# geometric vs google — AI API latency and uptime comparison
Updated November 22, 2026. As of November 22, 2026, geometric and google are evenly matched on edge latency — each is faster in 2 of 4 measured region(s). From Asia (Tokyo), google leads at 64 ms vs 479 ms p50.

| Region | geometric p50 | google p50 | Faster |
| --- | --- | --- | --- |
| Asia (Tokyo) | 479 ms | 64 ms | google |
| Europe (Germany) | 10 ms | 86 ms | geometric |
| South America (Santiago) | 414 ms | 691 ms | geometric |
| US (Central) | 206 ms | 43 ms | google |


## Does geometric or google have better uptime?

Over the last 24 hours geometric and google are level on availability at 100% of probes succeeding across 4 region(s). Neither is separated from the other by uptime at this sample size.

| Provider | Probes succeeding | Worst region | there | Samples |
| --- | --- | --- | --- | --- |
| geometric | 100% | Asia (Tokyo) | 100% | 1152 |
| google | 100% | Asia (Tokyo) | 100% | 1152 |


Observed availability over the last 24 hours, not a contractual SLA. Longer windows: https://llmlatency.dev/best-uptime

Time to first token (TTFT) for both, with the model named: https://llmlatency.dev/time-to-first-token
Source: https://llmlatency.dev/compare/geometric-vs-google