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...
Context
262Ktokens
About 374 pages of text at once
Max output
236Ktokens
About 337 pages in one answer
Intelligence
5.5/ 100
Above 0% of the catalogue
Output speed
108tokens/s
A 500-word answer in about 6.5 s
From public market statistics for this model
First token
0.6s
Reasoning models start later
From public market statistics for this model
Health, 30 days
94.63%
23 of 30 days without a fault
IranRouter’s measurements
Price & cost
Every rate in Rial. A request pays only for the tokens it actually uses.
| Input | 191,870 | IRR / 1M tokens |
|---|---|---|
| Output | 548,199 | IRR / 1M tokens |
| Reasoning tokensThe output rate | 548,199 | IRR / 1M tokens |
| Cache read | 109,640 | IRR / 1M tokens |
With prompt caching, the fixed part of your prompt is billed at the cache-read rate on later requests.
What would this model cost you a month?
Monthly cost
27.14MIRR
905K IRR a day, 452 IRR each request
The same work on peer models
30 days at today’s rate.
Rial price over 90 days
It moves with the exchange rate; the steps are the maker’s own price changes. Built at today’s margin, so approximate if the margin changed in the window.
Performance, 30 days
Health is measured by IranRouter itself: a day counts as healthy unless requests to this model failed on our side or it could not be served. First token and speed come from IranRouter’s traffic, and from public market statistics for this model on days without enough of it.
Daily health94.63%
Time to first token0.70 s
Output speed135 tokens/s
Place in the market
By usage across the global model market.
Daily rank#30
Share of the day’s tokens0.5%
Among its peers
Cost of one message against intelligence; this model is highlighted.
Cost of one message, IRR (log scale)
Capabilities
- Input
- Text
- Output
- Text
Parameters it accepts
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_pOther benchmarks
Standard tests
- GPQA DiamondScore: 70%Tasks: 1,926
- τ-bench Verified AirlineScore: 66%Tasks: 349
Start in a minute
The official OpenAI and Anthropic SDKs; only the address and the key change.
https://iranrouter.com/v1nvidia/nemotron-3.5-lightning# pip install openai from openai import OpenAI client = OpenAI( base_url="https://iranrouter.com/v1", api_key="ir-...", ) r = client.chat.completions.create( model="nvidia/nemotron-3.5-lightning", messages=[{"role": "user", "content": "Hello, introduce yourself"}], ) print(r.choices[0].message.content)
Peer models
Its family and models with a close score; the last column compares one message’s cost with this model.
| Model | Against this model | ||||
|---|---|---|---|---|---|
| Meta: Muse Glimmer 30BMeta | 3,289 | 6.3 | 81 | 131K | 400% dearer |
| Google: Gemini 3.5 Flash LiteGoogle | 5,071 | 11.7 | 132 | 1M | 671% dearer |
| NVIDIA: Nemotron 3 UltraNVIDIA | 6,578 | 11.8 | 69 | 262K | 900% dearer |
Technical specs
- ID
nvidia/nemotron-3.5-lightning- Maker
- NVIDIA
- Tokenizer
- Other
- Released
- Aug 11, 2026
- Added to IranRouter
- Aug 19, 2026
- Context
- 262,144 tokens
- Max output
- 235,929 tokens
Scores by Artificial Analysis, as of Oct 31, 2026