Requesty
Sign in

identity

open weights
NVIDIA logo

nemotron-3-super-120b-a12bNVIDIA

in /1Mfreeinput tokens
out /1Mfreeoutput tokens
context1.0M66K out
median ttft2.55smeasured
api
chat
hosting
US
model lab
NVIDIA
weights
open
added
March 2026
model id
nvidia/nemotron-3-super-120b-a12b

capabilities 2/8

visionreasoningtoolscachingweb searchjson schemacomputer useimage gen

pricing

no markup
input
free
output
free
cache write
-
cache read
-

worked cost

Estimated cost for three request volumes
volumecost
100K in + 10K outfree
1M in + 100K outfree
10M in + 1M outfree

Requesty charges what the upstream provider charges, with no markup and no per-request fee. Prompt caching and smart routing cut the effective cost further on repeated context. Gateway pricing

provider price, passed throughper 1M tokens

measured

through Sep 12
median ttft
2.55s
median tok/s
89.0
cache hit
72.2%
answered
95.20%

Weekly aggregates from production traffic routed through Requesty to this endpoint. A metric with no qualifying sample is left out rather than filled in. Compare against the other providers

benchmarks

artificial analysis
Benchmark scores, each normalised to 100
evalScore as a share of 100/100
GPQA Diamond80.0
τ²-Bench67.8
Coding Index37.7
SciCode36.2
Terminal-Bench Hard28.8
Humanity's Last Exam20.8
Intelligence Index13.6
7 evalsmean40.7

Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2026-03-11.

policy

data terms
retention
yes
trains on prompts
yes
hosted in
US

Terms are the provider's, not Requesty's: routing a request here puts it under them. NVIDIA Privacy Policy

Need every request to stay in one jurisdiction? EU hosting routes only through EU-hosted providers.

quickstart

openai compatible
nvidia/nemotron-3-super-120b-a12b

this id pins the nvidia deployment, with no routing and no failover. the managed id on the canonical page routes across all 1 providers instead

main.py
from openai import OpenAI client = OpenAI(    api_key="YOUR_REQUESTY_API_KEY",    base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create(    model="nvidia/nemotron-3-super-120b-a12b",    messages=[        {"role": "user", "content": "Explain quantum computing in one paragraph."},    ],) print(response.choices[0].message.content)

Change the base url to https://router.requesty.ai/v1, use your Requesty key, set the model to the id above. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog. Browse all models

notes

reference

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid Mamba-Transformer MoE model activating just 12B parameters, with multi-token prediction for high throughput. 1M token context for long-horizon agent coherence, cross-document reasoning, and multi-step planning. Strong on AIME 2025, TerminalBench, and SWE-Bench Verified. Part of the NVIDIA Nemotron family.

questions 6

How much does nemotron-3-super-120b-a12b cost?
nemotron-3-super-120b-a12b is priced at free per million input tokens and free per million output tokens when accessed via Requesty. Requesty charges exactly what the upstream provider charges, we don't add markup.
What is the context window of nemotron-3-super-120b-a12b?
nemotron-3-super-120b-a12b has a context window of 1.0M tokens, with a maximum output of 66K tokens per response. That is roughly 1,398 words of input you can fit in a single prompt.
How does nemotron-3-super-120b-a12b perform on benchmarks?
nemotron-3-super-120b-a12b scores 80.0% on GPQA Diamond, 67.8% on τ²-Bench, 37.7% on Coding Index. The benchmarks pane shows every published result, each normalised to 100.
What can nemotron-3-super-120b-a12b do?
nemotron-3-super-120b-a12b supports tool calling, extended reasoning. You can call it through any OpenAI-compatible client by pointing base_url to Requesty.
How do I use nemotron-3-super-120b-a12b with the OpenAI SDK?
Install the OpenAI SDK, set base_url to "https://router.requesty.ai/v1", set your API key to your Requesty key, and set the model to "nvidia/nemotron-3-super-120b-a12b". The quickstart pane shows Python, JavaScript and cURL snippets.
Can I run nemotron-3-super-120b-a12b through Requesty?
Yes. nemotron-3-super-120b-a12b runs through Requesty's OpenAI-compatible API, served from NVIDIA. You do not host the model yourself: point base_url at Requesty, set the model to "nvidia/nemotron-3-super-120b-a12b", and requests are routed to the upstream provider with automatic failover. The same key gives you 600+ other models too.

more from nvidia 6

Other NVIDIA endpoints
endpointctxin /M
nemotron-3.5-lightning-30b-a3b1.0Mfree
muse-glimmer-30b131Kfree
nemotron-3.5-content-safety131Kfree
nemotron-3-nano-omni-30b-a3b-reasoning131Kfree
nemotron-3-ultra-550b-a55b1.0Mfree
nemotron-3-nano-30b-a3b262Kfree

call nemotron-3-super-120b-a12b through one endpoint

One key for this endpoint and 600+ other models. No markup on provider prices, automatic failover when a provider degrades, and prompt caching built in. Methodology

nemotron-3-super-120b-a12bnvidiain free /1Mout free /1Mctx 1.0Mttft 2.55shosted US