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

# Connection & Usage

> Troubleshoot API connectivity, authentication, model, and task errors.

<AccordionGroup>
  <Accordion title="Why do I get 401 Unauthorized?">
    Send the key as `Authorization: Bearer sk-...`. Confirm the key is active in
    **Console > API Keys** and that your client is not sending an old key from a
    different environment variable.
  </Accordion>

  <Accordion title="Why do I get model_not_found?">
    Call [`GET /v1/models`](/api-reference/list-models) with the same key and
    copy an exact returned ID. A model can be absent because it is unavailable,
    disabled, or outside the key's model limits.
  </Accordion>

  <Accordion title="Why does an image request time out?">
    Synchronous image generation often takes 20 to 60 seconds. Set a timeout of
    at least 120 seconds. Do not automatically resubmit after an ambiguous
    network timeout until you have checked request logs for a billed result.
  </Accordion>

  <Accordion title="Why is video generation not returned immediately?">
    Video generation is asynchronous. Save the returned task ID, poll every 10
    to 20 seconds, and download only after the status becomes `completed`.
  </Accordion>

  <Accordion title="What should I retry?">
    Retry `429` and temporary `5xx` responses with exponential backoff and
    jitter. Do not retry invalid parameters, a rejected key, an unavailable
    model, or insufficient balance without fixing the cause.
  </Accordion>

  <Accordion title="Why does video polling fail after submission?">
    Include the same exact model ID as `?model=...` in both status and content
    URLs. Store the model ID together with every task ID.
  </Accordion>
</AccordionGroup>