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

# FAQ

> Common questions about sign-up, top-ups, API, billing and errors

## Account

<AccordionGroup>
  <Accordion title="What perks do new users get?">
    After email verification, new users automatically receive a **trial credit**; the exact amount is shown at sign-up.
    Registering via an invite link can stack an additional referral bonus.
  </Accordion>

  <Accordion title="Can I delete my account?">
    Yes. Apply under **Profile settings → Account security → Delete account**.
    After deletion, remaining credit can be refunded within 30 days (minus a fee); it is forfeited afterward.
  </Accordion>

  <Accordion title="Forgot password">
    Sign-in page → Forgot password → receive a reset link by email.
  </Accordion>

  <Accordion title="Can multiple people share one account?">
    Technically yes, but it's **not recommended**. Create a separate token for each user and allocate quota in the console — this controls cost and enables call auditing.
  </Accordion>
</AccordionGroup>

## Top-ups & invoices

<AccordionGroup>
  <Accordion title="Payment succeeded but credit hasn't arrived?">
    It usually credits automatically within 1-2 minutes. If it's still missing after 10 minutes, keep the order number / payment screenshot for later verification.
  </Accordion>

  <Accordion title="Can I get a refund?">
    Yes.

    * Unspent balance within 30 days: refunded to the original method, minus payment-channel fees.
    * Over 30 days: no refund, but it can be transferred to another account or kept on the account balance for continued use.
    * Crypto / redemption codes: no cash refund.
  </Accordion>

  <Accordion title="How do I request an invoice?">
    Submit a request under Console → **Profile settings → Invoices**.
    Electronic general invoices are issued in 1-3 business days; special invoices require qualification info and take 5-10 business days.
    Only RMB orders can be invoiced.
  </Accordion>

  <Accordion title="Do you support enterprise / corporate bank transfers?">
    Yes. When going through the business channel, follow the site announcements.
  </Accordion>
</AccordionGroup>

## API calls

<AccordionGroup>
  <Accordion title="What Base URL should I use?">
    * OpenAI-compatible protocol: `https://openp.ai/v1`
    * Claude / Gemini native protocols: `https://openp.ai` (without `/v1`; the SDK completes the path)
  </Accordion>

  <Accordion title="Why does calling a model return model_not_allowed?">
    * The token's **model allowlist** doesn't include this model → edit the token to add permission.
    * The model is only open to a **higher tier** → upgrade your account group.
    * The model is retired → confirm in the console model list whether it's still available.
  </Accordion>

  <Accordion title="What should I do about a 429?">
    You hit the RPM / TPM rate limit. We suggest:

    1. Implement exponential-backoff retries on the client.
    2. Reduce concurrency or merge requests.
    3. Upgrade to a higher tier for a larger quota.

    See [Rate limits](/en/advanced/rate-limits).
  </Accordion>

  <Accordion title="Do you support the OpenAI Assistants API?">
    Partially, subject to console announcements. Most customers are better served by the [Responses API](/en/api-reference/openai/responses) instead.
  </Accordion>

  <Accordion title="Can I call it directly from the browser?">
    Technically CORS is enabled, so you can. But it's **strongly discouraged** to expose your API key in the frontend — forward through your own backend.
  </Accordion>
</AccordionGroup>

## Models & billing

<AccordionGroup>
  <Accordion title="Why is the price I see higher / lower than OpenAI's official price?">
    OpenPAI price = official published USD price × multiplier × exchange rate.
    Some models are slightly marked up due to supply-side costs (premium accounts / reserved pools); some domestic models are actually cheaper.
    The Console → **Models** page shows each model's live multiplier.
  </Accordion>

  <Accordion title="Why don't reasoning tokens (reasoning_tokens) appear in content?">
    The chain of thought for models like o3 / GPT-5 is **invisible by design**, but it counts toward usage and is billed.
    Claude `thinking` and Gemini `thinkingConfig` modes do return thinking content explicitly.
    See [Reasoning & thinking](/en/advanced/reasoning).
  </Accordion>

  <Accordion title="How much can prompt caching save?">
    It depends. When a repeated system prompt is long and fixed, the cache-hit portion is settled at 0.1-0.5× of the input price,
    typically saving 30-70% of input cost in RAG / agent scenarios. See [Cache billing](/en/pricing/cache-billing).
  </Accordion>

  <Accordion title="Are Midjourney / Suno failed tasks billed?">
    No. Async tasks that fail on the system side are fully refunded; tasks rejected by the upstream are billed by the compute already consumed.
  </Accordion>
</AccordionGroup>

## Logs & deployment

<AccordionGroup>
  <Accordion title="Does OpenPAI record my prompt content?">
    No. Prompt content is not recorded; only token counts are tallied for billing.
  </Accordion>

  <Accordion title="Do you support self-hosted deployment?">
    Enterprise customers can get a self-hosted / on-premises deployment plan; the specifics are subject to site announcements.
  </Accordion>
</AccordionGroup>

## Still have questions?

<Card title="Error code reference" icon="circle-exclamation" href="/en/support/error-codes" horizontal>
  A complete reference of HTTP statuses and error codes.
</Card>