`x-ratelimit-remaining-tokens`
on a Global Standard gpt-5-mini (1M TPM, Sweden Central, API version `2024-12-01-preview`
), computed each charge as limit - remaining
, and kept only responses where a single request finished within ±2 seconds so the delta was attributable to one call.Breakdown of the 29 paired samples:
20 charged exactlyusage.prompt_tokens
(examples: 8,329 / 13,605 / 40,073 / 93,837)2 within 5% ofinput + max_tokens
ormax(input, max_tokens)
— probably coincidence7 charged well above input — all retried after connection errors (one request with 252,781 input tokens was charged 630,582, suggesting two attempts each hit by a character-based input estimate)
This rules out the documented formulas:
- One request was charged 8,329 tokens with
max_completion_tokens = 10000
. No formula involving max_tokens — sum or maximum — can produce a charge below max_tokens itself. input + completion
matched 0 of 29. Completions aren't counted.- Behavior was identical with
reasoning_effort
atminimal
,low
, and unset. Not a reasoning-budget effect.
The Azure docs are contradictory. One section says the estimate "includes prompt text and count, the max_tokens parameter setting, the best_of parameter setting" — a worst-case ceiling reading. The 429 section commits to an actual sum: "prompt + max_tokens." Neither matches reality. OpenAI's platform docs use
max(max_tokens, character-based estimate)
— also doesn't match.So for a completed request, the counter visibly ends at exact input tokens with no max_tokens component. What I can't observe externally:
-
Is the counter charged when the request arrives (the documented prompt + max_tokens estimate, later reconciled to actual input), or charged once at completion with the exact input?
-
If requests are charged on receipt, does the over-estimate get refunded, or is the refund delayed/aggregated such that it's invisible in my per-request delta?
-
For the retried requests, is each attempt charged independently against the remaining budget, or is there a deduplication window?
Has anyone else seen this exact-input-only behavior? I'm especially curious if the charging-on-receipt theory holds — that would explain why max_tokens never shows up in completed-request deltas.
Next Cursor is losing its edge for my heavy coding workflows →