BazaarLinkBazaarLink
Sign in

Nemotron 3 Super 120b A12b API Pricing & Quick Start

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

Intelligence#177 / 573
25
Artificial Analysis Intelligence Index
Speed#45 / 586
152.4
Output tokens per second (median)
Input Price#311 / 586
$0.30NT$ 10
USD / 1M tokens
Output Price#308 / 586
$0.90NT$ 29
USD / 1M tokens
First-token latency#485 / 586
0.97s
Time to first token (AA median)
ProviderNVIDIA
ReleasedMarch 2026
Model IDnvidia/nemotron-3-super-120b-a12b

Technical specifications

Context window
1M tokens
Reasoning
Yes
Input
Text
Output
Text

Pricing comparison

BazaarLink retail price alongside AA's observed market standard.

BazaarLink price our site

Input$0.30NT$ 10
Output$0.90NT$ 29
Cache read$0.06NT$ 2
Cache write
3:1 blended (est.)$0.45NT$ 15
All prices per 1M tokens. Supports TWD credit card / official invoice.

Market reference Artificial Analysis

Input$0.25
Output$0.78
Cache readAA not tracked
Cache writeAA not tracked
3:1 blended$0.38
Our price differs from AA reference by ~20%.
Source: artificialanalysis.ai

Independent benchmarks

Scores below come from Artificial Analysis, an independent third party. BazaarLink does not participate in the testing.

Intelligence 25
Coding 38
Math
MMLU
GPQA 80
This modelCategory leader
Coding ability
#97out of 198 models
LiveCodeBench / SciCode and similar
Overall intelligence
#177out of 573 models
Aggregated across academic benchmarks
Time to first token
#485out of 586 models
AA 全球 p50:0.97 秒
Intelligence
25
Mid-tier
This model
25
Category leader
61
Median
15
Coding
38
Mid-tier
This model
38
Category leader
78
Median
37
GPQA
80%
This model
80%
Category leader
94%
Median
69%
HLE
19%
This model
19%
Category leader
53%
Median
7%
SciCode
36%
This model
36%
Category leader
60%
Median
33%
IFBench
71%
This model
71%
Category leader
83%
Median
44%
τ²-Bench Telecom
68%
This model
68%
Category leader
99%
Median
46%
AA-LCR
60%
This model
60%
Category leader
76%
Median
40%
Terminal-Bench Hard
29%
This model
29%
Category leader
66%
Median
14%

Top 5 — CodingCoding Index leaderboard

1GPT-5.6 Sol (xhigh)openai/gpt-5-6-sol-xhigh78$5 / $30
4GPT-5.6 Sol (high)openai/gpt-5-6-sol-high77$5 / $30
5Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)anthropic/claude-opus-5-xhigh77$5 / $25
AASource: Artificial Analysis · Independent third-party evaluation; not influenced by BazaarLinkView full evaluation on AA →

Quick Start

Use Nemotron 3 Super 120b A12b via BazaarLink API — just change the base_url:

Python
from openai import OpenAI

client = OpenAI(
    base_url="https://bazaarlink.ai/api/v1",
    api_key="sk-bl-YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="nvidia/nemotron-3-super-120b-a12b",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
TypeScript
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://bazaarlink.ai/api/v1",
  apiKey: "sk-bl-YOUR_API_KEY",
});

const response = await client.chat.completions.create({
  model: "nvidia/nemotron-3-super-120b-a12b",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Why use Nemotron 3 Super 120b A12b via BazaarLink?

  • USD billing (TWD-quoted) + unified invoices — no foreign credit card needed for Taiwan teams
  • OpenAI-compatible API — zero code changes required
  • Automatic failover — multi-provider redundancy for the same model
  • Chinese-language support — local team, instant help
Try Now← All Models

Frequently Asked Questions

What is Nemotron 3 Super 120b A12b?

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

How much does the Nemotron 3 Super 120b A12b API cost?

Nemotron 3 Super 120b A12b costs $0.3000 per 1M input tokens and $0.9000 per 1M output tokens when accessed through BazaarLink.

How do I use Nemotron 3 Super 120b A12b with the OpenAI SDK?

Set base_url to "https://bazaarlink.ai/api/v1" and use model ID "nvidia/nemotron-3-super-120b-a12b". All OpenAI SDK methods (chat.completions, embeddings, streaming) work without code changes.

What is the context window for Nemotron 3 Super 120b A12b?

Nemotron 3 Super 120b A12b supports a context window of 1,000,000 tokens.

Is Nemotron 3 Super 120b A12b available for free?

Nemotron 3 Super 120b A12b is a paid model. BazaarLink offers free trial credits on registration so you can test it without a credit card.

Relay integrity checks

No integrity-check data is available for this model yet.

BazaarLink Probe verifies endpoints that claim to serve this model and flags behavior that differs from the reference baseline.

View the full integrity report →

Related models and links

More from this provider: NVIDIA

Nemotron 3 Nano 30b A3bGlm 4.7Glm 5Glm 5.2Deepseek V3.2Deepseek V4 Pro
ModelsAPI documentationAPI latency probe
Support
Support
Hi! How can we help you?
Send a message and we'll get back to you soon.