Moduck

Nvidia: Nemotron 3 Super 120B A12B

Nemotron middle tier for collaborative agents and high-volume reasoning workloads

Model lab
Nvidia
Model family
nemotron
Modalitiestext → text
Context window262,144
Maximum output262,144
InputUSD 0.096 / 1M tokens
OutputUSD 0.416 / 1M tokens

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to moduck/nvidia/nemotron-3-super-120b-a12b.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "moduck/nvidia/nemotron-3-super-120b-a12b"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Nemotron 3 Super 120B A12B API Pricing

TypePrice information
InputUSD 0.096 / 1M tokens
OutputUSD 0.416 / 1M tokens
Cached inputUSD 0.048 / 1M tokens

Benchmarks

Reasoning

Intelligence Index · v4.312.8
Coding Index37.7
Agentic Index1.7

Performance

Measured on the Moduck gateway across live traffic, hour by hour over the last 24 hours. Time to first token is how long before anything appears; throughput is how fast the answer is written after that; end-to-end latency is the whole round trip. Figures are medians unless the card says otherwise.

Artificial Analysis measurement · Reasoning

Output speed146.29 tokens/s
Time to first token1.3 s
Time to first answer token—
End-to-end response time—
Measurement variantOutput speedTime to first tokenTime to first answer tokenEnd-to-end response time
Reasoning146.29 tokens/s1.3 s——

Performance trends

Throughput146.29 tok/sCurrent
Time to first token1.3 sCurrent
End-to-end latency7.9 sCurrent
Throughput
Current146.29 tok/s
Window average150.1 tok/s
Time to first token
Current1.3 s
Window average1.5 s
End-to-end latency
Current7.9 s
Window average7.5 s
Tail latency (P99)
Current16.6 s
Window average16.9 s
Prompt cache hit rate
Current18.2%
Window average24.6%
Error rate
Current0.0%
Window average0.1%

Availability

Uptime is the share of time at least one provider serving this model responded. Availability is stricter: the share of requests actually served. A provider that answers but fails part of the traffic lowers availability without lowering uptime. Both cover the last three days.

Uptime100%At least one provider responded
Availability100%Requests actually served
Error rate0%Share of failed requests
Served requests, hour by hour
24 hours agoNow

Nemotron 3 Super 120B A12B Compare models

ModelInput priceOutput priceContext windowCapabilities
Nemotron 3 Super 120B A12BThis pageUSD 0.096 / 1M tokensUSD 0.416 / 1M tokens262,144Text output · Reasoning · Tool calling
Nemotron 3.5 Lightning 30B A3BUSD 0.04 / 1M tokensUSD 0.16 / 1M tokens262,144Text output · Reasoning · Tool calling
Nemotron 3 Ultra 550B A55BUSD 0.4 / 1M tokensUSD 1.76 / 1M tokens1,000,000Text output · Reasoning · Tool calling
Nemotron 3 Nano 30B A3BUSD 0.04 / 1M tokensUSD 0.16 / 1M tokens262,144Text output · Reasoning · Tool calling
Nemotron Nano 9B v2USD 0.048 / 1M tokensUSD 0.184 / 1M tokens131,072Text output · Reasoning · Tool calling

Model specifications

Input
text
Output
text
Context window
262,144
Maximum output
262,144
Release date
2026-03-11
Attachments
No
Reasoning
Yes
Tool calling
Yes
Temperature setting
Yes
Open weights
Yes

Frequently asked questions

What is Nemotron 3 Super 120B A12B for?

Nemotron middle tier for collaborative agents and high-volume reasoning workloads

What inputs and outputs does Nemotron 3 Super 120B A12B support?

Recorded inputs: text; outputs: text.

How is Nemotron 3 Super 120B A12B priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.096 / 1M tokens; Output USD 0.416 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Nemotron 3 Super 120B A12B?

Current model records list Context window 262,144 tokens; Maximum output 262,144 tokens.

What model parameter does the Quickstart use?

The example uses moduck/nvidia/nemotron-3-super-120b-a12b. This is a cataloged Moduck public or reserved ID; check your account’s available models before calling it.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.