← All models
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...
At a glance
- Context window
- 262Ktokens
- Max output
- 236Ktokens
- Knowledge to
- —
- Released
- 2025
Capabilities
CapabilitiesReasoningToolsStructured output
InputText
OutputText
ReasoningSupported
Benchmarks
- Intelligence index
- 9
- Coding index
- 14
- Agentic index
- 1
Standard evaluations
| Benchmark | Score | Tasks |
|---|---|---|
| gpqa_diamond | 0.62 | 1,649 |
| tau_bench_verified_airline | 0.52 | 350 |
Source: Artificial Analysis · as of Sep 16, 2026
Performance
Uptime on IranRouter
78.1%
Aug 18Sep 16
Reference uptime
99.8%
Aug 18Sep 16
Median latency
844 ms
Aug 18Sep 16
Throughput
104.8 tok/s
Aug 18Sep 16
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.
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
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-nano-30b-a3b",
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.