Measured vs estimated
Which of Meted's numbers are observations and which are models.
Every number Meted reports carries a label: measured or estimated. The
labels appear on the response headers, in the meted dev log, and in a
meted eval report.
Measured
Observations, from the provider or from a clock.
| Output tokens | The provider's own usage.completion_tokens |
| Input tokens | The provider's usage.prompt_tokens |
| Reasoning tokens | completion_tokens_details.reasoning_tokens |
| Optimizer overhead | Tokens Meted added to the request |
| Truncation | finish_reason: "length" |
| Every latency | Engine, gateway, time to first token, provider, total |
Streaming responses report usage too. Meted asks the provider for it, then removes the extra event before it reaches you. See Streaming.
When a provider returns no usage, Meted estimates output tokens from the
response text. The summary's usageMeasured becomes false, and meted eval
marks the output line mixed.
Estimated
Model outputs, from the Sufficiency Engine.
| Estimated sufficient output | Sum of targetOutputTokens |
| Potential output reduction | 1 − sufficient ÷ actual |
| Estimated net reduction | As above, after subtracting overhead |
| Unconstrained estimate | What a request would have produced with no ceiling |
Estimating output without a token limit
Once a ceiling has been applied, the length the model would have produced without one is not observable, because that run did not happen. Meted models it:
- In Observe Mode, the unconstrained output is the actual output. Nothing
was prevented, and the number is marked
measured. - In an active mode, the unconstrained output is estimated from the task
type and complexity, and the number is marked
prior.
prior is a built-in multiplier per complexity band, applied to the target. The
gateway holds no request history, so the multiplier is not calibrated against
your traffic. To measure the unconstrained length instead of modelling it, run
both sides:
meted eval --limit 50
meted eval sends every prompt twice, once without a ceiling and
once with one, so both lengths come from the provider.
Why the two are never mixed
A figure derived from the engine is labelled estimated wherever it surfaces,
and one taken from the provider or a clock is labelled measured. The
optimizer overhead page sets out which
comparison subtracts overhead and which does not.