OpenAI: gpt-oss-120b Performance
Try gpt-oss-120b on us. Starter credit covers your first requests, then one key reaches all 24 provider routes with automatic failover.
openai/gpt-oss-120b
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), effective throughput, and success rate for OpenAI: gpt-oss-120b. 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 |
|---|---|---|---|---|---|---|
| tinfoil | 924 ms | 2917 ms | — | 100.00% | — | 19 |
| sambanova | 1673 ms | 27118 ms | 309 tok/s n=2 | 92.86% | — | 14 |
| akashml | 543 ms | 1112 ms | — | 100.00% | — | 4 |
| cerebras | 615 ms | 2036 ms | 127 tok/s n=1 | 100.00% | 1 provider_error |
2 |
| baseten | 923 ms | 2972 ms | — | 100.00% | — | 4 |
| fireworks | 972 ms | 1704 ms | — | 100.00% | — | 3 |
| databricks | 1177 ms | 1688 ms | — | 100.00% | — | 3 |
| nscale | 1209 ms | 1209 ms | — | 100.00% | — | 1 |
| regolo | 1229 ms | 2032 ms | — | 100.00% | — | 4 |
| scaleway | 1275 ms | 1908 ms | — | 100.00% | — | 4 |
| mancer | 1319 ms | 2702 ms | — | 100.00% | — | 6 |
| together | 2169 ms | 2169 ms | — | 100.00% | — | 1 |
| parasail | 2282 ms | 2282 ms | — | 100.00% | — | 1 |
| cloudflare-workers-ai | 2694 ms | 2694 ms | — | 100.00% | — | 1 |
| privatemode | — | — | — | 0.00% | 4 provider_auth_config |
6 |
Full provider & model leaderboard.
24 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.