The error means the total amount of text (tokens) you’re sending—your conversation history plus the bot’s reply length—is exceeding the maximum allowed for the model (16,384 tokens). This is a hard limit set by the model itself.
How to fix it:
- Clear or Shorten the Chat:
- Start a new conversation by clearing your current chat/history.
- Alternatively, delete older messages in the current conversation to reduce the total length.
- Reduce the Output Length:
- If possible, lower the max tokens or reply length setting in your chat website's settings.
Tip:
If you’re using the Free API, CosmosRP-2.5 and CosmosRP-2.1 both have a 16k token limit (8k if you’re not using an API key), so longer chats will hit this error. For more context, you can become a Supporter, which increases limits (e.g., up to 32k on CosmosRP-2.5).
Still stuck?
If the error persists even after clearing the chat, try starting a fresh session or a new character. Wait for community helpers if more detail is needed!
Please note: This is an automated response from @atomic spoke. While it strive to provide accurate assistance, It 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. Thank you.