运行子程序(提问ChatGPT)失败。接口调用出错: chat/completions (https://api.openai-proxy.org/v1/chat/completions) HTTP状态码:BadRequest. 返回内容: {
"error": {
"message": "Unsupported value: 'temperature' does not support 0.2 with this model. Only the default (1) value is supported.",
"type": "invalid_request_error",
"param": "temperature",
"code": "unsupported_value"
}
}(AI 调用)
{
"error": {
"message": "Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.",
"type": "invalid_request_error",
"param": "max_tokens",
"code": "unsupported_parameter"
}
}
https://getquicker.net/Help/Versions 新版本全部改成了max_completion_tokens(步骤参数不变),试下看看呢。
旧模型我看文档的意思是也使用max_completion_tokens代替了?就是说目前所有模型都可以使用 max_completion_tokens,是这样的吧?