Nvidia: Nemotron Cascade 2 30B A3B

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to nvidia/nemotron-cascade-2-30b-a3b.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "nvidia/nemotron-cascade-2-30b-a3b"

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 Cascade 2 30B A3B API Pricing

Benchmarks

Performance

Availability

Nemotron Cascade 2 30B A3B Compare models

Model specifications

Input

text

Output

text

Context window

256,000

Maximum output

32,768

Release date

2026-03-24

Attachments

No

Reasoning

Yes

Tool calling

Yes

Temperature setting

Yes

Open weights

Yes

Frequently asked questions

Related models

Nemotron 3.5 Lightning 30B A3BNvidiaInputUSD 0.04 / 1M tokensOutputUSD 0.16 / 1M tokensView modelNemotron 3 Ultra 550B A55BNvidiaInputUSD 0.4 / 1M tokensOutputUSD 1.76 / 1M tokensView modelNemotron 3 Super 120B A12BNvidiaInputUSD 0.096 / 1M tokensOutputUSD 0.416 / 1M tokensView model