FAQ

1. Status Code Description

  • 4xx (Client Error): Generally due to request syntax error, authentication failure, or authorization failure, the request cannot be completed.
  • 5xx (Server Error): Generally server-side error, server downtime, request processing timeout, etc.
Error Code Possible Situation Solution
400 Request body format error, etc.
Check the error content returned by the conversation or check the error content in the console, and operate according to the prompt.
[Common Case 1]: If it is a gemini model, you may need to bind a card;
[Common Case 2]: Data volume exceeds limit, common in vision models, image volume exceeding the upstream single request traffic limit will return this error code;
[Common Case 3]: Added unsupported parameters or parameter filling errors. Try creating a new clean assistant to test if it is normal;
[Common Case 4]: Context exceeds limit, clear context or create a new conversation or reduce the number of context items.
401 Authentication failed: Model not supported or server account banned, etc. Contact or check the corresponding service provider account status
403 Request operation unauthorized Operate according to the error information returned by the conversation or the console error information prompt
404 Requested resource not found Check request path, etc.
422 Request format is correct, but semantic error This type of error can be parsed by the server, but cannot be processed. Common in JSON semantic errors (e.g., null value; required value is string, but written as number or boolean, etc.).
429 Request rate reached limit Request rate (TPM or RPM) reached limit, cool down for a while before using
500 Internal server error, unable to complete request If it persists, contact the upstream service provider
501 Server does not support the requested function, unable to complete request
502 The server acting as a gateway or proxy received an invalid response from the upstream server while attempting to fulfill the request
503 The server is currently unable to handle the request due to a temporary overloading or maintenance of the server. The length of the delay may be included in the Retry-After header field
504 The server acting as a gateway or proxy did not receive a timely response from the upstream server

2. Model Image Recognition Issues

First, confirm whether the model supports image recognition. In the popular model list, models with a small eye icon after the name support image recognition.

  • How to Enable: If the model function is not correctly matched, you can find the model in the corresponding service provider's model list, click the settings button after its name, and check the image option.
  • Note: Please refer to the corresponding service provider documentation for specific model information. Models that do not support vision do not need to force the image function to be enabled, and checking the image option will have no effect.