OpenAI: gpt-oss-20b Performance
TrustedRouter performance signals and provider route posture for OpenAI: gpt-oss-20b.
openai/gpt-oss-20b
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-20b. 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 |
|---|---|---|---|---|---|---|---|
| cloudflare-workers-ai | 830 ms | 3016 ms | 829 ms | — | 100.00% | — | 4 |
| fireworks | 1425 ms | 2868 ms | 1425 ms | — | 100.00% | — | 7 |
| together | 1854 ms | 3375 ms | 1854 ms | — | 100.00% | — | 5 |
| novita | 1913 ms | 2733 ms | 1912 ms | — | 100.00% | — | 2 |
| deepinfra | 2819 ms | 6416 ms | 2819 ms | — | 100.00% | — | 3 |
| parasail | 4137 ms | 5333 ms | 4137 ms | — | 100.00% | 1 probe_config_error |
5 |
Full provider & model leaderboard.
14 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.