OpenAI compatible API · Attested · Public status
NVIDIA: Nemotron 3 Ultra Performance
TrustedRouter performance signals and provider route posture for NVIDIA: Nemotron 3 Ultra.
Onebase URL to migrate
100sof models and routes
Noneprompt logs by default
nvidia/nemotron-3-ultra-550b-a55b
open weights
Performance
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), throughput, and success rate for NVIDIA: Nemotron 3 Ultra — 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 | Throughput | Uptime | Config excluded | Samples |
|---|---|---|---|---|---|---|---|
| nebius | 3264 ms | 11477 ms | 3264 ms | 144 tok/s | 100.00% | — | 12 |
| baseten | 3889 ms | 10915 ms | 3889 ms | 237 tok/s | 100.00% | — | 12 |
| together | 6971 ms | 15771 ms | 6971 ms | — | 100.00% | — | 11 |
Full provider & model leaderboard.
Provider diversity
7 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.
View public status or inspect provider routes.