michaelbrinkworth
michaelbrinkworth
need help with this to
This lines up with something we’ve seen too, the repeated responses can quietly blow up token usage even if each call “looks” normal at the workflow level. One workaround some...
@luislm21 Sure, you can do this in n8n with no workflow refactor. Using the OpenAI node: Go to Credentials → OpenAI API Set: API Key: your key Base URL: https://aibadgr.com/api/v1...
@EnderKaran The symptoms here line up with rate-limit handling rather than request correctness. If 429s are being retried aggressively without backoff, the client can end up in a retry loop...