Max Token Limits Incorrect?

[lhyphendixon]

Self Checks

• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• Please do not modify this template :) and fill in all the required fields.

1. Is this request related to a challenge you're experiencing? Tell me about your story.

Hey guys, for some reason many models in both the Dify Cloud and Self-Hosted instances have Max Token limits far short of their actual capabilities. Surely I’m just missing something. The Claude models, for example, should have 200k token capabilities, yet, when I’m adjusting the model options in the chatbot builder, it only lets me go up to 8k. GPT-4 models are also well short of what they should be aside from the 32k model, which appropriately allows up to 32k. What’s going on?

2. Additional context or comments

No response

[crazywoola]

200k is context size, and 4k is the max tokens of output. I think you are referring to this one.