-
Notifications
You must be signed in to change notification settings - Fork 59.7k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Bug] 总结带图片聊天的token消耗差不多是实际情况的100倍 #5908
Comments
Title: [Bug] In summary, the token consumption of chatting with pictures is almost 100 times higher than the actual situation. 📦 Deployment methodOfficial installation package 📌 Software versionv2.15.8 💻 System environmentWindows 📌 System versionWin11 Home Edition 23H2 22635.4145 🌐 BrowserEdge 📌 Browser versionMicrosoft Edge version 131.0.2903.86 (official version) (64-bit) 🐛 Problem descriptionIn the picture, the token consumption of two chat summaries reached an outrageous 4w8. The chat content is shown in Figure 2, which is just a translation of the text of a picture. 📷 Steps to reproduceSend a picture and let 4o or 4o-mini translate the text of the picture. 4o-mini summarizes the chat. Exceptions will only occur when there are pictures. 🚦 Expected resultsWhat's going on with this bug? Since lobechat consumption is normal, it doesn't look like an issue with the api provider. 📝 Supplementary informationNo response |
先说结论:计算没什么问题,4o-mini 的图片消耗就是非常大。我做了一组实验:
可以看到他们的后台 token 统计是差不多的,在使用同一个图片、同一个模型情况下,两个应用产生的计费是没有差别的。 这是我使用的图片的信息: 使用官方的视觉计算器算一下,token 接近、价格消耗接近(毕竟没有算上文本部分),所以计费基本没问题: 那为什么 4o 消耗的 token 少那么多?来看看 4o 的计费: 注意看框里标出来的 base tokens,4o mini(2833)比 4o(85)足足大了 33 倍,这就是 token 看起来差别那么大的原因,4o mini 在文本处理上降本了,但图片没有,所以 OpenAI 通过这个方式把费用拉了回来。 |
4o-mini 的多模态消耗比 4o 的大太多了,我之前遇到过这个问题。 |
The multi-modal consumption of 4o-mini is much larger than that of 4o. I have encountered this problem before. |
@QAbot-zh @yann0917 但还有一个很奇怪的地方,请看第一张图片的三次调用记录,我使用纯4o-mini进行聊天和总结 唯独总结会有很高的消耗,聊天和总结的计费逻辑居然不一样,总结时是按照官方视觉计费器来算的,聊天却有另一套计费逻辑 |
Thanks for the answer But there is another very strange thing. Please see the three call records in the first picture. I use pure 4o-mini to chat and summarize.
That is to say, only the summary will have this exception. In other words, the billing method of using 4o-mini in next-chat summary is different? Is there a difference between chat and completion because of the calling type? |
@narugakuru 我没有复现哦,使用 gpt-4o-mini,两次对话,一次标题生成,浏览器F12记录了三次网络请求,oneapi 日志里也是对应的三次记录,提示数据都很大,基本都对得上 【ps. 官方网站不知道怎么了传图失败,我是在自己部署的网站上聊天测试的】 |
📦 部署方式
官方安装包
📌 软件版本
v2.15.8
💻 系统环境
Windows
📌 系统版本
Win11家庭版 23H2 22635.4145
🌐 浏览器
Edge
📌 浏览器版本
Microsoft Edge 版本 131.0.2903.86 (正式版本) (64 位)
🐛 问题描述
图中有两次聊天总结的token消耗达到了离谱的4w8,聊天内容见图2,仅仅只是翻译一张图片的文本。
最上面的2024-12-09 16:25:32时间的token消耗是同样的对话但是在lobechat的聊天总结。我测试了多个工具lobechat, chatbox都是正常的
网页端https://app.nextchat.dev/#/chat和软件都是一样的问题
📷 复现步骤
发送图片让4o或者4o-mini翻译图片文本,4o-mini总结聊天,只有有图片的时候会有异常
https://app.nextchat.dev/#/chat网页端也是一样的问题
🚦 期望结果
这个bug是怎么回事?因为lobechat消耗是正常的,看起来不像是api供应商的问题
📝 补充信息
No response
The text was updated successfully, but these errors were encountered: