#messages are not generated in some chats.

5 messages · Page 1 of 1 (latest)

heavy grove
#

After the error about the checkmarks in the privacy settings started to pop up, two large chats in Silly Tavern stopped working. Error 429 Too Many Requests. I use Deepseek V3.1. Everything works in the new chats, please help, I really don't want to lose progress.

mystic badgeBOT
#

I'm an AI assistant - my answers may be incorrect and I cannot see screenshots. Please verify information with the OpenRouter docs.

To help debug your issue, I need a bit more information:

  1. What is the exact error message or response you see (full text, not just "429") when trying to use the affected chats?
  2. What is the exact model identifier you are using (e.g., deepseek-chat, deepseek-coder, or something else)?
  3. Can you share the relevant code snippet or describe precisely how you're making the API call in SillyTavern for these chats?

These details are essential for troubleshooting and for mods to assist further if needed.

-# This is an automated response powered by Answer HQ. Use !mute to stop the bot from responding.

Author Not Found

The author you are looking for could not be found.

heavy grove
#
  1. Streaming request failed with status 429 Too Many Requests
  2. Deepseek v3.1 free
mystic badgeBOT
#

Thank you for the details.

A 429 Too Many Requests error means the model or provider rate limit has been exceeded. For the exact model you are using, deepseek/deepseek-chat-v3-0324:free, OpenRouter "routes requests to the best providers that are able to handle your prompt size and parameters, with fallbacks to maximize uptime" DeepSeek V3 0324.

Possible causes and next steps:

  • You may have hit the rate or concurrency limit for the free DeepSeek V3.1 model in those chats. Free variants may be throttled or queued during peak usage.
  • Older/larger chats can hit token/context limits or trigger stricter throttling. The context limit for this model is 164K tokens, but very active chats might have usage patterns that trip provider anti-abuse or rate controls DeepSeek V3 0324.
  • New chats working suggests the issue is chat-specific, possibly due to context size or prior usage.

What you can try:

  1. Reduce the message history/context in affected chats (archive or trim earlier messages) and test again.
  2. Wait and retry later as rate limits may reset after a cooldown period.
  3. If possible, upgrade to a paid provider or use another model with higher rate limits.

If you continue to experience this error, there may be a limitation or temporary throttling on the free DeepSeek model. For persistent issues, contact SillyTavern support for app-specific help or ask OpenRouter mods for clarification.

For more on provider routing and rate limits, see: "OpenRouter routes requests to the best providers that are able to handle your prompt size and parameters, with fallbacks to maximize uptime." [Provider Routing](https://openrouter.ai/docs...

DeepSeek V3 0324 - API, Providers, Stats

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.

It succeeds the DeepSeek V3 model and performs really well on a variety of tasks. Run DeepSeek V3 0324 with API

Author Not Found

The author you are looking for could not be found.

#

.../provider-routing)

You can review model specifics and limits here: DeepSeek V3 0324

If this does not resolve your problem, please contact the mods through the Discord server for further assistance.

-# This is an automated response powered by Answer HQ. Use !mute to stop the bot from responding.

DeepSeek V3 0324 (free) - API, Providers, Stats

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.

It succeeds the DeepSeek V3 model and performs really well on a variety of tasks. Run DeepSeek V3 0324 (free) with API