OpenAI compatible API. Attested gateway. Public status.
OpenAI: gpt-oss-120b Performance
TrustedRouter performance signals and provider route posture for OpenAI: gpt-oss-120b.
1 URLbase_url migration
100smodels and routes
0prompt logs by default
openai/gpt-oss-120b
Performance
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), throughput, and success rate for OpenAI: gpt-oss-120b — unsupported route and probe-configuration rows are separated from provider downtime, and no prompt or output content is stored.
| Provider | p50 TTFT | p95 TTFT | p50 TTFB | Throughput | Uptime | Config excluded | Samples |
|---|---|---|---|---|---|---|---|
| fireworks | 622 ms | 1177 ms | 603 ms | — | 54.72% | — | 53 |
| cerebras | 684 ms | 961 ms | 651 ms | — | 55.56% | — | 72 |
| nebius | 830 ms | 1277 ms | 786 ms | — | 55.56% | — | 18 |
| parasail | 1114 ms | 1934 ms | 1009 ms | — | 50.00% | — | 8 |
| tinfoil | 1145 ms | 1562 ms | 1042 ms | — | 34.09% | — | 44 |
| novita | 1224 ms | 1224 ms | 1121 ms | — | 33.33% | — | 3 |
| phala | 2939 ms | 8223 ms | 2937 ms | — | 39.13% | — | 23 |
Full provider & model leaderboard.
Provider diversity
15 routes.
More routes give the auto router more room to fail over around provider 429 and 5xx responses.
Streaming
Gateway overhead is measured separately.
Public status separates TLS/health overhead from full model latency so slow LLMs do not inflate the router metric.
Status
Metadata rollups.
Status samples store latency, outcome, provider, model, route, cost, and region metadata only.
View public status or inspect provider routes.