openai.BadRequestError: Error code: 400 - {'object': 'error', 'message': "This model's maximum context length is 4096 tokens.

[Liwan-Chen]

openai.BadRequestError: Error code: 400 - {'object': 'error', 'message': "This model's maximum context length is 4096 tokens. However, your messages resulted in 4544 tokens. Please reduce the length of the messages.", 'code': 40303}
使用的[Llama-3-70B] 模型 max token 是8k， 为什么会出现这个token 的限制？