OpenAI compatible API. Attested gateway. Public status.

OpenAI: gpt-oss-120b Performance

TrustedRouter performance signals and provider route posture for OpenAI: gpt-oss-120b.

Verify gateway
1 URLbase_url migration
100smodels and routes
0prompt logs by default

openai/gpt-oss-120b

Performance

All models

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.

Providerp50 TTFTp95 TTFTp50 TTFBThroughputUptimeConfig excludedSamples
cerebras 785 ms 6565 ms 708 ms 75.00% 76
nebius 1073 ms 1623 ms 1070 ms 100.00% 10
tinfoil 1099 ms 2059 ms 1094 ms 100.00% 58
novita 1113 ms 1537 ms 1010 ms 100.00% 5
phala 1120 ms 5625 ms 1049 ms 100.00% 28
parasail 1159 ms 1289 ms 1056 ms 88.89% 9

Full provider & model leaderboard.

Provider diversity

13 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.

Sign in

Choose a sign in method.