# together — AI API latency & reliability by region
Updated July 23, 2026. Edge latency and uptime of the together API measured from each region.

| Region | p50 TTFB | p95 | Uptime |
| --- | --- | --- | --- |
| Asia (Tokyo) | 185 ms | 375 ms | 100% |
| Europe (Germany) | 296 ms | 495 ms | 100% |
| South America (São Paulo) | 261 ms | 743 ms | 100% |
| US (Central) | 124 ms | 170 ms | 100% |


Source: https://llmlatency.dev/provider/together