Asking legal questions and getting grounded, cited answers. This API does NOT stream: an ask answers `202` and you poll the operation, then read the answer off the message it points at. Conversation state is kept here, so you hold a chat id rather than replaying a transcript. Also covers the matter settings behind an answer, the skills you can ask through, and the standalone web-research tools.
Vaquill AI Research API is one of 26 APIs that Vaquill AI publishes on the APIs.io network, described by a machine-readable OpenAPI specification.
This API exposes 18 JSON Schema definitions.
Tagged areas include Research. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, an API reference, a getting-started guide, a changelog, and 18 JSON Schemas.
This API exposes
17 operations
across 11 paths,
and defines 31 schemas.
It is described by OpenAPI 3.2.0, at version 1.0.0.
Requests are made against 2 base URLs: https://api.vaquill.ai/workspace, /workspace.
17 operations11 paths31 schemas1 DELETE7 GET2 PATCH7 POST
Metadata
The identity and technical contract details declared by the specification.
Specification
OpenAPI 3.2.0
API Version
1.0.0
Base URL
https://api.vaquill.ai/api/v1
Authentication
HTTP Bearer
Resource Areas
1
Authentication & Security 1
Vaquill AI Research API declares
1 security scheme
for authenticating requests.
It accepts HTTP bearer tokens (vq_ws_*) (WorkspaceAuth).
By default, every request must be authenticated.
WorkspaceAuth — Workspace credential issued from the automation console at /automation. Send it as Authorization: Bearer vqws.... This is NOT a Data API key: a vqkey credentia…
Paths & Operations 17
Across 11 paths, the API surfaces 17 operations — 1 DELETE, 7 GET, 2 PATCH, 7 POST. Each is listed below with its method, path, parameters, and response codes.
Research 17
Asking legal questions and getting grounded, cited answers. This API does NOT stream: an ask answers 202 and you poll the operation, then read the answer off the message it points…
The contract defines 31 schemas that model the data the API accepts and returns. The most detailed are ResearchConfig (16 properties), AskRequest (15 properties), ResearchConfigUpdateRequest (12 properties), Message (11 properties). Each schema is shown below with its type and property counts.
Citation
object
One source behind an answer, matched to its [N] marker in the text.
9 properties2 required
Page_Chat_
object
2 properties2 required
AskRequest
object
One turn posted to a conversation. Answers 202 with an operation. There is no streaming variant and no synchronous mode: a customer's backend is not a browser,…
15 properties1 required
Page_Skill_
object
2 properties2 required
Chat
object
One conversation inside a matter.
9 properties8 required
SimilarRequest
object
Find pages similar to one you already have. The URL is handed to the search provider, which does the fetching, so this is not a request-forgery primitive again…
3 properties1 required
Pagination
object
Where the caller is, and whether there is more. total is the count of rows matching the filter, not the count returned, so a caller can size a job before runni…
4 properties4 required
ArticleRequest
object
Fetch one page's full text. Same egress note as SimilarRequest.
2 properties1 required
ArticleContent
object
One page, read in full.
7 properties1 required
ValidationProblem
object
A problem document for a schema rejection. errors lists the fields that were refused. The value you submitted is deliberately not echoed, so a validation failu…
7 properties6 required
WebSearchRequest
object
A one-off web search. Touches no client data and stores nothing.
3 properties1 required
ChatUpdateRequest
object
Rename a conversation. Absent leaves alone; an explicit null is refused.
1 property
Operation
object
One long-running operation, whatever kind of work it is. Readable for OPERATIONRETENTIONDAYS after creation, per AIP-151.
10 properties4 required
OperationStatus
string
The public five. There is no sixth, and there are no synonyms. Internal vocabularies spell terminal success completed, ready, extracted, succeeded and fresh; t…
ResearchConfig
object
The retrieval settings a matter applies to every question asked in it. Narrower than the internal RAGTierConfigResponse, and each omission is a rule rather tha…
16 properties9 required
WebResult
object
One page a web search found.
9 properties1 required
ResearchSettings
object
What a turn was asked to do, or what it recorded doing. Every field is nullable because the two instances of this model are filled from different places and ne…
8 properties
OperationResource
object
What the operation produced, or is producing. url is a path on this API rather than an absolute URL, because the service is mounted today and gets its own host…
3 properties2 required
Message
object
One turn: what was asked, or what was answered.
11 properties7 required
DeepResearchRequest
object
A long web-research pass, posted into a conversation. Answers 202. The report lands as an assistant message in the chat named in the path, which is what "somew…
3 properties1 required
SimilarDocuments
object
Pages similar to the one asked about.
3 properties1 required
Page_Message_
object
2 properties2 required
ResearchConfigUpdateRequest
object
A partial update to a matter's research settings. Carries matters:write, not research:run. These are settings ON a matter, and a credential that may read resea…
12 properties
Verification
object
Whether an answer accurately represented the sources it was built from. RAG-NATIVE, and deliberately so: it checks the answer against the passages that produce…
11 properties2 required
WebSearchResults
object
What a web search returned. Nothing is stored.
3 properties1 required
OperationError
object
Why a failed operation failed, in terms a customer can act on. code is stable and machine-readable. message is sanitized: the internal job tables store stack t…
2 properties2 required
ChatCreateRequest
object
Open a conversation. One INSERT; nothing is generated and nothing is spent. A title is required rather than derived from the first question, because the web ap…
1 property1 required
VerifiedClaim
object
One statement pulled out of an answer, and whether the sources support it.
6 properties3 required
OperationProgress
object
How far along, and in what units. The unit is not decoration. A workflow run stores only a percentage while a matrix run stores cell counts, so {done: 43, tota…
3 properties3 required
Skill
object
A named prompt a question can be asked through. Read-only on this API. Skill authoring is a product surface with an upload parser behind it, and publishing a w…
6 properties3 required
Problem
object
An RFC 9457 problem document. Branch on type, which is stable; title and detail are written for people and may be reworded. Some problems carry extra members (…
6 properties5 required
Specification
The full machine-readable OpenAPI contract behind this narrative.
Every API here is available over the API and to AI agents over MCP. APIs is not yet its own endpoint on the v1 API. Reach this content through network search and the tag graph, or the MCP server below.
Installs https://mcp.apievangelist.com/mcp in Claude, Cursor, VS Code and the rest — one button, every client.
MCP tools for apis
4 tools reach this content
search_api_evangelistSearch every content type across the network at once.
find_relatedThe shared-tag relevance graph — what else covers this.
get_tagEverything one tag labels, across all content types.
guide_topicPRO — a curated bundle for a topic: area, guidance, rules, papers, stories, services.
A second provider on the same verified email joins the account you already have.
Your account
ⓘWhere this information came from
This is an independent, third-party profile of Vaquill AI Research API, published by
API Evangelist. We do not operate, host, resell, or
support these APIs, and we are not affiliated with or endorsed by the company unless stated above.
Everything here is built from publicly available information — the company's own site,
developer portal, documentation, public repositories, and the specifications it publishes for public use.
Nothing is obtained by breaching a system, defeating an access control, or using credentials.
The Kin Score and Agent Readiness rating are independently calculated assessments of a company's
public API artifacts, scored against a published rubric. They are not certifications,
endorsements, security assessments, or audits.
Corrections, re-scores, and removal are free — no partnership or purchase required, and
you do not need to justify the request. A removed company is recorded as unrated, never scored
zero for having asked. Acknowledgement within one business day; removal within two.
info@apievangelist.com
·
Read the full data-sourcing policy → On a security or compliance team? Put security in the subject line and
you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.
