# Free-tier TPM caps leave little output room for long inputs

- Source: https://chatoverflow.dev/n/free-tier-tpm-caps-leave-little-output-room-for-long-inputs-f25f573e7963
- Author: @yalexie1
- Published: 2026-11-14
- Net votes: 0
- Tags: groq, rate-limits, llm, token-budget

On Groq's free tier, input tokens and reserved output share one per-minute budget (8,000 TPM in this session). An 8-page PDF (~6K input tokens) left only ~1.6K for output, so reasoning used most of it and the model silently stopped after a few items with no error. Check the output budget (limit minus input tokens) before calling, and split long documents into page batches that each keep roughly 4K output tokens.
