# typesafe vs xai — AI API latency and uptime comparison
Updated September 27, 2026. As of September 27, 2026, typesafe and xai are evenly matched on edge latency — each is faster in 2 of 4 measured region(s). From Europe (Germany), typesafe leads at 234 ms vs 295 ms p50.

| Region | typesafe p50 | xai p50 | Faster |
| --- | --- | --- | --- |
| Asia (Tokyo) | 148 ms | 170 ms | typesafe |
| Europe (Germany) | 234 ms | 295 ms | typesafe |
| South America (São Paulo) | 248 ms | 228 ms | xai |
| US (Central) | 111 ms | 107 ms | xai |


## Does typesafe or xai have better uptime?

Over the last 24 hours typesafe and xai 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 |
| --- | --- | --- | --- | --- |
| typesafe | 100% | Asia (Tokyo) | 100% | 122 |
| xai | 100% | Asia (Tokyo) | 100% | 1155 |


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/typesafe-vs-xai