# fireworks vs typesafe — AI API latency and uptime comparison
Updated September 27, 2026. As of September 27, 2026, fireworks has lower edge latency (time-to-first-byte) than typesafe in 3 of 4 measured region(s). From Europe (Germany), fireworks responds in 98 ms p50 vs 234 ms.

| Region | fireworks p50 | typesafe p50 | Faster |
| --- | --- | --- | --- |
| Asia (Tokyo) | 19 ms | 148 ms | fireworks |
| Europe (Germany) | 98 ms | 234 ms | fireworks |
| South America (São Paulo) | 252 ms | 248 ms | typesafe |
| US (Central) | 28 ms | 111 ms | fireworks |


## Does fireworks or typesafe have better uptime?

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


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/fireworks-vs-typesafe