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

# Global AI FAQ: Accounts, Tokens, Calls, and Billing

> Common questions and fixes for Global AI: sign-in issues, token management, API errors, billing, and client integrations.

The most common questions when using Global AI. If you cannot find an answer, please [contact us](/en/contact).

## Accounts and sign-in

<AccordionGroup>
  <Accordion title="I did not receive the sign-up verification code">
    First check your spam folder, then confirm you entered the correct email address. If it is still missing, wait a few minutes and try again. If the failure persists, contact support to confirm the platform's email service is working.
  </Accordion>

  <Accordion title="Forgot password and lost email access">
    [Contact us](/en/contact) for manual assistance. To avoid this situation, we recommend [binding a third-party account](/en/account/personal-settings#bind-a-third-party-account) in advance as a backup sign-in method.
  </Accordion>

  <Accordion title="Third-party OAuth sign-in created a different account">
    If you already registered with an email, third-party sign-in creates a new account by default. Sign in to the original email account first, then go to [Personal settings](/en/account/personal-settings#bind-a-third-party-account) and bind the third-party account. After that, either method signs you into the same account.
  </Accordion>
</AccordionGroup>

## Tokens and API calls

<AccordionGroup>
  <Accordion title="Can I recover a lost token key?">
    No. If lost, go to [Token management](/en/usage/tokens), delete the token, create a new one, and update your application configuration.
  </Accordion>

  <Accordion title="Call returns 401 / invalid api key">
    Common causes: the token was copied incompletely, deleted, expired, ran out of quota, or triggered an IP allowlist or model restriction. Go to [Token management](/en/usage/tokens) and check the token status and restrictions.
  </Accordion>

  <Accordion title="Model returns 404 / not found">
    The model ID is misspelled, or the model is not allowed in your group or token. Search for the model on the [Model marketplace](https://globalai.vip/pricing) to confirm the ID, or adjust the token's model restrictions.
  </Accordion>

  <Accordion title="429 Too Many Requests happens frequently">
    The platform enforces concurrency and rate limits per user and per token. Reduce concurrency, or add exponential backoff on the client side. If you need a higher limit, [contact us](/en/contact).
  </Accordion>

  <Accordion title="Streaming output is not working">
    Confirm that `stream=True` is set (Python) or the SSE headers are present (curl), and that your client supports chunked reading. Some models do not support streaming. See the [Model marketplace](https://globalai.vip/pricing) for per-model details.
  </Accordion>
</AccordionGroup>

## Billing and top-up

<AccordionGroup>
  <Accordion title="Payment succeeded but the balance did not update">
    Check the order status on the [Wallet page](/en/billing/topup#view-top-up-history). If the order shows success but the balance did not increase, take a screenshot of the successful payment and [contact us](/en/contact).
  </Accordion>

  <Accordion title="Redemption code shows as invalid">
    Confirm the code has no extra spaces, has not expired, and was not used by another account. Each code is single-use and cannot be redeemed twice.
  </Accordion>

  <Accordion title="Why did the same prompt cost more this time?">
    Actual quota consumption depends on the input and output token counts. Longer conversation history or longer model responses raise costs. Check per-call token details in the [Usage logs](/en/usage/logs).
  </Accordion>

  <Accordion title="How do I estimate monthly cost?">
    View the last 30 days of consumption on the [Dashboard](/en/usage/logs#dashboard), then combine it with each model's multiplier (see the [Model marketplace](https://globalai.vip/pricing)) to estimate future usage.
  </Accordion>
</AccordionGroup>

## Client integrations

<AccordionGroup>
  <Accordion title="Which API address should I enter in a client?">
    Use the API base URL shown on the platform home page, typically `https://globalai.vip/v1`. The native Claude format and some clients require the host URL without `/v1` (`https://globalai.vip`). Follow the client's instructions. See the [Client integration overview](/en/clients/overview) for details.
  </Accordion>

  <Accordion title="Client connection times out or output is truncated">
    The most common cause is an enabled proxy, VPN, or circumvention tool. **Try disabling all proxies and global proxy software**, then retry.
  </Accordion>

  <Accordion title="Campus network cannot reach globalai.vip">
    Switch to the backup domain `https://hk.globalai.vip`. Sign-in, top-up, and API calls all work the same way.
  </Accordion>

  <Accordion title="Why can't I use Agent mode in Cursor?">
    Cursor's third-party API only allows Ask mode and cannot invoke Agent. If you need Agent, subscribe to Cursor's official plan, or use [Claude Code](/en/clients/claude-code) or [Cline / Roo Code](/en/clients/coding-agents) inside Cursor.
  </Accordion>

  <Accordion title="How do I enter a third-party key in Trae?">
    Trae does not support third-party APIs, so you cannot enter a Global AI key directly into its model configuration. Install [Claude Code](/en/clients/claude-code) and use its UI extension inside Trae.
  </Accordion>

  <Accordion title="Claude Code keeps burning quota — how do I check consumption?">
    Claude Code resends historical tokens every round, and long conversation contexts amplify this. Go to [Usage logs](https://globalai.vip/usage-logs/common), filter by token name, and inspect each request's token count and actual charge. See the [cost notes in the integration overview](/en/clients/overview#a-note-on-claude-model-cost).
  </Accordion>

  <Accordion title="Can I use the same token in multiple clients?">
    Yes, but we recommend one token per client so you can distinguish usage in [Usage logs](https://globalai.vip/usage-logs/common) and minimize the impact if a single token leaks.
  </Accordion>
</AccordionGroup>

## Error code cheat sheet

| Status | Meaning                     | Common cause and fix                                                                                    |
| ------ | --------------------------- | ------------------------------------------------------------------------------------------------------- |
| 400    | Bad request                 | Malformed body or fields. Verify the model name and `messages` structure                                |
| 401    | Authentication failed       | Wrong or deleted key, or extra whitespace. Recopy from [/keys](https://globalai.vip/keys)               |
| 403    | Forbidden                   | Token does not allow this model, or the IP allowlist does not match. Adjust the token settings          |
| 404    | Endpoint or model not found | Base URL typo, or the model ID is not in the allowed group                                              |
| 413    | Payload too large           | Exceeds the model context or platform limit. Shorten input or switch to a large-context model           |
| 429    | Rate limited                | Concurrency is too high or too many requests in a short window. Wait, then retry with lower concurrency |
| 500    | Internal server error       | Occasional upstream error. Retry later; if it persists, contact support                                 |
| 503    | Service unavailable         | Upstream is temporarily unavailable or under maintenance. Wait or switch to another model               |

## Security and compliance

<AccordionGroup>
  <Accordion title="What if I suspect a token was stolen?">
    Immediately go to [API keys](https://globalai.vip/keys) and delete the token. Check the recent source IPs in the logs. After deletion, create a new token and update every application that depends on it.
  </Accordion>

  <Accordion title="Should I enable 2FA?">
    Strongly recommended. When your account holds a balance or powers production applications, 2FA significantly reduces the risk of account theft. See [Enable two-factor authentication](/en/account/personal-settings#enable-two-factor-authentication-2fa).
  </Accordion>

  <Accordion title="Does the platform log my request content?">
    The platform only records call metadata (time, model, token count, status) for billing and troubleshooting. Request bodies and response content are not recorded.
  </Accordion>

  <Accordion title="Which countries and regions cannot use Global AI? What are the usage rules?">
    Global AI has explicit regional restrictions and prohibited uses (violence, sexual content, politically sensitive material, criminal activity, malicious abuse, and more). Read the full [Usage policy](/en/policies) before using the platform.
  </Accordion>
</AccordionGroup>


## Related topics

- [Global AI Usage Policy: Regional Limits and Compliance](/en/policies.md)
- [Global AI Token Management: Create, Limit, and Secure](/en/usage/tokens.md)
- [Global AI Quickstart: From Sign-Up to First API Call](/en/quickstart.md)
- [Global AI Account: Sign Up and Sign In Methods](/en/account/register-login.md)
- [Call Global AI: OpenAI, Claude, and Gemini Formats](/en/usage/api.md)