OpenAI: gpt-oss-20b Performance
Compare measured TTFT, throughput, uptime, and route health for gpt-oss-20b across TrustedRouter providers using metadata-only production probes.
openai/gpt-oss-20b
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), 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 | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| io-net | 966 ms | 1537 ms | — | 100.00% | — | 2 |
| cloudflare-workers-ai | 1022 ms | 1661 ms | — | 100.00% | — | 2 |
| regolo | 1028 ms | 3109 ms | — | 100.00% | — | 4 |
| databricks | 1518 ms | 2050 ms | — | 100.00% | — | 2 |
| nscale | 1950 ms | 3297 ms | — | 100.00% | — | 2 |
| akashml | 2265 ms | 4822 ms | — | 100.00% | — | 4 |
| nvidia-nim | 3119 ms | 18949 ms | — | 100.00% | — | 4 |
| deepinfra | 3694 ms | 3694 ms | — | 100.00% | — | 1 |
| parasail | 4039 ms | 4039 ms | — | 100.00% | — | 1 |
Full provider & model leaderboard.
12 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.