Free · 5-minute setup

Run Nemotron 3 Ultra in your terminal

NVIDIA's 550B open reasoning model, wired into OpenCode as your coding agent. No GPU. No subscription. Copy, paste, done.

550B / 55B active 1M context Free API Mac + Windows
Pick your machine — the whole guide updates

First, the thing nobody tells you

You are not downloading a 550B model onto your laptop. That would need roughly 4× B200 GPUs. What actually happens: NVIDIA hosts the model and gives you free API access, and you install a small terminal app called OpenCode that talks to it.

So: OpenCode lives on your machine. Nemotron lives on NVIDIA's servers. Your API key connects the two.

01

Install OpenCode

Open Terminal (Cmd + Space → type "Terminal") and paste this:

Terminal
curl -fsSL https://opencode.ai/install | bash

Takes about 30 seconds. You'll see a progress bar and a green OpenCode logo when it's done.

Windows has no one-line curl installer. Pick one of these three. Easiest first:

Option A — winget (built into Windows 11 and updated Windows 10). Open PowerShell from the Start menu:

PowerShell
winget install SST.opencode

Option B — npm. Install Node.js first (LTS version, next-next-finish), then reopen PowerShell:

PowerShell
npm install -g opencode-ai@latest

Option C — Scoop, if you already use it:

PowerShell
scoop bucket add extras
scoop install extras/opencode

Use Windows Terminal, not the old black Command Prompt

OpenCode's interface needs proper colour support. Windows Terminal ships with Windows 11 and is a free install from the Microsoft Store on Windows 10. PowerShell inside Windows Terminal is the setup that behaves.

02

Check it installed

The installer usually prints "No config file found for zsh". That means your Mac doesn't know where OpenCode lives yet. Paste both lines:

Terminal
echo 'export PATH=$HOME/.opencode/bin:$PATH' >> ~/.zshrc
source ~/.zshrc

Then confirm:

Terminal
opencode --version

A version number means you're good. command not found means the PATH line didn't save — quit Terminal, reopen, try again.

Close PowerShell and open a new window first. Windows only picks up new commands in a fresh terminal — this single step fixes most "it didn't work" messages. Then:

PowerShell
opencode --version

A version number means you're set.

"opencode is not recognized"

Reopen PowerShell once more — installers add to PATH only for new sessions. Still nothing? Restart the PC, or reinstall using Option B (npm), which registers the command more reliably.

"running scripts is disabled on this system"

PowerShell's default script policy. Run this once, then reopen PowerShell:

PowerShell
Set-ExecutionPolicy -Scope CurrentUser RemoteSigned
03

Get your free NVIDIA API key

Same on both platforms — and this is where most people get stuck, so read this bit properly.

"No API Key Permissions" — you're in the wrong org

If the page says you can't create keys, you're signed into a company or SSO organisation where an admin controls keys. Click the green Switch Org button and pick your personal org (usually your own name or "Default"). If nothing usable shows up, sign out and create a fresh account with a personal email.

OTP arrived on your phone but there's no box to type it

The code goes into the same browser tab where you started signing in — nothing gets typed into a terminal.

  • NVIDIA often opens login in a separate window. Check behind your main browser window.
  • Don't refresh or hit back — that invalidates the code and you'll need a new one.
  • The field may just say "Verification code" or show six empty boxes.
  • If nothing opened at all, allow pop-ups for nvidia.com and retry.

Don't use the temporary key

The "Get API Key" button on a model page gives a testing key that expires in a few hours. Fine for a demo, useless the next morning. Generate a proper one from the API Keys page.

04

Connect NVIDIA to OpenCode

Move into any project folder and launch OpenCode:

Terminal
cd ~/Desktop/my-project
opencode
PowerShell
cd $HOME\Desktop\my-project
opencode

Quick trick: open the folder in File Explorer, right-click empty space, choose Open in Terminal. No typing paths.

Inside the OpenCode screen, type:

Inside OpenCode
/connect

Choose NVIDIA from the list, paste your nvapi- key, press Enter. The key is stored locally — you only do this once.

05

Select Nemotron 3 Ultra

Still inside OpenCode:

Inside OpenCode
/models

Type nemotron to filter, then pick Nemotron 3 Ultra 550B A55B and hit Enter. Or set it directly:

Inside OpenCode
/model nvidia/nemotron-3-ultra-550b-a55b

Now just talk to it. Try: "read this folder and explain what the project does". It reads files, writes code, runs commands and fixes its own errors.

06

Prefer Python? Skip OpenCode entirely

If you just want the model inside your own script, the API is OpenAI-compatible. Save your key as an environment variable first:

Terminal
echo 'export NVIDIA_API_KEY="nvapi-your-key-here"' >> ~/.zshrc
source ~/.zshrc
pip install openai
PowerShell
setx NVIDIA_API_KEY "nvapi-your-key-here"
pip install openai

setx saves it permanently, but only new terminals see it — close PowerShell and reopen before running your script.

Python
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://integrate.api.nvidia.com/v1",
    api_key=os.environ["NVIDIA_API_KEY"],
)

stream = client.chat.completions.create(
    model="nvidia/nemotron-3-ultra-550b-a55b",
    messages=[{"role": "user", "content": "Write a Python script that renames every file in a folder to lowercase."}],
    temperature=1,
    top_p=0.95,
    max_tokens=16384,
    extra_body={"chat_template_kwargs": {"enable_thinking": True}},
    stream=True,
)

for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")
07

When something breaks

What you seeWhat to do
command not found: opencodePATH line didn't save. Redo Step 02, then quit and reopen Terminal.
'opencode' is not recognizedOpen a brand-new PowerShell window. Still failing? Restart, or reinstall via npm.
running scripts is disabledRun Set-ExecutionPolicy -Scope CurrentUser RemoteSigned, then reopen PowerShell.
npm not recognizedNode.js isn't installed, or you didn't reopen the terminal after installing it.
EPERM / permission errorsTurn on Developer Mode in Windows Settings, or run PowerShell as administrator once for the install.
401 / UnauthorizedKey is wrong, expired, or has a stray space. Generate a fresh one from the API Keys page.
No API Key PermissionsWrong organisation. Hit Switch Org, or sign up again with a personal email.
Nemotron not in /models listProvider isn't connected. Run /connect again and pick NVIDIA.
Rate limited / 429Free tier throttle. Wait a minute, or switch to Nemotron 3 Super for lighter tasks.
Replies feel slowIt's a reasoning model — it thinks before answering. Long tasks are where it earns its keep.
08

What you're actually working with

Parameters
550B
55B active per token
Context
1M
tokens
Architecture
Hybrid
Mamba-Transformer MoE
Cost
Free
via NVIDIA's API

Built for long-running agent work — planning, coding, tool calling, debugging across big codebases. It's the strongest open model out of a US lab, though not the highest-scoring open model overall. Worth knowing before you argue about it in the comments.