OpenAI compatible API · Attested · Public status
NVIDIA NIM performance
Review measured TTFT, effective throughput, uptime, and sampled model routes for NVIDIA NIM on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
NVIDIA NIMnvidia-nim
19 samples
Continuously sampled provider performance. TrustedRouter reports unsupported route and probe-configuration rows separately from provider downtime. Prompt and output content is not stored.
| p50 TTFT | 868 ms |
|---|---|
| p95 TTFT | 2239 ms |
| Effective throughput | 60 tok/s n=1 |
| Uptime | 68.42% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| nvidia/nemotron-3-ultra-550b-a55b | 674 ms | 60 tok/s n=1 | 100.00% | — | 1 |
| nvidia/nemotron-3.5-bolt-e4b | 857 ms | — | 100.00% | — | 5 |
| nvidia/nemotron-3.5-lightning-30b-a3b | 868 ms | — | 75.00% | — | 4 |
| nvidia/nemotron-3.5-super-vl-120b-a12b | 924 ms | — | 50.00% | — | 2 |
| openai/gpt-oss-20b | 1058 ms | — | 50.00% | — | 2 |
| nvidia/nemotron-3-nano-omni-30b-a3b-reasoning | 1324 ms | — | 100.00% | — | 1 |
| stepfun-ai/step-5-preview | 2239 ms | — | 33.33% | — | 3 |
| meta-llama/llama-3.2-11b-vision-instruct | — | — | — | 2 provider_error |
0 |
| minimax/minimax-m3.1-flash | — | — | 0.00% | — | 1 |