NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
At a glance
- Context window
- 262Ktokens
- Max output
- 131Ktokens
- Knowledge to
- —
- Released
- 2026
Capabilities
Benchmarks
- Intelligence index
- 14
- Coding index
- 27
- Agentic index
- 6
Standard evaluations
| Benchmark | Score | Tasks |
|---|---|---|
| gpqa_diamond | 0.68 | 738 |
| tau_bench_verified_airline | 0.63 | 49 |
Source: Artificial Analysis · as of Sep 16, 2026
Performance
Uptime on IranRouter
45.5%
Reference uptime
100%
Median latency
777 ms
Throughput
123.6 tok/s
IranRouter uptime comes from our own automated probes; the reference figures are daily measurements of this model's upstream routes. Each card shows a 30-day average, and a day without data stays empty.
Popularity
- Current rank
- #25
- Rank change, 7 days
- +3
Daily tokens · 90 days
129.3B
Ranked by daily token volume across the global model market; the figure above the chart is the daily average.
Supported parameters
Parameters this model accepts; anything else is ignored.
Quick start
from openai import OpenAI
client = OpenAI(
api_key="ir-...",
base_url="https://iranrouter.com/v1",
)
resp = client.chat.completions.create(
model="nvidia/nemotron-3.5-lightning",
messages=[{"role": "user", "content": "سلام!"}],
)
print(resp.choices[0].message.content)Only base_url and the key change; the rest of your code stays as it is.