> ## Documentation Index
> Fetch the complete documentation index at: https://docs.4096bytes.com/llms.txt
> Use this file to discover all available pages before exploring further.

# FAQ

> Troubleshoot common 4096bytes client setup errors

This page covers common issues when connecting 4096bytes to clients. Start by checking three values: API Key, Base URL, and model name.

## Connection parameters

<AccordionGroup>
  <Accordion title="What should I use as the Base URL?">
    OpenAI compatible clients usually use `https://api.4096bytes.com`. If the dashboard shows a client-specific address in the **Use key** dialog, use the value shown there.
  </Accordion>

  <Accordion title="Should I add /v1, /chat/completions, or /messages myself?">
    Do not manually append API paths. Most clients only need the Base URL root, and the client app adds the request path. Claude Code, Codex, and Cursor may use different formats, so follow the matching client page.
  </Accordion>

  <Accordion title="Where do I get the model name?">
    Copy the model name from the dashboard. Keep letters, numbers, hyphens, and version suffixes exactly the same. Do not copy model names from old screenshots or other users.
  </Accordion>

  <Accordion title="Can I copy example values directly?">
    `YOUR_4096BYTES_API_KEY` and `PASTE_MODEL_NAME_FROM_DASHBOARD` are placeholders. Copy the real API Key and model name from the dashboard. The fixed `https://api.4096bytes.com` value is the current OpenAI compatible endpoint.
  </Accordion>
</AccordionGroup>

## API Key management

<AccordionGroup>
  <Accordion title="Can multiple clients share one API Key?">
    Technically yes, but it is not recommended. Use separate keys for Codex, Claude Code, Cursor, and Cherry Studio. This makes usage easier to trace and lets you disable only one key if it leaks.
  </Accordion>

  <Accordion title="Can I view the full API Key again after creation?">
    Usually no. Copy and store it immediately after creation. If you forgot to save it, delete the old key and create a new one.
  </Accordion>

  <Accordion title="What should I do if my API Key leaks?">
    Delete the leaked key in the dashboard immediately. Then create a new key and update the affected client. Do not keep using a key that appeared in screenshots, logs, chats, or public repositories.
  </Accordion>

  <Accordion title="Should I set a quota limit?">
    For personal long-term use, you can start without a limit. For temporary tests, team members, shared devices, or rarely used clients, set a small limit to avoid unexpected usage.
  </Accordion>
</AccordionGroup>

## Errors

<AccordionGroup>
  <Accordion title="401 or authentication failed">
    The API Key may be invalid, deleted, incomplete, or copied with extra characters. Copy it again and check for spaces, newlines, smart quotes, or hidden characters.
  </Accordion>

  <Accordion title="403 or permission denied">
    Check the key group, model availability, and account status. The group must be enabled and include the model you are calling.
  </Accordion>

  <Accordion title="404 or endpoint not found">
    The Base URL may be wrong, or the client may be appending paths incorrectly. Use `https://api.4096bytes.com` and remove any manually added full request path.
  </Accordion>

  <Accordion title="429 or too many requests">
    Request rate, concurrency, balance, or key limits may have been reached. Reduce concurrency, retry later, and check balance, quota, and rate limits in the dashboard.
  </Accordion>

  <Accordion title="model not found">
    Copy the model name again from the dashboard. It must match exactly, including capitalization, numbers, hyphens, and suffixes.
  </Accordion>

  <Accordion title="unsupported protocol or invalid URL">
    The Base URL format is incomplete. It must start with `https://`. Do not enter `api.4096bytes.com`, extra spaces, quotes, or line breaks.
  </Accordion>
</AccordionGroup>

## Client behavior

<AccordionGroup>
  <Accordion title="The client still fails after saving settings">
    Restart the client first. Then check whether there are multiple config locations, providers, or model lists. Confirm the active model comes from 4096bytes.
  </Accordion>

  <Accordion title="Why does Cursor still use official models?">
    Cursor custom API Keys may not affect every built-in feature. Select the 4096bytes model in Chat or Agent. Tab completion, indexing, and background tasks may still use Cursor services.
  </Accordion>

  <Accordion title="Why does Claude Code ignore the Base URL?">
    Claude Code reads Anthropic-related environment variables. Follow [Claude Code](/en/clients/claude-code) and use `ANTHROPIC_BASE_URL` plus the matching auth variable.
  </Accordion>

  <Accordion title="Codex still uses the old model">
    Put the new config at the beginning of `~/.codex/config.toml`, and make sure `model_provider` points to the 4096bytes provider. Restart the terminal after saving.
  </Accordion>

  <Accordion title="Cherry Studio does not show models">
    If the client cannot fetch the model list automatically, add the model name manually from the dashboard and select it again in the current chat.
  </Accordion>
</AccordionGroup>

## Recommended order

1. Copy the API Key again.
2. Confirm the Base URL is `https://api.4096bytes.com` or the client-specific value shown in the dashboard.
3. Copy the model name again.
4. Confirm the provider type matches the client page.
5. Restart the client or terminal.
6. Check balance, quota, key expiry, rate limits, and group status.
7. Contact support with redacted details.

If you have not completed the basic setup, start with [Get an API Key](/en/quickstart/get-api-key), then open the matching client page.