> ## Documentation Index
> Fetch the complete documentation index at: https://docs.yingtu.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# API technical support

> Contact API support with a safe diagnostic package, understand the current service-status boundary, and avoid sharing credentials or image payloads.

Email [hi@yingtu.ai](mailto:hi@yingtu.ai) when a documented troubleshooting step does not resolve an API, asynchronous-task, access, or billing problem.

As of September 2026, the operations team brings three years of experience operating AI API gateway services. That experience informs the retry, task-durability, billing, and diagnostic guidance in these docs; it is not a contractual response-time or uptime guarantee.

## Include enough information to investigate

Send one report per incident and include the fields that apply:

| Information        | Example or guidance                                                     |
| ------------------ | ----------------------------------------------------------------------- |
| Request identifier | `responseId` from a synchronous response                                |
| Task identifier    | `task_id` from an asynchronous submission                               |
| Model              | Exact model ID, such as `gemini-3.1-flash-image`                        |
| Operation          | `generateContent`, `asyncGenerateContent`, or task retrieval            |
| Time               | Timestamp with time zone; UTC is preferred                              |
| Result             | HTTP status, `error.code`, and a short redacted error message           |
| Billing context    | Whether quota was reserved, settled, returned, or appears unchanged     |
| Reproduction       | Minimal request structure with the prompt and media removed or replaced |

If neither `responseId` nor `task_id` exists, include the request time, operation, model ID, and the HTTP response that was available.

<Warning>
  Never send an API key, Authorization header, password, payment credential,
  full Base64 image, or unnecessary personal data. Revoke or rotate a key
  before contacting support if it may have been exposed.
</Warning>

## Check the documented action first

* For HTTP status and retry decisions, use [API errors and safe retries](/en/getting-started/errors-and-retries).
* For a task that remains pending, use [bounded polling](/en/unified-api/polling) and include the saved `task_id`.
* For reserved or returned API quota, use [image generation billing](/en/getting-started/billing).
* For request capacity, upstream `429`, and the availability objective, use [traffic capacity and availability](/en/getting-started/traffic-capacity-and-availability).

## Service status and response expectations

There is currently no public historical status dashboard or incident-subscription feed. The availability figure in this documentation is an operational objective, not measured public uptime or a contractual SLA.

No public first-response time is promised. A complete diagnostic package reduces the clarification needed before an incident can be investigated. Material model or API documentation changes are recorded in the [documentation changelog](/en/resources/changelog); the current model catalog and prices remain available in the [model marketplace](https://api.yingtu.ai/pricing).

<CardGroup cols={2}>
  <Card title="Email API support" icon="mail" href="mailto:hi@yingtu.ai">
    Send a redacted report with the request or task identifiers.
  </Card>

  <Card title="Protect submitted data" icon="shield-check" href="/en/resources/data-handling-and-privacy">
    Review upstream transfer, diagnostics, and retention boundaries.
  </Card>
</CardGroup>