TokensClub documentation

Troubleshooting

Check the address, protocol, key group, complete model ID and balance first, then investigate the error details.

ErrorCheck first
400Request format and model-supported parameters; reduce to a minimal example.
401Whether the key is complete, valid or disabled, and whether the authentication header is correct.
403Group, model permissions, IP or other access restrictions.
404Repeated paths, an incorrect model ID or an unsupported endpoint.
429Request rate, concurrency, quota or upstream limits.
5xx / timeoutCheck usage first, then retry a limited number of times after a delay.

Text works, but tools or multi-turn requests fail

A basic text request does not verify every feature. Record the protocol, model, failure time and request ID, then test the features you need individually.

An HTML response

Confirm that you are calling an API path. An incorrect URL or a proxy verification page may return HTML; do not parse it as JSON.

Information for troubleshooting

Time and timezone:
Client and version:
Model ID / group:
Protocol and endpoint:
HTTP status / error body:
Request ID:
Reproducible:

Remove API keys, passwords and private conversation content before sharing diagnostic information.

Long requests and streaming

A non-streaming request may disconnect with HTTP 524 if no response arrives after about 125 seconds. The upstream may still complete processing and charge for usage.

For long requests, use streaming (stream: true), although streaming does not guarantee avoiding timeouts. After a disconnect, check usage history first. Do not immediately resend while the result or charge is unconfirmed.

Need help? Use the public support contacts on our contact page.

Contact us

Updated: 2026-10-25 · Features depend on the active platform configuration