Zernio
Zernio
API Reference

Support Runs

Start a support run (private beta)POSTGet a support run (private beta)GET
Dashboard
llms.txtOpenAPI
OverviewPlatformsAPI ReferenceResources
Support Runs

Get a support run (private beta)

Private beta: returns 403 feature_not_available unless enabled for your account. Returns a run started by your team. Prefer the support.run.completed and support.run.failed webhooks; use this as the fallback, waiting pollAfterSeconds between polls. costUsd is the amount billed: the model cost plus 20%, never above maxCostUsd, and 0 for a failed run.

GET
/v1/support/runs/{runId}

Authorization

bearerAuth
AuthorizationBearer <token>

API key authentication: send your Zernio API key in the Authorization header, prefixed with Bearer.

In: header

Path Parameters

runId*string

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.supportruns.getSupportRun({  path: {    runId: 'run_abc123',  },});console.log(data);
{  "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",  "pollAfterSeconds": 0}
Was this page helpful?

Start a support run (private beta)

Private beta: returns 403 `feature_not_available` unless enabled for your account. Asks Ana, the Zernio support agent, a question about your workspace. The run is asynchronous: 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. Billed when the run finishes at the model cost plus 20%, never above `maxCostUsd`; failed runs are free. 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.