OpenAI compatible API · Attested · Public status

OpenAI: gpt-oss-120b Performance

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

Verify gateway
Onebase URL to migrate
100sof models and routes
Noneprompt logs by default

openai/gpt-oss-120b

open weights Performance

All models

AI IQ IQ 96 #66 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
nebius 827 ms 9190 ms 827 ms 100.00% 2
cerebras 3606 ms 12837 ms 3606 ms 100.00% 37
phala 3635 ms 12506 ms 3634 ms 100.00% 3
fireworks 3866 ms 14385 ms 3866 ms 100.00% 30
baseten 4791 ms 10072 ms 4791 ms 100.00% 14
tinfoil 4983 ms 13254 ms 4983 ms 51 tok/s 100.00% 55
crusoe 5131 ms 10690 ms 5131 ms 8 tok/s 100.00% 12
parasail 10841 ms 12533 ms 10841 ms 60.00% 5

Full provider & model leaderboard.

Provider diversity

23 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.

Workspace access

Sign in

Choose a sign in method. Wallet accounts start with $0 credits.

By signing in you agree to the terms of service and privacy policy.