How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Vera Health Chat API

The Chat API from Vera Health — 6 operation(s) for chat.

Vera Health Chat API is published by Vera Health on the APIs.io network, described by a machine-readable OpenAPI specification.

This API exposes 5 JSON Schema definitions.

Tagged areas include Chat. The published artifact set on APIs.io includes an OpenAPI specification and 5 JSON Schemas.

This API exposes 6 operations across 6 paths, and defines 23 schemas. It is described by OpenAPI 3.2.0, at version 1.0.0.

Requests are made against a single base URL, https://www.verahealth.ai.

6 operations 6 paths 23 schemas 3 GET3 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://www.verahealth.ai
Authentication
API Key
Resource Areas
1

Authentication & Security 1

Vera Health Chat API declares 1 security scheme for authenticating requests. An API key is passed in the header as x-api-key (apiKeyAuth). By default, every request must be authenticated.

  • apiKeyAuth — API key for authentication. Contact support@verahealth.ai to obtain your API key.

Paths & Operations 6

Across 6 paths, the API surfaces 6 operations — 3 GET, 3 POST. Each is listed below with its method, path, parameters, and response codes.

Chat 6
POST
/api/chat/v1deprecated
Chat
chatV1 body → 200400401404429500
POST
/api/chat/v2
Send a chat message
chatV2 body → 200400401413422429500
GET
/api/chat/v2/stream/{runId}
Resume a chat stream
resume-a-chat-stream 1 param → 200400401404429500
GET
/api/chat/v2/quotas
Get your rate-limit quotas
get-your-rate-limit-quotas → 200401429500
POST
/api/chat/v3
Ask the agent with a chosen tool set
chatV3 body → 200400401403404409413422
GET
/api/chat/v3/threads/{threadId}/stream
Reconnect to an agentic stream
reconnect-to-an-agentic-stream 1 param → 200204401403404500

Schemas 23

The contract defines 23 schemas that model the data the API accepts and returns. The most detailed are AgentReference (10 properties), EvidenceLevel (9 properties), VendorMetadata (9 properties), ChatMetadata (7 properties). Each schema is shown below with its type and property counts.

AgentToolPayloadPriorAuth
object
The priorAuth tool's deliverable: the letter the model authored, in Markdown. On these turns answer is empty.
2 properties 2 required
ValidationError
object
Request-validation failure. Emitted by the shared API layer before the route runs, so it does not use the ChatError envelope and carries no metadata echo. The…
3 properties 3 required
ChatResponse
object
Returned when stream is false.
3 properties 3 required
ConversationTurn
object
2 properties 2 required
AgentChatError
object
Error envelope.
1 property 1 required
RateLimitError
object
Rate-limit error body. Emitted by the auth layer, so it carries no metadata echo (unlike the ChatError envelope).
1 property 1 required
EvidenceLevel
object
Structured Level-of-Evidence assessment for a cited paper. Populated from the offline paperloe table (Babylon refs) or the legacy references.evidencelevel JSON…
9 properties 8 required
AgentToolId
string
A tool you can switch on or off per request. Literature retrieval is always on and is not listed here: it cannot be disabled.
AgentReference
object
A source the answer drew on. Every reference is citable: sourceId is the number a cite, figure or calculator index in the answer resolves to.
10 properties 2 required
QuotasResponse
object
1 property 1 required
ChatRequest
object
Request envelope for POST /api/chat/v2.
4 properties 2 required
ChatError
object
Error envelope. metadata is the request metadata echoed back when present (null otherwise).
2 properties 2 required
AgentChatResponse
object
Non-streaming response (stream: false).
6 properties
AgentToolPayloadPatientHandout
object
The patientHandout tool's deliverable: the document the model authored, in Markdown. On these turns answer is empty.
3 properties 2 required
VendorMetadata
object
Vera-owned provider data. Structure may evolve.
9 properties
ChatMetadata
object
Your identifiers and routing fields. Returned byte-identical on every response event. Additional fields are accepted and echoed unchanged.
7 properties 5 required
AgentToolPayloadMedcalc
object
The medcalc tool's payload: which calculator ran, the inputs it resolved from the question, and the sourceId a calculator placement in the answer resolves to.
4 properties 2 required
TokenUsage
object
Token counts for answer generation (input and output). Either may be null if the provider did not report it. Covers answer generation, not auxiliary retrieval/…
2 properties
QuotaEntry
object
One rate limit configured on the calling API key.
6 properties 6 required
AgentChatRequest
object
Request envelope for POST /api/chat/v3.
6 properties 1 required
Error
object
3 properties
AgentToolOutput
object
One reported tool call. Only the tools below report a payload; retrieval, the drug lookup and the bibliographic lookups do their work on the model channel and…
2 properties 2 required
AgentSuggestedQuestions
object
Three follow-up questions derived from the question and the answer.
3 properties 3 required

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

vera-health-chat-api-openapi.yml Raw ↑
Where this information came from

This is an independent, third-party profile of Vera Health Chat 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.