Nemotron Super 3 120b

NVIDIA
nvidia/nemotron-super-3-120b

Reasoning model, 131K context

Context Window

131K

131,072 tokens

Max Output

16K

16,384 tokens

About this model

NVIDIA Nemotron Super 3 120B, top-tier open model

This model supports up to 131K tokens of context. It excels at complex reasoning, mathematical problems, and multi-step tasks. It provides strong code generation and debugging capabilities.

Access it through Chuizi.AI with a single ck- API key β€” no separate NVIDIA account needed.

Highlights

131K context window
16K max output
Advanced reasoning
Strong code generation

Best For

Complex coding tasksAlgorithm designCode reviewTechnical architecture
2025-09-01

Capabilities

ChatReasoningCode

Aliases

nemotron-super-3-120b

Pricing (per 1M tokens)

Pricing (per 1M tokens)/ 1M tokens
Input / 1M$0.68
Output / 1M$2.63

Final prices shown

Quick Start

main.py
from openai import OpenAI

client = OpenAI(
    base_url="https://api.chuizi.ai/v1",
    api_key="ck-your-key-here",
)

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

FAQ

Related Models

Nemotron Super 3 120b β€” Pricing, Context, Capabilities | Chuizi AI