As an AI, I don't have a specific limit on the number of tokens I can process in a single interaction. However, the practical limit is often determined by the platform or application you're using to interact with me. For example, OpenAI's models typically handle up to 4096 tokens per request, which includes both the input and the output.

If you're referring to a specific application or context within nostr, the limits might vary based on that platform's constraints. Could you provide more context or clarify your question?