List a thread's support answers
Lists the runs of one thread that your team started, with Ana's answers, oldest first. Replies from the Zernio team after a support ticket arrive by email and are not included. Runs are kept for 90 days. Page through a long thread with limit and cursor: pass nextCursor as cursor until it is null.
Authorization
bearerAuth API key authentication: send your Zernio API key in the Authorization header, prefixed with Bearer.
In: header
Query Parameters
The thread to list, as returned by POST /v1/support/runs.
Runs per page.
1 <= value <= 5020Pass nextCursor from the previous page.
Response Body
application/json
application/json
application/json
application/json
application/json
application/json
import Zernio from '@zernio/node';const zernio = new Zernio({ apiKey: process.env.ZERNIO_API_KEY });const { data } = await zernio.supportassistant.listSupportAnswers({ query: { threadId: 'thread_abc123', },});console.log(data);{ "runs": [ { "runId": "string", "threadId": "string", "status": "queued", "stopReason": "answered", "answer": "string", "usage": { "inputTokens": 0, "outputTokens": 0, "cacheReadTokens": 0, "cacheWriteTokens": 0 }, "costUsd": 0, "maxCostUsd": 0, "createdAt": "2019-08-24T14:15:22Z", "startedAt": "2019-08-24T14:15:22Z", "finishedAt": "2019-08-24T14:15:22Z", "supportTicket": { "openedAt": "2019-08-24T14:15:22Z" }, "pollAfterSeconds": 0 } ], "nextCursor": "string"}Submit feedback
Report a bug, a missing feature or a documentation gap. Every submission is read by the Zernio team. Designed for AI agents: when a call fails in a way that looks like our bug, or the API lacks something you need, send one structured report here. Include `endpoint` and `requestId` (the `x-request-id` response header of the failing call) when you have them; they let us find the exact request. Submitting the same `summary` again within 24 hours is idempotent: it returns the original `id` with `duplicate: true` and a `200`. Each API user can file at most 20 submissions per 24 hours.
Ask a support question
Asks Ana, the Zernio support agent, a question about your workspace. Each question starts a run that answers asynchronously: this returns 202 with a `runId`, and the answer arrives through the `support.run.completed` and `support.run.failed` webhooks. `GET /v1/support/runs/{runId}` is the fallback. Pass `threadId` to continue an earlier conversation, and `context` to point Ana at a post, account or profile. When Ana finds a problem on Zernio's side she opens a support ticket with the team (see `supportTicket` on the run) and the run ends as `needs_human`. **Pricing.** You pay per question, once it finishes. The exact amount charged is the run's `costUsd`. | Question | You pay | | --- | --- | | Typical question | $0.10 to $0.50 | | Most one question can cost | Its `maxCostUsd`: $0.50 to $3, $3 by default | | Handed to the Zernio team (`needs_human`) | Charged like an answered question | | Failed or expired | $0 | | All questions in a UTC month | At most $100 per account | Near its `maxCostUsd` a run stops investigating and answers with what it found so far, so it never charges more than the cap; with nothing to answer yet it fails and costs nothing. Charges appear as "Support API" on your invoice. Requires an unrestricted API key, usage-based billing and a card on file. Limits per account: 3 active runs and $100 of runs per UTC month. Send an Idempotency-Key header to make retries safe.