The model wrote 23 tokens and billed 150 — reasoning tokens are output you never see
This story is from 2026-10-21. It is preserved in the archive; the latest stories are on the live feed.
On 22 September we sent Kimi K3 a short request with max_tokens: 16 . The visible answer was 23 tokens long. The usage block said 150 completion tokens. 127 of them were text nobody ever saw. That gap is the whole article. Reasoning models think before they answer, the thinking is billed at the out…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-10-21 11:00 · DEV Community — AI
The model wrote 23 tokens and billed 150 — reasoning tokens are output you never see