Includes 694 hourly rounds up to 2026-11-16 from NIMStats by Mauro Druwel (source), measured with a different prompt and timeout. Our own probe adds a round every 30 minutes.
nemotron-3-ultra-550b-a55b
Servingnvidia/nemotron-3-ultra-550b-a55b answered 92.6% of probes on the NVIDIA NIM free API in the last 14 days, with a median time to first token of 1.72 s and 49.9 tok/s. It ranks 5 of 15 tracked models.
Model vs. median
Against the median of models that answered, last 14 days.
nemotron-3-ultra-550b-a55b median of answering models
Error breakdown
24 failed of 325 probes, last 14 days.
| Failure | Probes | Share of failures |
|---|---|---|
| Empty answer | 10 | 41.7% |
| Timed out | 5 | 20.8% |
| Server error (5xx) | 5 | 20.8% |
| Network error | 4 | 16.7% |
Time to first token
Each probe. Lower is better.
Throughput
Tokens per second after the first token, each probe. Higher is better.
Availability heatmap
Last 7 days by UTC hour.
all answered some failed none answered not probed
Run history
Last 20 probes.
| Time | Result | First token | Full reply | Speed |
|---|---|---|---|---|
| OK | 782 ms | 4.79 s | 50.0 tok/s | |
| OK | 546 ms | 6.45 s | 33.0 tok/s | |
| OK | 382 ms | 4.34 s | 50.6 tok/s | |
| OK | 405 ms | 5.39 s | 40.1 tok/s | |
| OK | 877 ms | 6.50 s | 35.6 tok/s | |
| OK | 406 ms | 4.13 s | 53.6 tok/s | |
| OK | 1.59 s | 4.87 s | 60.9 tok/s | |
| OK | 397 ms | 2.50 s | 95.1 tok/s | |
| OK | 461 ms | 6.72 s | 32.0 tok/s | |
| OK | 414 ms | 7.04 s | 30.2 tok/s | |
| OK | 369 ms | 13.7 s | 15.0 tok/s | |
| OK | 717 ms | 3.83 s | 64.3 tok/s | |
| OK | 2.64 s | 10.7 s | 46.9 tok/s | |
| OK | 1.76 s | 10.7 s | 46.6 tok/s | |
| OK | 436 ms | 3.64 s | 57.7 tok/s | |
| OK | 3.56 s | 11.2 s | 44.7 tok/s | |
| OK | 1.39 s | 15.6 s | 32.0 tok/s | |
| OK | 5.59 s | 11.7 s | 42.9 tok/s | |
| OK | 1.08 s | 8.68 s | 57.6 tok/s | |
| OK | 2.51 s | 7.81 s | 64.0 tok/s |
Call nemotron-3-ultra-550b-a55b
The endpoint is OpenAI-compatible.
Create a free key at build.nvidia.com, then:
curl https://integrate.api.nvidia.com/v1/chat/completions \
-H "Authorization: Bearer $NVIDIA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nvidia/nemotron-3-ultra-550b-a55b",
"messages": [{"role": "user", "content": "Hello"}],
"max_tokens": 256,
"stream": true
}'Other models answering
Top of the leaderboard right now.
- 95 nvidia nemotron-3.5-bolt-e4b 114 ms first token · 86.3 tok/s compare
- 93 nvidia nemotron-3.5-super-vl-120b-a12b 343 ms first token · 126 tok/s compare
- 91 poolside laguna-xs-2.1 175 ms first token · 39.8 tok/s compare
- 89 nvidia nemotron-3-nano-omni-30b-a3b-reasoning 717 ms first token · 95.8 tok/s compare
- 63 stepfun step-5-preview 13.0 s first token · 21.3 tok/s compare
- 62 meta muse-glimmer-30b 26.4 s first token · 8.2 tok/s compare