๐ŸŽ New: $25 in Token Factory credits + $25 in Tavily credits for new accounts โ€” claim yours
NemoCode.org
Powered by Nebius Token Factoryยทopen models

Nemotron for Claude

A local relay that connects Claude Code, Codex, OpenCode, and Pi Code to NVIDIA Nemotron and other open models on Nebius Token Factory โ€” with live Tavily web search, short commands, and zero edits to your real tool config.

install.sh
$curl -fsSL https://nemocode.org/install.sh | sh

macOS & Linux ยท installs Bun if needed ยท stays up to date (auto-updating)

claude
codex
opencode
pi
SOC 2-compliant data centersZero data retention supported
The model

What is Nemotron?

Nemotron is NVIDIA's family of open-weight models tuned for reasoning, tool use, and agentic coding, with a reasoning mode you can turn on per turn. Alongside it, Cosmos Reason adds vision โ€” so image-heavy work has somewhere to go even when your primary model is text-only. Through Nebius Token Factory every token is served from SOC 2-compliant data centers, with zero data retention supported.

Toggleable reasoning

Nemotron reasons on demand, so trivial turns stay fast and hard ones go deep.

Built for tool use

Tuned for agentic tool calling and long-horizon software engineering workflows.

Cosmos 3 for vision

Cosmos 3 handles screenshots, diagrams, and spatial layouts for text-only models.

Open weights

Nemotron and Cosmos ship open weights, so you are never locked to a single provider.

More detail on the official Nemotron model card and Artificial Analysis.

Supported harnesses

The coding agents you already use, on open models.

100% supported

Claude Code

claudemo

Routes Claude Code through a local Anthropic-to-Nebius translation proxy. Your subscription, login, and config stay untouched.

100% supported

Codex CLI

codemo

Talks to Nebius through a local Responses-to-chat proxy, with headless exec support. Sessions stay resumable across providers.

100% supported

OpenCode

opencodemo

Launches with Nebius wired in as an OpenAI-compatible provider, injected only for that run. Close it and your setup is exactly as it was.

100% supported

Pi Code

pimo

Starts with a custom Nebius provider and a temporary config directory, while normal local session history keeps persisting.

Start relaying

Three commands from zero to running.

  1. 1

    Install once

    Run the one-liner. It drops nemocode plus claudemo, codemo, opencodemo, and pimo onto your PATH and installs Bun if you don't have it.

  2. 2

    Add your keys

    On first run, nemo configure asks for your Nebius Token Factory key and an optional Tavily key for live web search.

  3. 3

    Launch an agent

    Type claudemo or codemo and keep working. The Relay injects Nebius settings for that run only. Nothing is written to your real agent config.

One key.
Every agent.

One Nebius Token Factory key powers all four agents through a single local proxy. The model list is pulled live from Nebius, so every model they serve is one command away. Add an optional Tavily key and every agent gets live web search with real citations.

Nemotron 3 UltraCosmos 3Qwen 3.5DeepSeek V4MiniMax M3
Get a Token Factory key
Why route through the Relay

One relay, four harnesses

Claude Code, Codex, OpenCode, and Pi Code all run on Nebius open models through a single local install.

Live web search, built in

The proxy emulates native web_search with Tavily and streams real Anthropic citation blocks straight into your agent.

Cost tracking per session

Every turn is metered against the model's real per-token rates and printed as a running total when you exit.

Config-free & self-updating

Nothing rewrites your agent config files. The installed binary keeps itself current from the release site.

Limited-time promo

Start with $25 + $25 in free credits

The Nebius builders program gives new accounts $25 in Token Factory credits and $25 in Tavily credits โ€” millions of Nemotron tokens plus the live web search the relay runs on Tavily.

Claim your free credits

Add Nemotron to your agents in one line.

Free to install, config-free, and reversible. Your subscriptions and logins stay exactly where they are.