Nemotron 3.5 Lightning

Nemotron 3.5 Lightning is NVIDIA's open mixture-of-experts model, the efficiency-focused member of the Nemotron 3 family, built for high-throughput, always-on agentic workloads.

start building →

compare models

                             ... ................... .. ....... .....  .
                          ..+****************************+*++**+**++++++- .
                           :%@@@@@@@@@@@@@@@@@@@@@@%%@@%@@@@%%%%%%%%%%%=+..
                          .:%@@@@##@@@@@@@@@@@@@@@@@%@%@@@@@%%%@%%%%%@%%*..
                        ...-%@@@@@@@@@@@@@@@@@@@@@@@@@%%@%@@%@%%%@%@@%%%*.
                   ...:-+****+*+***=%@@%@@@@@@@@@@@@%@@@%%%%@@%%%%%%%%%%*.
               ..:-*==%@@@@%+::.:....:-+*=@@@@@@@@@@@@@%@@%@%@%%%@%%%%%%*:
            ..-+=%@@@@@%%=%==****+-::.....-+*%%%@%@%@%%%%@@@@@@%%@%%%%%%*.
         ..:+=@@@@@%=*+:::.-%%@@@%@%%=+:....:-+=%@@%@@@%%%%%@%%@%%%%%%%=*.
       .:-*%@@@@@*+::.....::=%%@@@@@@@%%=+:....:-*%%%%@%@@%%@%%%%%%%%%%=+:
    ..:*%@@#@@%+:.....:-+*==+----+*=%@@%%%=+:.   :-=%%@%@%%%%%%%%%%%%%%=+..
  ..:*%@@#@@=-:....-+=%%@@%%+:.   ..:-*%@@@%=+:. ..:-=%%%%%%%%%%%%%%%%=%+.
 .:*@@@@#@%*:...:+=@@@@@===***-:.    ..-*%@@@%=-.   .:+%%%%%%%%%%%=%=%%=*.
.:%@@###@=-:  :+%%@@@%*-:.::=@%%*:.    .:+%@@%%%-.   .:+%%%%%%%%%%%%%===+.
 :=@#@##@*:. .+%@@@@=-.   .:%@@%%%-.. .:+%%%%%%*:.  .:+=%%%%%%%%%%%%%===+.
 .:%@##@@%-: .:=@@@@=-.   .:=%@@@@%+::+=%@%@%=+.....:*%%%%%%%%%%%%%=%===+.
  .-%@@@@@%-...-%@@@@*:   .:=@@@@%%%*=%@@%%=*:....:+=%%%%%%=%%%%%%==%%==+.
   .-%@@#@@=-...-%@@@%*:. .:=%@@@@@%%%@@%%*-.. .:+=%%%%%%=--+*======%===+.
    .-%@@@@@=:..:-%@@@@=:..:=@@@%%%@%%%%*-....:+==%%%%%*-:. ..:-*=======+.
     .:=%@@@@%-. .:=@%@%%*--=@%%%%%%%=+:....-*=%%%%%%*-:..    ...:*=====+..
      .:*%@@@@%+:...-*%@%@%=***=**+-:....:+*%%%%%=%*-.         ..-*=====+..
        .+%@@@@%=-....:+=%%%+::.:.:.:--+*=%%%%%==+:..       ..:+*=======+..
         .:+%%@@%@=+:...::--*++++***==%%%%%%==+-..       ..:+*=========*+..
           .:*%@@@@%=*-:...:=%%%%%%%%%%%%=*+:..    ....:-*=============*+..
            ..:+=%@%%%%=**++*======***+-:... ......:++*====%===========*-..
               .:-+=%%%%%%%%+::..:..........::-++======%===============*+.
                  ..:-+**===-::..:..::-+++*======%=%%%%%%============***+.
                     .....::*======%=%===%%=%==%=%%%%============*==*=**-..
                          .:=%%%%%%%%%%%%%%%%=%%=%================*==*=*+..
                          .:*=%%%==%%===%===================**=*=*******-.
                          ..-+++++++++++++++++++-+++++--+--+-+---------::
                             ..   ...... .. .. ..... . .  ..  .. ..  ..

input · usd / 1m tok

$0.05

output · usd / 1m tok

$0.20

context window

262.14ktokens

modalities · in → out

pricing

base api ratesusd per 1m tokens

input: $0.05
output: $0.20
cache read: $0.01

providers

Fireworks hosts Nemotron 3.5 Lightning. Impossibl routes your request intelligently and handles failover automatically when a provider is down.

Fireworks

specifications

takes text in, gives text outnvidia/nemotron-3.5-lightning

creatorNVIDIA
model typeText generation
context window262,144 tokens
maximum outputnot published
input
takes text in, gives text out
outputtext
tool callingnot verified
releasedaug 11, 2026
endpoint/v1/chat/completions

unknown means the public catalog does not establish that fact. a model's documented capabilities can differ from what a particular api supports. see the model documentation for integration details.

try it · your prompt, this model, live

# responses API
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["IMPOSSIBL_API_KEY"],
    base_url="https://api.impossibl.com/v1",
)

resp = client.responses.create(
    model="nvidia/nemotron-3.5-lightning",
    input="▌",
)
print(resp.output_text)

edit the prompt, then run

# responses API
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["IMPOSSIBL_API_KEY"],
    base_url="https://api.impossibl.com/v1",
)

resp = client.responses.create(
    model="nvidia/nemotron-3.5-lightning",
    input="▌",
)
print(resp.output_text)

edit the prompt, then run

benchmarks

intelligence index

12.9#91 of 108 models on the gateway

coding index26.8#55 of 64
agentic index3.5#49 of 53
omniscience-17.7#63 of 84
gpqa74.3%#64 of 80
humanity’s last exam10.6%#69 of 87

GPQA74.3%
AA-LCR60.3%
SciCode32.1%
Humanity’s Last Exam10.6%
Tau Banking8.9%
GDP.pdf All-pass3.0%
Multilingual LCR1.1%
AutomationBench Partial0.8%
CritPt0.0%

Intelligence Index12.86
Omniscience Index-17.72
GDPval Elo637.77
legal index (API)15.5
coding index (API)26.8
agentic index (API)3.5
economics index (API)22.8
engineering index (API)18.1
intelligence index (API)12.9
strategy and ops index (API)6.9
finance and accounting index (API)12.2
healthcare and medical index (API)11.5

view source ↗all source data and breakdowns (json) ↗

each configuration is listed separately; these evaluations describe the tested model configuration, and performance and costs can differ on impossibl. unmeasured scores are omitted and api values keep their source units. last checked 2026-10-14.

compare Nemotron 3.5 Lightning with other models

frontier labs and open weights, best-ranked firstusd / 1m tok · in / out

anthropic/claude-opus-5-5$4.00 / $20.00compare →
openai/gpt-6-astra$10.00 / $50.00compare →
meta/muse-wonder$4.00 / $20.00compare →
xiaomi/mimo-v2.6-pro$0.435 / $0.87compare →

impossibl models --all →

frequently asked questions

What is Nemotron 3.5 Lightning?

Nemotron 3.5 Lightning is NVIDIA's open mixture-of-experts model, the efficiency-focused member of the Nemotron 3 family, built for high-throughput, always-on agentic workloads. It targets specialized tasks such as code review, tool use, and alert monitoring, runs locally on RTX PCs, DGX Spark, and Jetson, and can be post-trained with NeMo.

How much does Nemotron 3.5 Lightning cost?

Nemotron 3.5 Lightning costs $0.05 per million input tokens and $0.20 per million output tokens through the Impossibl API. Cache reads cost $0.01 per million tokens. All rates are in USD.

view the pricing table ↑

What is the context length of Nemotron 3.5 Lightning?

Nemotron 3.5 Lightning has a 262,144-token context window through the Impossibl API.

What inputs and outputs does Nemotron 3.5 Lightning support?

Nemotron 3.5 Lightning accepts text as input. Nemotron 3.5 Lightning returns text.

How do I use Nemotron 3.5 Lightning through an API?

Nemotron 3.5 Lightning is available through the Impossibl API. Use nvidia/nemotron-3.5-lightning as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.

follow the api quickstart →

When was Nemotron 3.5 Lightning released?

NVIDIA released Nemotron 3.5 Lightning on August 11, 2026.

Creator release announcement ↗

this page describes Nemotron 3.5 Lightning as listed by the impossibl public api. prices and availability come from that catalog, refreshed here every five minutes. this is an impossibl offering, not a comparison of independent hosting-provider quotes. model descriptions and release dates, where available, use the creator sources linked under the answers above.

view the source catalog ↗model as markdown ↗report a correction →