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

open weights Performance

All models

AI IQ IQ 95 #59 public AI IQ rank for gpt-oss-120b
View AI IQ profile

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
fireworks 2934 ms 16454 ms 2933 ms 100.00% 12
nebius 3030 ms 14360 ms 3030 ms 100.00% 15
novita 3725 ms 15866 ms 3724 ms 100.00% 5
phala 5010 ms 16785 ms 5009 ms 100.00% 15
crusoe 5623 ms 20414 ms 5623 ms 100.00% 17
parasail 5760 ms 26241 ms 5759 ms 100.00% 11
cerebras 6044 ms 16764 ms 6044 ms 98.39% 62
tinfoil 10343 ms 17645 ms 10342 ms 100.00% 42
baseten 10744 ms 18011 ms 10744 ms 100.00% 9

Full provider & model leaderboard.

Provider diversity

19 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.