Skip to main content
Train a model using reinforcement learning on Prime Intellect’s infrastructure — no GPUs to manage.

​
Prerequisites

​
1. Install the CLI and log in

# install uv (if not already installed)
curl -LsSf https://astral.sh/uv/install.sh | sh
# install the prime CLI
uv tool install -U prime
# log in
prime login

​
2. Set up your workspace

# ~/dev/my-lab
prime lab setup
This sets up your workspace with AGENTS.md, environments, and example training configs in configs/lab/.

​
3. Launch training

Pick one of the example configs and run it: 
prime rl run configs/lab/alphabet-sort.toml
That’s it. Prime Intellect handles the GPU cluster, rollouts, and optimization. You’ll get a dashboard link in the output. You can also launch your coding agent (Claude, Cursor, OpenCode, etc.) and use it to manage your workspace and research workflows.

​
4. Monitor progress

Terminal: 
prime rl logs <run-id> -f
Dashboard: Open the link from the previous step to see reward curves, rubric scores, and individual rollouts in real time.

​
Next steps

End-to-End Run

Detailed walkthrough with baseline evals, model selection, and result review.

Advanced Configs

Multi-environment training, online evals, difficulty filtering, and W&B integration.

Models & Pricing

Supported models and pricing details.

What is Lab?

Understand the full platform and how everything fits together.