Nemotron 3 Ultra 550B A55B

Nemotron 3 Ultra is NVIDIA's open-weight language model for reasoning, coding, and coordinating tasks through tools.

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

input · usd / 1m tok

$0.60

output · usd / 1m tok

$2.40

context window

262.14ktokens

modalities · in → out

pricing

base api ratesusd per 1m tokens

input: $0.60
output: $2.40
cache read: $0.12

providers

Fireworks hosts Nemotron 3 Ultra 550B A55B. Impossibl routes your request intelligently and handles failover automatically when a provider is down.

Fireworks

specifications

takes text in, gives text outnvidia/nemotron-3-ultra-550b-a55b

creatorNVIDIA
model typeText generation
context window262,144 tokens
maximum outputnot published
input
takes text in, gives text out
outputtext
tool callingnot verified
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-ultra-550b-a55b",
    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-ultra-550b-a55b",
    input="▌",
)
print(resp.output_text)

edit the prompt, then run

benchmarks

intelligence index

22.9#27 of 33 models on the gateway

coding index49.3#45 of 63
agentic index20.1#38 of 52
omniscience-0.4#13 of 21
gpqa86.7%#42 of 85
humanity’s last exam28.4%#54 of 95

GPQA86.7%
Tau283.3%
IFBench81.4%
AA-LCR79.3%
SciCode40.3%
Terminal-Bench Hard36.4%
Humanity’s Last Exam28.4%
Tau Banking14.2%
Multilingual LCR11.1%
AnalystAgent6.3%
GDP.pdf All-pass5.0%
CritPt3.1%
AutomationBench Partial3.0%

Intelligence Index22.93
Omniscience Index-0.40
GDPval Elo1013.25
legal index (API)26.4
coding index (API)49.3
agentic index (API)20.1
economics index (API)36.6
engineering index (API)27.2
intelligence index (API)22.9
strategy and ops index (API)16.4
finance and accounting index (API)23.9
healthcare and medical index (API)23

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 2026-10-29. some source data could not be refreshed; retained results may be older.

compare Nemotron 3 Ultra 550B A55B 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 →
moonshotai/kimi-k3.1-pro$2.00 / $10.00compare →
deepseek/deepseek-v4.1-flash-1017$0.30 / $1.20compare →

impossibl models --all →

frequently asked questions

What is Nemotron 3 Ultra 550B A55B?

Nemotron 3 Ultra is NVIDIA's open-weight language model for reasoning, coding, and coordinating tasks through tools. Its hybrid architecture combines attention with state-space and mixture-of-experts layers, and applications can turn reasoning on or off.

How much does Nemotron 3 Ultra 550B A55B cost?

Nemotron 3 Ultra 550B A55B costs $0.60 per million input tokens and $2.40 per million output tokens through the Impossibl API. Cache reads cost $0.12 per million tokens. All rates are in USD.

view the pricing table ↑

What is the context length of Nemotron 3 Ultra 550B A55B?

Nemotron 3 Ultra 550B A55B has a 262,144-token context window through the Impossibl API.

What inputs and outputs does Nemotron 3 Ultra 550B A55B support?

Nemotron 3 Ultra 550B A55B accepts text as input. Nemotron 3 Ultra 550B A55B returns text.

How do I use Nemotron 3 Ultra 550B A55B through an API?

Nemotron 3 Ultra 550B A55B is available through the Impossibl API. Use nvidia/nemotron-3-ultra-550b-a55b 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 →

this page describes Nemotron 3 Ultra 550B A55B 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 →