The answer
We have measured this. Across the 3 OpenAI models we have enough completions for, the median wait ranges from 30s (gpt-5.6-sol) to 82s (gpt-5.6-luna). Nine in ten gpt-5.6-sol jobs finished within 16 min. Every figure carries n and a confidence grade on its own page.
OpenAI promises only "within 24 hours" - a ceiling, not a typical wait. The measured medians above are what jobs actually get, and they are why batching is worth the wait for most workloads.
Every model we have measured
Every OpenAI model we have enough completions to publish a percentile for. Most predictable first - spread is p90 over p50.
| Model | Median (p50) | p90 | Spread | n |
|---|---|---|---|---|
| OpenAI gpt-5.6-luna | 82s | 10 min | 7.6x | 3390 |
| OpenAI gpt-5-nano | 74s | 25 min | 20.3x | 3899 |
| OpenAI gpt-5.6-sol | 30s | 16 min | 32.4x | 1884 |
Each row is measured over the last 30 days, and links to that model's own page with its full distribution and confidence grade. A model we have not yet measured enough of to stand behind a percentile is left out entirely - never filled in with an estimate.
How predictable is it?
7.6x spread - p90 over p50
How much longer the slow tail runs than the typical job. Nearer 1× is more predictable.
Half of gpt-5.6-luna jobs finished within 82s, and nine in ten within 10 min - a spread of 7.6x. The slow tail runs 7.6x longer than the typical job, so planning on the median alone would set your deadline that far too tight. That gap is exactly what a median hides - and it is the number no provider publishes. The tightest we measure is gemini-3.7-flash at Google (1.3x); this one sits at 7.6x.
Spread is p90 divided by p50, both measured here over the last 30 days. No provider publishes it; it is the number that tells you whether a median is safe to plan on.
The full numbers, per model
Questions this answers
- How long does the OpenAI batch API actually take?
- It depends on the model. The median ranges from 30s (gpt-5.6-sol) to 82s (gpt-5.6-luna) across the 3 models we have measured, over the last 30 days.
- Is that faster than OpenAI's 24-hour window?
- Far faster for the typical job. OpenAI guarantees completion within 24 hours; the measured medians above are minutes, not hours. The 24-hour window is the contract, not the experience.
- Which OpenAI model is fastest for batch?
- Measured over the last 30 days: gpt-5.6-sol at a median of 30s (p90 16 min, spread 32.4x); gpt-5-nano at a median of 74s (p90 25 min, spread 20.3x); gpt-5.6-luna at a median of 82s (p90 10 min, spread 7.6x). Each model has its own page with the full distribution.
See it live
Every number here is measured, and it is all public.
The live dashboard shows every model with its distribution, n and confidence grade. /v1/coverage is the same data as JSON, no key required. Send five measurements in seven days and the delay is gone: you read every figure live, and the decision endpoints open (/v1/should-i-batch, /v1/estimate-batchtime).