[{"data":1,"prerenderedAt":31},["ShallowReactive",2],{"nr-en-three-ai-endpoints-measured-latency-change-frankfurt":3},{"slug":4,"title":5,"dek":6,"date":7,"time":8,"publishedAt":9,"updated":10,"updatedAt":10,"dateFmt":11,"updatedFmt":10,"kind":12,"tier":13,"author":14,"authorName":15,"topics":16,"tracker":23,"trackerLabel":24,"headlineStat":25,"image":26,"ogImage":27,"imageAlt":5,"csv":10,"minutes":28,"words":29,"html":30},"three-ai-endpoints-measured-latency-change-frankfurt","3 AI endpoints with measured latency change from Frankfurt","The i6eal AI latency index measured the time to first content token of three unchanged endpoints from Frankfurt over two complete UTC weeks. The changes differ.","2026-11-09","08:15","2026-11-09T08:15:00+01:00","","November 9, 2026","daten","standard","ideal-syka","Ideal Syka",[17,18,19,20,21,22],"AI latency","Frankfurt","measurement","Anthropic","OpenAI","Google","\u002Fki-latenz","To the AI latency index","-14.73 % for Claude Haiku 4.5 (gateway, Frankfurt, TTFT)","\u002Fnewsroom\u002Fimg\u002Fthree-ai-endpoints-measured-latency-change-frankfurt.webp","\u002Fog-nr\u002Fthree-ai-endpoints-measured-latency-change-frankfurt.en.png",3,658,"\u003Ch2>What was measured\u003C\u002Fh2>\n\u003Cp>The i6eal AI latency index measures time to first content token (TTFT) from a Lambda function in Frankfurt. Medians of daily measurements are compared across two completed UTC weeks, from 26 October to 1 November and from 2 to 8 November 2026. Only weekdays with a value in both weeks count.\u003C\u002Fp>\n\u003Ch2>The findings in detail\u003C\u002Fh2>\n\u003Cp>The data sections below show how the three endpoints changed. Claude Haiku 4.5 (Anthropic) and Gemini 3 Flash (Google) became faster, GPT-5 mini (OpenAI) slower. Each change refers only to the same endpoint in both weeks. No provider ranking follows from this, nor any general statement about the performance of whole providers.\u003C\u002Fp>\n\u003Ch2>How to read the numbers\u003C\u002Fh2>\n\u003Cp>The measurement is a short, synthetic probe with a short prompt. It is not a measurement of your complete workload. The collector discards a warm-up run and keeps the faster of two successful probes per measurement round. Direct and gateway routes are not ranked against each other. The observed differences establish no cause, statistical significance, model quality or reliability.\u003C\u002Fp>\n\u003Ch2>What this may mean for you\u003C\u002Fh2>\n\u003Cp>If you plan the response time of one of these models for an application based in Germany, it is worth looking at the measurement series before relying on a single weekly value. Whether a change shows up in your own use can only be checked with your own measurements.\u003C\u002Fp>\n\u003Ch2>The finished data sections\u003C\u002Fh2>\n\u003Cdiv class=\"tbl-scroll\">\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth>Endpoint\u003C\u002Fth>\n\u003Cth>Route\u003C\u002Fth>\n\u003Cth align=\"right\">Paired days per week\u003C\u002Fth>\n\u003Cth align=\"right\">Before TTFT (ms)\u003C\u002Fth>\n\u003Cth align=\"right\">Current TTFT (ms)\u003C\u002Fth>\n\u003Cth align=\"right\">Change\u003C\u002Fth>\n\u003C\u002Ftr>\n\u003C\u002Fthead>\n\u003Ctbody>\u003Ctr>\n\u003Ctd>Claude Haiku 4.5 (Anthropic)\u003C\u002Ftd>\n\u003Ctd>gateway\u003C\u002Ftd>\n\u003Ctd align=\"right\">7\u003C\u002Ftd>\n\u003Ctd align=\"right\">672.00\u003C\u002Ftd>\n\u003Ctd align=\"right\">573.00\u003C\u002Ftd>\n\u003Ctd align=\"right\">-14.73 %\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>GPT-5 mini (OpenAI)\u003C\u002Ftd>\n\u003Ctd>gateway\u003C\u002Ftd>\n\u003Ctd align=\"right\">7\u003C\u002Ftd>\n\u003Ctd align=\"right\">712.00\u003C\u002Ftd>\n\u003Ctd align=\"right\">810.00\u003C\u002Ftd>\n\u003Ctd align=\"right\">+13.76 %\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>Gemini 3 Flash (Google)\u003C\u002Ftd>\n\u003Ctd>gateway\u003C\u002Ftd>\n\u003Ctd align=\"right\">7\u003C\u002Ftd>\n\u003Ctd align=\"right\">1565.00\u003C\u002Ftd>\n\u003Ctd align=\"right\">1383.00\u003C\u002Ftd>\n\u003Ctd align=\"right\">-11.63 %\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftbody>\u003C\u002Ftable>\u003C\u002Fdiv>\n\u003Cp>2026-10-26–2026-11-01 → 2026-11-02–2026-11-08 (UTC).\u003C\u002Fp>\n\u003Ch2>Coverage and measurement limits\u003C\u002Fh2>\n\u003Cp>7 endpoints have sufficient paired days and unchanged model\u002Froute descriptions. 0 endpoints have insufficient paired days; 0 were excluded because model\u002Froute 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.\u003C\u002Fp>\n\u003Cp>Source timestamp: 2026-11-09T01:20:59.205Z.\u003C\u002Fp>\n\u003Ch2>Observed latency changes\u003C\u002Fh2>\n\u003Cdiv class=\"tbl-scroll\">\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth>Endpoint\u003C\u002Fth>\n\u003Cth>Route\u003C\u002Fth>\n\u003Cth align=\"right\">Paired days per week\u003C\u002Fth>\n\u003Cth align=\"right\">Before TTFT (ms)\u003C\u002Fth>\n\u003Cth align=\"right\">Current TTFT (ms)\u003C\u002Fth>\n\u003Cth align=\"right\">Change\u003C\u002Fth>\n\u003C\u002Ftr>\n\u003C\u002Fthead>\n\u003Ctbody>\u003Ctr>\n\u003Ctd>Claude Haiku 4.5 (Anthropic)\u003C\u002Ftd>\n\u003Ctd>gateway\u003C\u002Ftd>\n\u003Ctd align=\"right\">7\u003C\u002Ftd>\n\u003Ctd align=\"right\">672.00\u003C\u002Ftd>\n\u003Ctd align=\"right\">573.00\u003C\u002Ftd>\n\u003Ctd align=\"right\">-14.73 %\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>GPT-5 mini (OpenAI)\u003C\u002Ftd>\n\u003Ctd>gateway\u003C\u002Ftd>\n\u003Ctd align=\"right\">7\u003C\u002Ftd>\n\u003Ctd align=\"right\">712.00\u003C\u002Ftd>\n\u003Ctd align=\"right\">810.00\u003C\u002Ftd>\n\u003Ctd align=\"right\">+13.76 %\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>Gemini 3 Flash (Google)\u003C\u002Ftd>\n\u003Ctd>gateway\u003C\u002Ftd>\n\u003Ctd align=\"right\">7\u003C\u002Ftd>\n\u003Ctd align=\"right\">1565.00\u003C\u002Ftd>\n\u003Ctd align=\"right\">1383.00\u003C\u002Ftd>\n\u003Ctd align=\"right\">-11.63 %\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftbody>\u003C\u002Ftable>\u003C\u002Fdiv>\n\u003Cp>2026-10-26–2026-11-01 → 2026-11-02–2026-11-08 (UTC).\u003C\u002Fp>\n\u003Ch2>Coverage and measurement limits\u003C\u002Fh2>\n\u003Cp>7 endpoints have sufficient paired days and unchanged model\u002Froute descriptions. 0 endpoints have insufficient paired days; 0 were excluded because model\u002Froute descriptions changed.\u003C\u002Fp>\n\u003Cp>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.\u003C\u002Fp>\n\u003Cp>\u003Ca href=\"https:\u002F\u002Fi6eal.de\u002Fki-latenz\u002F\">i6eal KI-Latenz-Index\u003C\u002Fa>. Source timestamp: 2026-11-09T01:20:59.205Z.\u003C\u002Fp>\n\u003Ch2>Sources\u003C\u002Fh2>\n\u003Cul>\n\u003Cli>\u003Ca href=\"https:\u002F\u002Fi6eal.de\u002Fki-latenz\u002F\">i6eal\u003C\u002Fa>\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>\u003Cem>Editorially owned by \u003Ca href=\"\u002Fen\u002Fautor\u002Fideal-syka\">Ideal Syka\u003C\u002Fa>. Sources and method: \u003Ca href=\"\u002Fen\u002Fredaktion\">Newsroom & method\u003C\u002Fa>. Tips and corrections: \u003Ca href=\"mailto:ai@i6eal.de\">ai@i6eal.de\u003C\u002Fa>.\u003C\u002Fem>\u003C\u002Fp>\n",1794665243162]