OpenAI: gpt-oss-120b Performance
Compare measured TTFT, throughput, uptime, and route health for gpt-oss-120b across TrustedRouter providers using metadata-only production probes.
openai/gpt-oss-120b
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), 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 | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| sail-research | 1122 ms | 1540 ms | 161 tok/s n=1 | 100.00% | — | 2 |
| nscale | 1136 ms | 1136 ms | — | 100.00% | — | 1 |
| fireworks | 1327 ms | 1541 ms | — | 100.00% | — | 3 |
| regolo | 1393 ms | 1499 ms | 139 tok/s n=2 | 100.00% | — | 2 |
| cerebras | 1403 ms | 3711 ms | 123 tok/s n=1 | 100.00% | — | 9 |
| mancer | 1450 ms | 3108 ms | 104 tok/s n=2 | 100.00% | — | 4 |
| io-net | 1851 ms | 1851 ms | 140 tok/s n=2 | 100.00% | — | 1 |
| parasail | 2030 ms | 2030 ms | — | 100.00% | — | 1 |
| scaleway | 2262 ms | 3774 ms | 80 tok/s n=2 | 100.00% | — | 3 |
| siliconflow | 2308 ms | 2308 ms | 73 tok/s n=1 | 100.00% | — | 1 |
| databricks | 2365 ms | 4046 ms | — | 100.00% | — | 5 |
| akashml | 2421 ms | 6777 ms | — | 100.00% | — | 5 |
| wandb | 2858 ms | 2858 ms | — | 100.00% | — | 1 |
| sambanova | 3767 ms | 3767 ms | — | 100.00% | — | 1 |
| together | 4601 ms | 6338 ms | — | 100.00% | — | 3 |
| tinfoil | 4703 ms | 10812 ms | 73 tok/s n=1 | 100.00% | — | 8 |
| cloudflare-workers-ai | — | — | 172 tok/s n=1 | — | — | 0 |
| nebius | — | — | 103 tok/s n=1 | — | — | 0 |
Full provider & model leaderboard.
22 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.