the document.	The matter's document, as an attachment. Returns the bytes, not JSON. The storage location is never revealed and this route never redirects. Cost: 1 credit. Refunded when no such matter exists, when no document is held for it (404 `matter_file_unavailable`), and when the document cannot be read right now (503). Check `hasFile` on the matter first. "Not held" is routine for one forum and rare elsewhere: 27,407 of NCLT's 63,487 matters have no document, against 3.5% across the whole corpus. `GET /forums` gives the per-forum figure. One document per matter, in every forum, including the two that also publish an order list. A `fileSource` of `publisher` does not mean we lack a copy; it records where the scraper found the document.	No	Yes	Not declared	No
`get_india_tribunal_order_file`One order's own document, as an attachment. Returns the bytes, not JSON. The storage location is never revealed and this route never redirects. Cost: 1 credit. Refunded when no such matter exists, when the index names no order, when that order has no document (404 `matter_file_unavailable`), and when the document cannot be read right now (503). Why this exists. `GET /file` serves ONE document per matter. On CAT CIS a matter has about seven orders, each a separate PDF: 1,261,877 of them across 181,429 matters, every one held in our archive. DRT adds 55,945. Before this route those documents could be listed but not fetched, and `/file` returned a single order sheet with no way to ask for the others. `index` is the `index` field on an order from `GET /orders`, 0-based. Get the list first and read `hasFile` on the order you want: it is false on 886,208 of DRT's 942,153 order rows, and false on every NCLT order, whose inline history records an encrypted token this service cannot address. The twelve forums with no order list answer 404 here. The index is stable for a matter, because the order list is built by one deterministic clause (newest first) and a truncated list drops the oldest, so low indexes are the stable end. It is a position in a list, not a permanent document id: if a forum publishes a new order, indexes shift.	One order's own document, as an attachment. Returns the bytes, not JSON. The storage location is never revealed and this route never redirects. Cost: 1 credit. Refunded when no such matter exists, when the index names no order, when that order has no document (404 `matter_file_unavailable`), and when the document cannot be read right now (503). Why this exists. `GET /file` serves ONE document per matter. On CAT CIS a matter has about seven orders, each a separate PDF: 1,261,877 of them across 181,429 matters, every one held in our archive. DRT adds 55,945. Before this route those documents could be listed but not fetched, and `/file` returned a single order sheet with no way to ask for the others. `index` is the `index` field on an order from `GET /orders`, 0-based. Get the list first and read `hasFile` on the order you want: it is false on 886,208 of DRT's 942,153 order rows, and false on every NCLT order, whose inline history records an encrypted token this service cannot address. The twelve forums with no order list answer 404 here. The index is stable for a matter, because the order list is built by one deterministic clause (newest first) and a truncated list drops the oldest, so low indexes are the stable end. It is a position in a list, not a permanent document id: if a forum publishes a new order, indexes shift.	No	Yes	Not declared	No
`get_page_balance`Returns the translation and OCR pages this API key's account can spend now. Free. Never charged, so you can poll it to drive alerting or a pre-flight check without the check itself costing you anything. Like the credit balance, it is designed to still answer when the answer is "nothing": at a zero balance a metered call 402s and tells you nothing, which is the moment the number matters most. Authentication: a `vq_key_` key holding `translate:read`. ## Pages, not characters This product bills physical pages. A page of text is 2,000 characters; a page of a document is a page of that document. Nothing here is counted in tokens. ## Two pools, and which one this API spends `translation` and `ocr` are separate balances, not two views of one number. Translating a document, scanned or not, spends translation pages only. Reading a scan is included in that price: this API does not charge you OCR pages for it. Budget from the `translation` pool. The `ocr` pool exists for standalone text extraction, which is a separate operation this API surface does not currently expose. It is reported here so the figure is visible to an account that holds OCR pages, not because a translation call will draw on it. ## Your free allowance applies here too Pages are pooled per ACCOUNT, not per credential, so the monthly free allowance your account holds is spendable through the API as well. A charge draws on `free` before `paid`, which means the first pages of a month can cost nothing and leave `paid` untouched. Budget from `pagesRemaining`, which is `free` plus `paid`. Budgeting from `paid` alone understates what you can spend. ## Separate from API credits Translation pages and API credits are different currencies on different ledgers. `GET /credits/balance` reports credits for the primary-law endpoints and says nothing about pages; this endpoint reports pages and says nothing about credits. Neither pays for the other. ## Pages are pooled per organization If your key b	Returns the translation and OCR pages this API key's account can spend now. Free. Never charged, so you can poll it to drive alerting or a pre-flight check without the check itself costing you anything. Like the credit balance, it is designed to still answer when the answer is "nothing": at a zero balance a metered call 402s and tells you nothing, which is the moment the number matters most. Authentication: a `vq_key_` key holding `translate:read`. ## Pages, not characters This product bills physical pages. A page of text is 2,000 characters; a page of a document is a page of that document. Nothing here is counted in tokens. ## Two pools, and which one this API spends `translation` and `ocr` are separate balances, not two views of one number. Translating a document, scanned or not, spends translation pages only. Reading a scan is included in that price: this API does not charge you OCR pages for it. Budget from the `translation` pool. The `ocr` pool exists for standalone text extraction, which is a separate operation this API surface does not currently expose. It is reported here so the figure is visible to an account that holds OCR pages, not because a translation call will draw on it. ## Your free allowance applies here too Pages are pooled per ACCOUNT, not per credential, so the monthly free allowance your account holds is spendable through the API as well. A charge draws on `free` before `paid`, which means the first pages of a month can cost nothing and leave `paid` untouched. Budget from `pagesRemaining`, which is `free` plus `paid`. Budgeting from `paid` alone understates what you can spend. ## Separate from API credits Translation pages and API credits are different currencies on different ledgers. `GET /credits/balance` reports credits for the primary-law endpoints and says nothing about pages; this endpoint reports pages and says nothing about credits. Neither pays for the other. ## Pages are pooled per organization If your key b	No	Yes	Not declared	No
`get_pricing_in`Credit-to-price conversion and per-endpoint costs for the India legislation API, billed in US dollars. Use when estimating a workflow or comparing endpoint charges. Set region to US for United States primary-law pricing instead. Both surfaces use the same API key and account-wide credit balance. No authentication is required.	Credit-to-price conversion and per-endpoint costs for the India legislation API, billed in US dollars. Use when estimating a workflow or comparing endpoint charges. Set region to US for United States primary-law pricing instead. Both surfaces use the same API key and account-wide credit balance. No authentication is required.	No	Yes	Not declared	No
`get_regulatory_coverage`Read this before trusting an empty result anywhere else. A search returns nothing both when the publisher published nothing and when we have not reached that publisher for a fortnight, and only this route tells those apart. Cost: free. It lists the valid `publisherId` and `sourceId` values for every other `/reg` route. Monitoring began 2026-08-23, so nothing earlier exists here, and coverage is not uniform across publishers: read an empty result together with `GET /reg/sources` rather than as 'nothing was published'. Nothing returned states whether a document is in force or superseded. A null `sourceCheckedAt` means the source has not been checked yet, never that it was checked and is fine.	Read this before trusting an empty result anywhere else. A search returns nothing both when the publisher published nothing and when we have not reached that publisher for a fortnight, and only this route tells those apart. Cost: free. It lists the valid `publisherId` and `sourceId` values for every other `/reg` route. Monitoring began 2026-08-23, so nothing earlier exists here, and coverage is not uniform across publishers: read an empty result together with `GET /reg/sources` rather than as 'nothing was published'. Nothing returned states whether a document is in force or superseded. A null `sourceCheckedAt` means the source has not been checked yet, never that it was checked and is fine.	No	Yes	Not declared	No
`get_regulatory_document`The full record for one document. The body, the capture history and the diff are each opt in with `include`, because a body averages about 8,400 characters and most callers do not want it. Cost: 1 credit, whichever `include` values are asked for. Refunded when the call fails, and when the id names no document. `include=diff` compares the two most recent captures. When one side has no extracted text, `delta.bodyComparable` is false and the line counts are null: a diff of nothing is not a diff of zero changes.	The full record for one document. The body, the capture history and the diff are each opt in with `include`, because a body averages about 8,400 characters and most callers do not want it. Cost: 1 credit, whichever `include` values are asked for. Refunded when the call fails, and when the id names no document. `include=diff` compares the two most recent captures. When one side has no extracted text, `delta.bodyComparable` is false and the line counts are null: a diff of nothing is not a diff of zero changes.	No	Yes	Not declared	No
`get_regulatory_document_file`The publisher's original file as we archived it: usually a PDF, sometimes HTML or an image. Returns the bytes, not JSON, as an attachment. Cost: 1 credit. Refunded when the call fails, including when no file was ever archived. Check `fileAvailability` on the document first. `available` means this route serves the file. `not_archived` means we only ever read the listing, and this route answers 404 `content_not_archived`: do not retry it. A 502 `archive_unavailable` is a different fact: we hold the file and cannot read it right now, so retrying may help. Where we hold no copy, `publisherFileUrl` on the document is the publisher's own link.	The publisher's original file as we archived it: usually a PDF, sometimes HTML or an image. Returns the bytes, not JSON, as an attachment. Cost: 1 credit. Refunded when the call fails, including when no file was ever archived. Check `fileAvailability` on the document first. `available` means this route serves the file. `not_archived` means we only ever read the listing, and this route answers 404 `content_not_archived`: do not retry it. A 502 `archive_unavailable` is a different fact: we hold the file and cannot read it right now, so retrying may help. Where we hold no copy, `publisherFileUrl` on the document is the publisher's own link.	No	Yes	Not declared	No
`get_section_history`Recorded amendments to one provision, including the changing Act and section, effective dates and replaced wording where published. Use when tracing changes or checking whether published text reflects later amendments. An empty history can mean no changes or no parsed records, as coverage explains. Read appliedStatus on every event. Amendments are not applied to served text. Cost: 2 credits.	Recorded amendments to one provision, including the changing Act and section, effective dates and replaced wording where published. Use when tracing changes or checking whether published text reflects later amendments. An empty history can mean no changes or no parsed records, as coverage explains. Read appliedStatus on every event. Amendments are not applied to served text. Cost: 2 credits.	No	Yes	Not declared	No
`india_act_cited_by`Paged inbound citations from provisions elsewhere in the corpus that name an act. Use when finding provisions that mention the act, rather than following its outbound references. Matching uses the act's title, not its identifier, so title variants and line breaks can be missed. Read matchBasis and treat results as a floor. total counts distinct citing provisions across all pages. Cost: 2 credits.	Paged inbound citations from provisions elsewhere in the corpus that name an act. Use when finding provisions that mention the act, rather than following its outbound references. Matching uses the act's title, not its identifier, so title variants and line breaks can be missed. Read matchBasis and treat results as a floor. total counts distinct citing provisions across all pages. Cost: 2 credits.	No	Yes	Not declared	No
`india_act_definitions`Extracted defined terms and their defining provisions, plus a separate definitionSections list. Use when a question turns on an act's own meaning of a term. Extraction covers only a minority of acts, so an empty result does not mean the act defines nothing. definitionSections identifies provisions to read even without extracted terms. terms is paged, but definitionSections is not. Cost: 2 credits.	Extracted defined terms and their defining provisions, plus a separate definitionSections list. Use when a question turns on an act's own meaning of a term. Extraction covers only a minority of acts, so an empty result does not mean the act defines nothing. definitionSections identifies provisions to read even without extracted terms. terms is paged, but definitionSections is not. Cost: 2 credits.	No	Yes	Not declared	No
`india_act_subordinate`Paged rules, regulations, notifications and orders the publisher records as made under an act. Use when looking beyond the parent statute to its subordinate instruments. Matching uses the parent's title, not parent_act_id, which is an India Code identifier that does not address this corpus. Check matchBasis. total counts distinct instruments across all pages, while returned counts rows on this page. Cost: 2 credits.	Paged rules, regulations, notifications and orders the publisher records as made under an act. Use when looking beyond the parent statute to its subordinate instruments. Matching uses the parent's title, not parent_act_id, which is an India Code identifier that does not address this corpus. Check matchBasis. total counts distinct instruments across all pages, while returned counts rows on this page. Cost: 2 credits.	No	Yes	Not declared	No
`india_section_references`Outbound citations from a provision to other enactments and sections of its own act. Use when following references outwards, not finding citations to the act. actId identifies served targets, while resolved false marks coverage gaps rather than parse failures. Results are not paged. totalActs and totalSections give full counts, so check truncated before treating returned references as complete. Cost: 2 credits.	Outbound citations from a provision to other enactments and sections of its own act. Use when following references outwards, not finding citations to the act. actId identifies served targets, while resolved false marks coverage gaps rather than parse failures. Results are not paged. totalActs and totalSections give full counts, so check truncated before treating returned references as complete. Cost: 2 credits.	No	Yes	Not declared	No
`list_act_filters`Self-describing filter vocabulary: every category, state, department and status the acts corpus actually holds, with counts. Call this before filtering, so a query uses a value that exists instead of returning empty because the spelling was wrong.	Self-describing filter vocabulary: every category, state, department and status the acts corpus actually holds, with counts. Call this before filtering, so a query uses a value that exists instead of returning empty because the spelling was wrong.	No	Yes	Not declared	No
`list_acts`Browse and filter enactments rather than searching their text: by jurisdiction (central or a state), issuing regulator, year and status. Use when the user wants to know WHAT exists in an area before asking what it says, or to confirm an Act's exact title before citing it. Cost: 1 credit.	Browse and filter enactments rather than searching their text: by jurisdiction (central or a state), issuing regulator, year and status. Use when the user wants to know WHAT exists in an area before asking what it says, or to confirm an Act's exact title before citing it. Cost: 1 credit.	No	Yes	Not declared	No
`list_india_cases`Browse judgments by court and decision date, with no query. Newest first unless `order` says otherwise. Cost: 1 credit. Refunded when the call fails. A request we refuse as malformed is not charged. Only judgments whose full text is held and whose court and decision date are known are listed, and a decision date that is implausible (later than today or before 1800) never leads a page. Paging is keyset based, so a page cannot repeat or skip a judgment while the corpus is written to. There is no `total`: counting 13 million rows would time out, so `meta.hasMore` and `meta.nextCursor` are the contract.	Browse judgments by court and decision date, with no query. Newest first unless `order` says otherwise. Cost: 1 credit. Refunded when the call fails. A request we refuse as malformed is not charged. Only judgments whose full text is held and whose court and decision date are known are listed, and a decision date that is implausible (later than today or before 1800) never leads a page. Paging is keyset based, so a page cannot repeat or skip a judgment while the corpus is written to. There is no `total`: counting 13 million rows would time out, so `meta.hasMore` and `meta.nextCursor` are the contract.	No	Yes	Not declared	No
`list_india_courts`The canonical court registry: every `courtId` you can pass as `court`, with its name, type, state, the raw court strings that mean it (`aliases`), and how many judgments and which decision dates the corpus holds for it. Cost: free. Counts and dates are measured, not live: `countedAt` says when. A court with no count has not been measured yet, which is not the same as holding nothing.	The canonical court registry: every `courtId` you can pass as `court`, with its name, type, state, the raw court strings that mean it (`aliases`), and how many judgments and which decision dates the corpus holds for it. Cost: free. Counts and dates are measured, not live: `countedAt` says when. A court with no count has not been measured yet, which is not the same as holding nothing.	No	Yes	Not declared	No
`list_india_tribunal_forums`The fifteen forums whose matters we hold, each with its record count, the span of decisions, how many of its matters are judgments, and how many of its documents we actually have. Free. Call it first: it carries the `code` every other route on this surface takes. Four of the fifteen entries are not tribunals. The CCI is a regulator, the IBBI a board, RERA an authority and the GST AAR an advance-ruling body; `forumType` says which is which, and the path is `/tribunals` for all of them because splitting it would mean a caller has to know a body's constitutional character before they can look up a matter. `recordCount` is live from the publisher's own statistics table for the forums that have a row there, and our measured figure, with `countedAt` null, for the forums that do not. If that table cannot be read at all this endpoint answers `503` rather than serving the measured figures as if they were live. `files` is per forum on purpose: document coverage ranges from complete to 43% missing depending on the forum, so one corpus-wide number would mislead every caller it reached.	The fifteen forums whose matters we hold, each with its record count, the span of decisions, how many of its matters are judgments, and how many of its documents we actually have. Free. Call it first: it carries the `code` every other route on this surface takes. Four of the fifteen entries are not tribunals. The CCI is a regulator, the IBBI a board, RERA an authority and the GST AAR an advance-ruling body; `forumType` says which is which, and the path is `/tribunals` for all of them because splitting it would mean a caller has to know a body's constitutional character before they can look up a matter. `recordCount` is live from the publisher's own statistics table for the forums that have a row there, and our measured figure, with `countedAt` null, for the forums that do not. If that table cannot be read at all this endpoint answers `503` rather than serving the measured figures as if they were live. `files` is per forum on purpose: document coverage ranges from complete to 43% missing depending on the forum, so one corpus-wide number would mislead every caller it reached.	No	Yes	Not declared	No
`list_india_tribunal_matter_orders`The individual orders a forum recorded against one matter, newest first. A truncated list drops the oldest. Cost: 1 credit. Refunded when no such matter exists or a backend fails. Only three of the fifteen forums keep an order list (`hasOrderList` on `GET /forums` says which: CAT CIS, DRT and NCLT). For the other twelve this answers `200` with `status: not_applicable` and an empty list. That is an answer, not an error: the matter exists and the forum simply does not publish orders separately. `status` is the field to read before the list: - `listed`: the lookup ran. `orders` is the result, and may legitimately be empty. - `not_applicable`: this forum publishes no order list. - `unjoinable`: the key needed to find the orders is missing from this matter, so whether orders exist is unknown. 2,694 DRT matters store an empty case number and land here. It is never reported as "no orders", because that would assert something the lookup never established. There is deliberately no per-order file route: `GET /file` serves the one document held for the matter, in every forum, so that "the file" never silently means "the first of N orders" for three forums and "the document" for the other twelve.	The individual orders a forum recorded against one matter, newest first. A truncated list drops the oldest. Cost: 1 credit. Refunded when no such matter exists or a backend fails. Only three of the fifteen forums keep an order list (`hasOrderList` on `GET /forums` says which: CAT CIS, DRT and NCLT). For the other twelve this answers `200` with `status: not_applicable` and an empty list. That is an answer, not an error: the matter exists and the forum simply does not publish orders separately. `status` is the field to read before the list: - `listed`: the lookup ran. `orders` is the result, and may legitimately be empty. - `not_applicable`: this forum publishes no order list. - `unjoinable`: the key needed to find the orders is missing from this matter, so whether orders exist is unknown. 2,694 DRT matters store an empty case number and land here. It is never reported as "no orders", because that would assert something the lookup never established. There is deliberately no per-order file route: `GET /file` serves the one document held for the matter, in every forum, so that "the file" never silently means "the first of N orders" for three forums and "the document" for the other twelve.	No	Yes	Not declared	No
`list_india_tribunal_matters`Matters by forum, bench, year, decision date or exact case number, newest decision first, paged with a cursor. Cost: 1 credit per page. Refunded when a backend fails. An unknown forum, a contradictory filter or a bad cursor is refused for free, before the charge. There is deliberately no `total`: counting 813,168 rows per request to produce a number nobody pages to the end of is the defect this surface's sibling was built to avoid. Use `hasMore` and `nextCursor`, and `GET /forums` for per-forum counts. Order is `decisionDate` descending, then `caseId`, with undated matters last. Do not sort on `scrapedAt`: it is when we collected the record, not when the matter was decided, and APTEL matters decided in 2011 are all stamped 2026-03-13. `caseNumber` matches exactly. It is not a free-text target: there is no index supporting a substring match on it, so the term search covers `title`, `petitioner` and `respondent` instead.	Matters by forum, bench, year, decision date or exact case number, newest decision first, paged with a cursor. Cost: 1 credit per page. Refunded when a backend fails. An unknown forum, a contradictory filter or a bad cursor is refused for free, before the charge. There is deliberately no `total`: counting 813,168 rows per request to produce a number nobody pages to the end of is the defect this surface's sibling was built to avoid. Use `hasMore` and `nextCursor`, and `GET /forums` for per-forum counts. Order is `decisionDate` descending, then `caseId`, with undated matters last. Do not sort on `scrapedAt`: it is when we collected the record, not when the matter was decided, and APTEL matters decided in 2011 are all stamped 2026-03-13. `caseNumber` matches exactly. It is not a free-text target: there is no index supporting a substring match on it, so the term search covers `title`, `petitioner` and `respondent` instead.	No	Yes	Not declared	No
`list_languages`Returns every language this API can translate from and to. Free. Never charged, so you can call it at start-up or on a schedule to keep your own list current. It is rate limited like every other key-authenticated route. Authentication: a `vq_key_` key holding `translate:read`. ## Read this instead of hard-coding the list A code you invent is refused with a 422 before any page is charged, and the error names what is supported. Reading the list means a language we add works on your side with no change, and it means you never pay to discover a typo. Regional tags are accepted and narrowed to the language, so `hi-IN` is read as `hi`. You do not need to strip them yourself. ## Scope English plus the 22 languages of the Eighth Schedule to the Constitution of India. These are the languages Indian courts and governments work in, and each one is backed by script support in rendered output. `auto` appears in this list as a SOURCE only. There is no translating into an undetermined language, so sending it as `targetLanguage` is a 422 that says so. ## Direction is not decoration `direction` is `rtl` for Urdu, Sindhi and Kashmiri. Honour it when you render a language's own name and when you display translated output, or a correct translation is shown wrongly. ## Example ```bash curl https://api.vaquill.ai/api/v1/in/translation/languages \ -H "Authorization: Bearer $VAQUILL_API_KEY" ```	Returns every language this API can translate from and to. Free. Never charged, so you can call it at start-up or on a schedule to keep your own list current. It is rate limited like every other key-authenticated route. Authentication: a `vq_key_` key holding `translate:read`. ## Read this instead of hard-coding the list A code you invent is refused with a 422 before any page is charged, and the error names what is supported. Reading the list means a language we add works on your side with no change, and it means you never pay to discover a typo. Regional tags are accepted and narrowed to the language, so `hi-IN` is read as `hi`. You do not need to strip them yourself. ## Scope English plus the 22 languages of the Eighth Schedule to the Constitution of India. These are the languages Indian courts and governments work in, and each one is backed by script support in rendered output. `auto` appears in this list as a SOURCE only. There is no translating into an undetermined language, so sending it as `targetLanguage` is a 422 that says so. ## Direction is not decoration `direction` is `rtl` for Urdu, Sindhi and Kashmiri. Honour it when you render a language's own name and when you display translated output, or a correct translation is shown wrongly. ## Example ```bash curl https://api.vaquill.ai/api/v1/in/translation/languages \ -H "Authorization: Bearer $VAQUILL_API_KEY" ```	No	Yes	Not declared	No
`list_page_packs`Returns the page packs you can buy, and what they cost. Free. Never charged, so you can poll it to keep your own price list current. Authentication: a `vq_key_` key holding `translate:read`. ## Pages are sold in INR only Translation pages are bought in Indian rupees with GST, through Razorpay. There is no USD price for a page, which is why the translation rows in `GET /api/v1/api-credits/pricing` carry `usdCost: 0` and `unit: "page"`. That zero means "not priced in dollars", not "free". This route is where the real price lives. Pages are also a separate ledger from API credits. Credits do not buy pages and pages do not pay for primary-law calls. ## Every money field is in paise `priceInr`, `baseInr` and `gstInr` are in paise, 1/100 of a rupee, which is the unit the payment is charged in. `priceInr` is GST-inclusive and is the amount you pay. Only `pricePerPageInr` is in rupees, and it is a display figure. Read this list rather than hard-coding a price. Larger packs are cheaper per page, and both pools (`translation` and `ocr`) have their own packs. ## Example ```bash curl https://api.vaquill.ai/api/v1/in/translation/packs \ -H "Authorization: Bearer $VAQUILL_API_KEY" ```	Returns the page packs you can buy, and what they cost. Free. Never charged, so you can poll it to keep your own price list current. Authentication: a `vq_key_` key holding `translate:read`. ## Pages are sold in INR only Translation pages are bought in Indian rupees with GST, through Razorpay. There is no USD price for a page, which is why the translation rows in `GET /api/v1/api-credits/pricing` carry `usdCost: 0` and `unit: "page"`. That zero means "not priced in dollars", not "free". This route is where the real price lives. Pages are also a separate ledger from API credits. Credits do not buy pages and pages do not pay for primary-law calls. ## Every money field is in paise `priceInr`, `baseInr` and `gstInr` are in paise, 1/100 of a rupee, which is the unit the payment is charged in. `priceInr` is GST-inclusive and is the amount you pay. Only `pricePerPageInr` is in rupees, and it is a display figure. Read this list rather than hard-coding a price. Larger packs are cheaper per page, and both pools (`translation` and `ocr`) have their own packs. ## Example ```bash curl https://api.vaquill.ai/api/v1/in/translation/packs \ -H "Authorization: Bearer $VAQUILL_API_KEY" ```	No	Yes	Not declared	No
`list_regulatory_changes`An append only feed of corpus events: a document we had not seen (`new`), a new capture of one we had (`rechanged`, carrying the current text), or one the publisher removed from its listing (`retracted`). Cost: 1 credit. Refunded when the call fails. To follow this feed, call once with `since` (or with neither), then pass the previous response's `nextCursor` as `cursor` from then on. Do not resume from `observedAt`: timestamps here are not monotonic, so a timestamp resume can skip rows for good. `cursor` together with `since` is a 400. `total` is always `null` on this feed. It is walked, not sized, and null is not zero. Monitoring began 2026-08-23, so nothing earlier exists here, and coverage is not uniform across publishers: read an empty result together with `GET /reg/sources` rather than as 'nothing was published'. Nothing returned states whether a document is in force or superseded.	An append only feed of corpus events: a document we had not seen (`new`), a new capture of one we had (`rechanged`, carrying the current text), or one the publisher removed from its listing (`retracted`). Cost: 1 credit. Refunded when the call fails. To follow this feed, call once with `since` (or with neither), then pass the previous response's `nextCursor` as `cursor` from then on. Do not resume from `observedAt`: timestamps here are not monotonic, so a timestamp resume can skip rows for good. `cursor` together with `since` is a 400. `total` is always `null` on this feed. It is walked, not sized, and null is not zero. Monitoring began 2026-08-23, so nothing earlier exists here, and coverage is not uniform across publishers: read an empty result together with `GET /reg/sources` rather than as 'nothing was published'. Nothing returned states whether a document is in force or superseded.	No	Yes	Not declared	No
`list_regulatory_documents`One route for searching and listing. With `q` it runs a full text search over titles and extracted bodies and returns a marked `excerpt`. Without `q` it lists in date order. Scope filters apply with or without `q`. Cost: 1 credit. Refunded when the call fails. Fetch several known documents in one call with a repeated `id`. `total` is one of three things: a number (measured), `null` (not measured), or `0` (genuinely empty). Null is not zero. Walk with `nextCursor` until `hasMore` is false. Send a list as a repeated key (`?publisherId=4&publisherId=7`). A comma separated value is a 400 and is not charged. Monitoring began 2026-08-23, so nothing earlier exists here, and coverage is not uniform across publishers: read an empty result together with `GET /reg/sources` rather than as 'nothing was published'. Nothing returned states whether a document is in force or superseded.	One route for searching and listing. With `q` it runs a full text search over titles and extracted bodies and returns a marked `excerpt`. Without `q` it lists in date order. Scope filters apply with or without `q`. Cost: 1 credit. Refunded when the call fails. Fetch several known documents in one call with a repeated `id`. `total` is one of three things: a number (measured), `null` (not measured), or `0` (genuinely empty). Null is not zero. Walk with `nextCursor` until `hasMore` is false. Send a list as a repeated key (`?publisherId=4&publisherId=7`). A comma separated value is a 400 and is not charged. Monitoring began 2026-08-23, so nothing earlier exists here, and coverage is not uniform across publishers: read an empty result together with `GET /reg/sources` rather than as 'nothing was published'. Nothing returned states whether a document is in force or superseded.	No	Yes	Not declared	No
`resolve_india_case`Turn a case id, a Supreme Court Reports citation or a case number within a court into the judgment it names. Exact matches only. Cost: 2 credits. A malformed input and a citation form the corpus does not carry (`(2017) 10 SCC 1`, `AIR 1973 SC 1461`, `2019 SCC OnLine Del 1234`) are a 422 and are not charged. A backend failure is a 503 and is refunded. Every other outcome is charged, including `not_found`: a confident negative is the answer. Give exactly one of `citation` or `caseNumber`. `caseNumber` needs `court`. A `citation` is a case id (`2020_INSC_548`) or an SCR citation in any common spelling: `[1982] 2 S.C.R. 186`, `(1982) 2 SCR 186`, `1982 2 SCR 186`. Read `status` before `case`. `found` is exactly one judgment. `ambiguous` means several judgments match exactly and all are in `candidates`: case numbers repeat across case types, so this is common, and the route does not choose for you.	Turn a case id, a Supreme Court Reports citation or a case number within a court into the judgment it names. Exact matches only. Cost: 2 credits. A malformed input and a citation form the corpus does not carry (`(2017) 10 SCC 1`, `AIR 1973 SC 1461`, `2019 SCC OnLine Del 1234`) are a 422 and are not charged. A backend failure is a 503 and is refunded. Every other outcome is charged, including `not_found`: a confident negative is the answer. Give exactly one of `citation` or `caseNumber`. `caseNumber` needs `court`. A `citation` is a case id (`2020_INSC_548`) or an SCR citation in any common spelling: `[1982] 2 S.C.R. 186`, `(1982) 2 SCR 186`, `1982 2 SCR 186`. Read `status` before `case`. `found` is exactly one judgment. `ambiguous` means several judgments match exactly and all are in `candidates`: case numbers repeat across case types, so this is common, and the route does not choose for you.	No	Yes	Not declared	No
`resolve_india_cases_batch`The same resolver over a list, for when you would otherwise loop. Cost: 2 credits per DISTINCT input. Batching buys a round trip, never a discount. Repeats are folded into one and charged once. An input we refuse (`unsupported_citation_form`, `unknown_court`, `invalid_input`) is answered in its own slot and is not charged. An input that fails on our side is `unavailable` and is refunded on its own; it never voids the others. Up to 100 distinct inputs, and up to 500 before repeats are removed. Each is `{"citation": ...}` or `{"caseNumber": ..., "court": ...}`. Unknown fields on the body are refused rather than ignored.	The same resolver over a list, for when you would otherwise loop. Cost: 2 credits per DISTINCT input. Batching buys a round trip, never a discount. Repeats are folded into one and charged once. An input we refuse (`unsupported_citation_form`, `unknown_court`, `invalid_input`) is answered in its own slot and is not charged. An input that fails on our side is `unavailable` and is refunded on its own; it never voids the others. Up to 100 distinct inputs, and up to 500 before repeats are removed. Each is `{"citation": ...}` or `{"caseNumber": ..., "court": ...}`. Unknown fields on the body are refused rather than ignored.	No	No	Not declared	No
`resolve_india_citation`The provision named by an Indian legal citation, accepting common abbreviations and flexible element order. Use when a user provides a citation rather than a research topic, such as s.302 IPC, O. 39 R. 1 CPC or Art. 21 of the Constitution. Subsection and clause references are supported. Malformed citations are rejected rather than reported as not found. Cost: 2 credits.	The provision named by an Indian legal citation, accepting common abbreviations and flexible element order. Use when a user provides a citation rather than a research topic, such as s.302 IPC, O. 39 R. 1 CPC or Art. 21 of the Constitution. Subsection and clause references are supported. Malformed citations are rejected rather than reported as not found. Cost: 2 credits.	No	Yes	Not declared	No
`resolve_india_citations_batch`Provision resolutions for a list of Indian legal citations, using the same resolver as resolve_india_citation. Use when several citations need resolving without individual calls. Accepts up to 50 distinct citations and 500 entries before deduplication. One citation failing does not invalidate the others. Unknown request fields are rejected rather than ignored. Cost: 2 credits.	Provision resolutions for a list of Indian legal citations, using the same resolver as resolve_india_citation. Use when several citations need resolving without individual calls. Accepts up to 50 distinct citations and 500 entries before deduplication. One citation failing does not invalidate the others. Unknown request fields are rejected rather than ignored. Cost: 2 credits.	No	Yes	Not declared	No
`search`Generic corpus search over Indian Central and State legislation, returning `{id, title, url}` records for citation. Present so this server works in clients that require the standard search/fetch pair. Prefer `search_acts` if you can call it: it filters by category, state, year and status. Pair with `fetch` to read a result.	Generic corpus search over Indian Central and State legislation, returning `{id, title, url}` records for citation. Present so this server works in clients that require the standard search/fetch pair. Prefer `search_acts` if you can call it: it filters by category, state, year and status. Pair with `fetch` to read a result.	No	Yes	Not declared	No
`search_acts`Search Indian legislation down to the individual section: Central and State Acts plus the instruments of the principal regulators (SEBI, RBI, MCA, IRDAI, TRAI, DGFT). Use for any 'what does Indian law say' question. Supports boolean and phrase queries; filters by category, state, year and status. Returns sections with title, chapter and a sourceUrl pointing at the publisher's own document. The returned actId (e.g. 'IND_central_2065') feeds every acts tool. Cost: 2 credits.	Search Indian legislation down to the individual section: Central and State Acts plus the instruments of the principal regulators (SEBI, RBI, MCA, IRDAI, TRAI, DGFT). Use for any 'what does Indian law say' question. Supports boolean and phrase queries; filters by category, state, year and status. Returns sections with title, chapter and a sourceUrl pointing at the publisher's own document. The returned actId (e.g. 'IND_central_2065') feeds every acts tool. Cost: 2 credits.	No	Yes	Not declared	No
`search_india_cases`Search Supreme Court and High Court judgments by meaning and by words. Cost: 2 credits. Refunded when the call fails. A request we refuse as malformed (an unknown court, an inverted date range, a bad cursor) is not charged. Each result is a judgment, not a passage: the passage that matched best is the `snippet`. The query is embedded and matched as given: there is no query rewriting and no mapping between old and new statute names. Paging is honest about its depth. One query pages through at most 200 results (`meta.searchDepthLimit`); a cursor beyond that is a 400 `search_depth_exceeded` that asks you to narrow the query. There is no `total`: `meta.hasMore` and `meta.nextCursor` are the whole contract. A cursor belongs to the query and filters that produced it. `meta.partial` is true when one of the two judgment collections failed and the page was built from the other. A partial page is charged and may be missing judgments.	Search Supreme Court and High Court judgments by meaning and by words. Cost: 2 credits. Refunded when the call fails. A request we refuse as malformed (an unknown court, an inverted date range, a bad cursor) is not charged. Each result is a judgment, not a passage: the passage that matched best is the `snippet`. The query is embedded and matched as given: there is no query rewriting and no mapping between old and new statute names. Paging is honest about its depth. One query pages through at most 200 results (`meta.searchDepthLimit`); a cursor beyond that is a 400 `search_depth_exceeded` that asks you to narrow the query. There is no `total`: `meta.hasMore` and `meta.nextCursor` are the whole contract. A cursor belongs to the query and filters that produced it. `meta.partial` is true when one of the two judgment collections failed and the page was built from the other. A partial page is charged and may be missing judgments.	No	Yes	Not declared	No
`search_india_tribunal_matters`Find matters whose title, petitioner or respondent contains your term, narrowed by the same filters as the browse route, paged with a cursor. Cost: 2 credits per page. Refunded when a backend fails. A malformed query is refused for free, before the charge. 🔴 This searches metadata, not judgment text. No extracted text exists anywhere in this corpus: there is no `full_text`, `body`, `content`, `ocr` or `markdown` column on any relation behind this API. A matter that does not match your term may still discuss it at length in a document we hold and serve through `GET /file`. Every response states this in `searchScope` and names the exact fields matched in `searchedFields`, so a client can branch on it rather than inferring it from this paragraph. `searchedFields` is three fields, not the four the public tribunals site searches: `caseNumber` is excluded because no index supports a substring match on it (measured: 5.4-6.0s against 1.5-1.7s). Filter on it exactly with `GET /matters?caseNumber=` instead.	Find matters whose title, petitioner or respondent contains your term, narrowed by the same filters as the browse route, paged with a cursor. Cost: 2 credits per page. Refunded when a backend fails. A malformed query is refused for free, before the charge. 🔴 This searches metadata, not judgment text. No extracted text exists anywhere in this corpus: there is no `full_text`, `body`, `content`, `ocr` or `markdown` column on any relation behind this API. A matter that does not match your term may still discuss it at length in a document we hold and serve through `GET /file`. Every response states this in `searchScope` and names the exact fields matched in `searchedFields`, so a client can branch on it rather than inferring it from this paragraph. `searchedFields` is three fields, not the four the public tribunals site searches: `caseNumber` is excluded because no index supports a substring match on it (measured: 5.4-6.0s against 1.5-1.7s). Filter on it exactly with `GET /matters?caseNumber=` instead.	No	Yes	Not declared	No
`translate_text`Translates a piece of text and returns it in the same response. Charged in pages. See the cost rules below. A failed translation is refunded in full. Authentication: a `vq_key_` key holding `translate:write`. A wildcard (``) key includes it. ## Pages, not characters This product bills pages. A page of text is 2,000 characters, and the cost is `ceil(characters / 2000)`. \| Characters \| Pages \| \| --- \| --- \| \| 1 to 2,000 \| 1 \| \| 2,001 to 4,000 \| 2 \| \| 50,000 \| 25 \| Any non-empty text costs at least 1 page.* Unlike the dashboard, there is no free floor on SIZE here: a 10-character request spends a page. Empty or whitespace-only text is a 422 and costs nothing. That is about size, not about your allowance. Your account's monthly free pages are spendable through the API, and a charge draws on them first, so a short request can still cost you nothing out of pocket. ## When you are charged and when you are not Everything that can be checked up front is checked BEFORE the charge, and a refusal costs nothing: an unsupported language (read `GET /in/translation/languages` instead of hard-coding it), text over 50,000 characters (a 422, never a truncation) and empty text. If your balance cannot cover the pages you get a 402 and nothing is translated. Once charged, if the translation fails or comes back empty the pages are refunded and you get an error. You are never billed for a translation you did not receive. ## Retries Send an `Idempotency-Key` header. A retry of the same request with the same key returns the original response and does not charge again. ## Limits Text is at most 50,000 characters, because this route holds the connection open while the translation runs. Anything longer belongs on the document routes. ## Example ```bash curl -X POST https://api.vaquill.ai/api/v1/in/translation/translations \ -H "Authorization: Bearer $VAQUILL_API_KEY" \ -H "Idempotency-Key: $(uuidgen)" \ -H "Content-Type: application/json" \ -d '{"text": "The	Translates a piece of text and returns it in the same response. Charged in pages. See the cost rules below. A failed translation is refunded in full. Authentication: a `vq_key_` key holding `translate:write`. A wildcard (``) key includes it. ## Pages, not characters This product bills pages. A page of text is 2,000 characters, and the cost is `ceil(characters / 2000)`. \| Characters \| Pages \| \| --- \| --- \| \| 1 to 2,000 \| 1 \| \| 2,001 to 4,000 \| 2 \| \| 50,000 \| 25 \| Any non-empty text costs at least 1 page.* Unlike the dashboard, there is no free floor on SIZE here: a 10-character request spends a page. Empty or whitespace-only text is a 422 and costs nothing. That is about size, not about your allowance. Your account's monthly free pages are spendable through the API, and a charge draws on them first, so a short request can still cost you nothing out of pocket. ## When you are charged and when you are not Everything that can be checked up front is checked BEFORE the charge, and a refusal costs nothing: an unsupported language (read `GET /in/translation/languages` instead of hard-coding it), text over 50,000 characters (a 422, never a truncation) and empty text. If your balance cannot cover the pages you get a 402 and nothing is translated. Once charged, if the translation fails or comes back empty the pages are refunded and you get an error. You are never billed for a translation you did not receive. ## Retries Send an `Idempotency-Key` header. A retry of the same request with the same key returns the original response and does not charge again. ## Limits Text is at most 50,000 characters, because this route holds the connection open while the translation runs. Anything longer belongs on the document routes. ## Example ```bash curl -X POST https://api.vaquill.ai/api/v1/in/translation/translations \ -H "Authorization: Bearer $VAQUILL_API_KEY" \ -H "Idempotency-Key: $(uuidgen)" \ -H "Content-Type: application/json" \ -d '{"text": "The	No	No	Not declared	No
`upload_file`Uploads a source file and returns a `fileId` to translate it with. Free. Never charged: pages are spent when a translation finishes, not on upload or retrieval, so a file you never translate costs nothing. Authentication: a `vq_key_` key holding `translate:write`. A wildcard (`*`) key includes it. ## Why this route exists `POST /in/translation/documents` does not accept a URL. It accepts the `fileId` returned here, which refers to a file this API stored for your account. That is deliberate: the API never fetches an address you name, so it cannot be pointed at an internal service or at someone else's document. A `fileId` from another account is a 404. ## Limits - Types: `pdf`, `docx`, `txt`, `jpg`, `jpeg`, `png`, `tif`, `tiff`, `webp`, `bmp`. - Size: at most 150 MB, and not empty. - A `fileId` is valid for 24 hours. You can translate one file into several languages by posting `/documents` more than once with the same `fileId`. ## `pageCount` Physical pages for `pdf` and `docx`, which is what you will be charged. For images and plain text it is `null`: their page count is only known when the job runs, and `POST /documents` can then only check you hold at least one page. ## Example ```bash curl -X POST https://api.vaquill.ai/api/v1/in/translation/files \ -H "Authorization: Bearer $VAQUILL_API_KEY" \ -F "file=@petition.pdf" ``` ```json { "fileId": "3f2c9a52-8d2e-4a43-9e0b-5b6a1c7d9f10", "filename": "petition.pdf", "sizeBytes": 482113, "pageCount": 12, "expiresAt": "2026-11-02T12:34:56Z" } ```	Uploads a source file and returns a `fileId` to translate it with. Free. Never charged: pages are spent when a translation finishes, not on upload or retrieval, so a file you never translate costs nothing. Authentication: a `vq_key_` key holding `translate:write`. A wildcard (`*`) key includes it. ## Why this route exists `POST /in/translation/documents` does not accept a URL. It accepts the `fileId` returned here, which refers to a file this API stored for your account. That is deliberate: the API never fetches an address you name, so it cannot be pointed at an internal service or at someone else's document. A `fileId` from another account is a 404. ## Limits - Types: `pdf`, `docx`, `txt`, `jpg`, `jpeg`, `png`, `tif`, `tiff`, `webp`, `bmp`. - Size: at most 150 MB, and not empty. - A `fileId` is valid for 24 hours. You can translate one file into several languages by posting `/documents` more than once with the same `fileId`. ## `pageCount` Physical pages for `pdf` and `docx`, which is what you will be charged. For images and plain text it is `null`: their page count is only known when the job runs, and `POST /documents` can then only check you hold at least one page. ## Example ```bash curl -X POST https://api.vaquill.ai/api/v1/in/translation/files \ -H "Authorization: Bearer $VAQUILL_API_KEY" \ -F "file=@petition.pdf" ``` ```json { "fileId": "3f2c9a52-8d2e-4a43-9e0b-5b6a1c7d9f10", "filename": "petition.pdf", "sizeBytes": 482113, "pageCount": 12, "expiresAt": "2026-11-02T12:34:56Z" } ```	No	No	Not declared	No

Details

Registry status: Active
Published: Nov 13, 2026
Updated: Nov 13, 2026
Website: Not given
Repository: https://github.com/Vaquill-AI/vaquill-mcp⁠ (opens in a new tab)
Categories (suggested): Knowledge and notes Documents Files and storageSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
GDPR: Not declared

Are you the operator? Claim this listing