What was measured
The i6eal AI latency index measures time to first content token (TTFT) from a Lambda function in Frankfurt. It compares medians of daily measurements across two completed UTC weeks: 2026-11-02 to 2026-11-08 and 2026-11-09 to 2026-11-15. For the endpoint GPT-5 mini (OpenAI, direct route), values exist for all seven weekdays in both weeks. The measured change is +13.77 % (from 770 to 876 ms).
What this means for you
You should read the figure as an observation within an unchanged endpoint, not as a ranking or a statement about the overall performance of a provider. The index only compares how the same endpoint changed between two weeks. Whether the slowdown matters for your own workload depends on your prompts, your load and your requirements.
What remains open
The source establishes neither a cause nor statistical significance, model quality or reliability. It is a short synthetic probe with a short prompt, not a measurement of your full workload. Direct and gateway routes are deliberately not compared against each other.
Observed latency changes
| Endpoint | Route | Paired days per week | Before TTFT (ms) | Current TTFT (ms) | Change |
|---|---|---|---|---|---|
| GPT-5 mini (OpenAI) | direct | 7 | 770.00 | 876.00 | +13.77 % |
2026-11-02–2026-11-08 → 2026-11-09–2026-11-15 (UTC).
Coverage and measurement limits
7 endpoints have sufficient paired days and unchanged model/route descriptions. 0 endpoints have insufficient paired days; 0 were excluded because model/route descriptions changed.
TTFT measures time to the first content token from a Lambda in Frankfurt. This compares medians of daily measurements in two completed UTC weeks. Only weekdays with a value in both weeks count; each endpoint needs at least five paired days. The collector discards a warm-up and keeps the faster of two successful probes per measurement round. This is a short synthetic probe, not a measurement of your entire workload. Direct and gateway routes are not ranked against each other. Observed differences establish no cause, statistical significance, model quality or reliability.
i6eal KI-Latenz-Index. Source timestamp: 2026-11-16T01:20:59.062Z.
Sources
Editorially owned by Ideal Syka. Sources and method: Newsroom & method. Tips and corrections: ai@i6eal.de.




