OpenAI: gpt-oss-120b Performance
TrustedRouter performance signals and provider route posture for OpenAI: gpt-oss-120b.
openai/gpt-oss-120b
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), effective throughput, and success rate for OpenAI: gpt-oss-120b. Effective throughput uses provider-reported output tokens over complete request time. 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 | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|---|
| together | 697 ms | 3670 ms | 697 ms | 129 tok/s n=1 | 100.00% | — | 2 |
| deepinfra | 923 ms | 3805 ms | 923 ms | 28 tok/s n=1 | 100.00% | — | 2 |
| fireworks | 1170 ms | 1335 ms | 1170 ms | 116 tok/s n=1 | 100.00% | — | 5 |
| cloudflare-workers-ai | 1240 ms | 2611 ms | 1240 ms | 48 tok/s n=1 | 100.00% | — | 3 |
| cerebras | 1424 ms | 2783 ms | 1424 ms | 163 tok/s n=1 | 100.00% | — | 7 |
| novita | 1488 ms | 3146 ms | 1488 ms | 21 tok/s n=1 | 100.00% | — | 2 |
| baseten | 1590 ms | 2820 ms | 1590 ms | 121 tok/s n=1 | 100.00% | — | 3 |
| parasail | 1597 ms | 1597 ms | 1597 ms | 58 tok/s n=1 | 100.00% | — | 1 |
| nebius | 1619 ms | 1619 ms | 1619 ms | 225 tok/s n=1 | 100.00% | — | 1 |
| crusoe | 4033 ms | 4457 ms | 4033 ms | 65 tok/s n=1 | 100.00% | — | 3 |
| siliconflow | 26205 ms | 26205 ms | 26204 ms | — | 100.00% | — | 1 |
| tinfoil | 1323 ms | 3674 ms | 1323 ms | 84 tok/s n=1 | 90.00% | — | 10 |
Full provider & model leaderboard.
24 routes.
More routes give the auto router more room to fail over around provider 429 and 5xx responses.
Gateway overhead is measured separately.
Public status separates TLS/health overhead from full model latency so slow LLMs do not inflate the router metric.
Metadata rollups.
Status samples store latency, outcome, provider, model, route, cost, and region metadata only.
View public status or inspect provider routes.