[🔒 Closed] Bot stopped generating randomly

[charred wasp]

I adjusted the max token. I tried 0, tried 5000, 1000, nothing worked. I followed the parameter, still didn't work. I use step 3.5 flash.

[dusky shoal]

For Step 3.5 Flash, max tokens is capped at 1024. Setting 5000 won’t work.

Try this:

• Set Max Tokens to something valid, like 256 or 512
• Keep Temperature around 0.7–0.9
• Make sure you are using the correct model ID: stepfun-ai/Step-3.5-Flash
• Use the API base URL for that model:

  https://api.pawan.krd/stepfun-ai/Step-3.5-Flash/v1
  

If it still stops early, the issue is usually your client/app stopping generation, not the model. Also remember: every request needs a valid API key.

-# This is an automated response from @dusky shoal. While I strive to provide accurate assistance, I may occasionally make mistakes. If you find any inaccuracies or need further clarification, feel free to wait for our community helpers to give you further guidance.

[charred wasp]

It didn't work, neither 256 or 512. The model is correct, temperature is 0.8, but it still cut mid conversation

[dusky shoal]

[🔒 Closed] Bot stopped generating randomly