# \SupportAssistantApi
All URIs are relative to *https://zernio.com/api*
Method | HTTP request | Description
------------- | ------------- | -------------
[**ask_support_question**](SupportAssistantApi.md#ask_support_question) | **POST** /v1/support/runs | Ask a support question
[**get_support_answer**](SupportAssistantApi.md#get_support_answer) | **GET** /v1/support/runs/{runId} | Get a support answer
[**list_support_answers**](SupportAssistantApi.md#list_support_answers) | **GET** /v1/support/runs | List a thread's support answers
## ask_support_question
> models::AskSupportQuestion202Response ask_support_question(ask_support_question_request, idempotency_key)
Ask a support question
Asks the Zernio Support Assistant a question about your workspace. Each question starts a run that answers asynchronously. ### How a run works 1. This returns 202 with a `runId`. 2. The answer arrives through the `support.run.completed` and `support.run.failed` webhooks. `GET /v1/support/runs/{runId}` is the fallback. 3. When the assistant finds a problem on Zernio's side, it opens a support ticket with the team (see `supportTicket` on the run) and the run ends as `needs_human`. Pass `threadId` to continue an earlier conversation, and `context` to point the assistant at a post, account, profile or a failed request (its `X-Request-Id`). ### 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. ### Requirements and limits - 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.
### Parameters
Name | Type | Description | Required | Notes
------------- | ------------- | ------------- | ------------- | -------------
**ask_support_question_request** | [**AskSupportQuestionRequest**](AskSupportQuestionRequest.md) | | [required] |
**idempotency_key** | Option<**String**> | Optional client-generated unique key (e.g. a UUID) that makes retries safe. - Same key + same body: replays the original response. - Same key + different body: 422. - Key still processing: 409. A request cut off mid-handler (e.g. by a function timeout) can leave its key in progress, answering 409 until the key expires after 24 hours. | |
### Return type
[**models::AskSupportQuestion202Response**](askSupportQuestion_202_response.md)
### Authorization
[bearerAuth](../README.md#bearerAuth)
### HTTP request headers
- **Content-Type**: application/json
- **Accept**: application/json
[[Back to top]](#) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to Model list]](../README.md#documentation-for-models) [[Back to README]](../README.md)
## get_support_answer
> models::SupportRun get_support_answer(run_id)
Get a support answer
Returns a run started by your team, with the answer once it is ready. Prefer the `support.run.completed` and `support.run.failed` webhooks. Use this as the fallback, waiting `pollAfterSeconds` between polls. `costUsd` is the amount billed for the question, never above `maxCostUsd`, and 0 for a failed run (pricing on Ask a support question).
### Parameters
Name | Type | Description | Required | Notes
------------- | ------------- | ------------- | ------------- | -------------
**run_id** | **String** | | [required] |
### Return type
[**models::SupportRun**](SupportRun.md)
### Authorization
[bearerAuth](../README.md#bearerAuth)
### HTTP request headers
- **Content-Type**: Not defined
- **Accept**: application/json
[[Back to top]](#) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to Model list]](../README.md#documentation-for-models) [[Back to README]](../README.md)
## list_support_answers
> models::ListSupportAnswers200Response list_support_answers(thread_id, limit, cursor)
List a thread's support answers
Lists the runs of one thread that your team started, with each question and its answer, 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.
### Parameters
Name | Type | Description | Required | Notes
------------- | ------------- | ------------- | ------------- | -------------
**thread_id** | **String** | The thread to list, as returned by `POST /v1/support/runs`. | [required] |
**limit** | Option<**i32**> | Runs per page. | |[default to 20]
**cursor** | Option<**String**> | Pass `nextCursor` from the previous page. | |
### Return type
[**models::ListSupportAnswers200Response**](listSupportAnswers_200_response.md)
### Authorization
[bearerAuth](../README.md#bearerAuth)
### HTTP request headers
- **Content-Type**: Not defined
- **Accept**: application/json
[[Back to top]](#) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to Model list]](../README.md#documentation-for-models) [[Back to README]](../README.md)