{'error': {'message': "This model's maximum context length is 128000 tokens. However, your messages resulted in 132166 tokens (including 317 in the response_format schemas.)

[yevonnaelandrew]

Error code: 400 - {'error': {'message': "This model's maximum context length is 128000 tokens. However, your messages resulted in 132166 tokens (including 317 in the response_format schemas.). Please reduce the length of the messages or schemas.", 'type': 'invalid_request_error', 'param': 'messages', 'code': 'context_length_exceeded'}}

[hrithikkoduri]

Hi @yevonnaelandrew,

This still is one of the short comings of WebRover, where it falls short sometimes because of context length. Claude has a context length of 200k , so might try using that.

Gemini Flash 2.0 has 1M context window and much cheaper then OpenAI. Haven't had the time to try it, but let me know if you do!

[iamkrishnagupta10]

I'm working on solving this . Still experimenting with the idea of token queuing. Where tokens falling outside of the limit will be on a wait list to be rendered as second batch.