Getting Started

Train a model with reinforcement learning on Prime Intellect’s infrastructure — no GPUs to manage, no cluster to reserve.

On-demand training is in beta. Request access before your first run, or dispatch will be refused.

Pick your path

	What it is	Access
Hosted Training	You submit a config, we run it on GPUs we operate, billed per GPU-hour.	Beta, request access
Model Factory Clusters	A dedicated cluster running training, inference, Slurm and Kubernetes side by side. Use this when you need control over the stack.	Contact us
prime-rl	The open-source training framework, running on your own hardware.	Self-hosted

Hosted Training is the fastest way to start, and the rest of this page covers it.

Prerequisites

Python 3.10+
A Prime Intellect account with on-demand training enabled and a funded wallet, see Billing

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. See what you can run

prime train models

This lists the models available to dispatch and an On-Demand Capacity table of purchasable GPU types with their current $/GPU-hour. Models on that list are already cached cluster-side and start warm. An on-demand run can still train a model that is not listed, it just downloads the weights first.

3. Create a volume to keep your weights

Checkpointing is off by default, and when a run finishes its pods are torn down. Without a volume and a [ckpt] block, a completed run leaves you with dashboard metrics and no model.

prime volumes create research --size 100Gi
prime volumes list   # wait for RUNNING before dispatching

Trace storage

Before launching, review Prime Traces pricing and upload settings. Traces uploaded by platform runs incur ingestion and storage charges. Stored traces can be explored in the Traces dashboard. The November 6 legacy sample storage retirement is separate from the retirement of shared LoRA training.

4. Launch a run

Training runs are configured with a prime-rl .toml file. The [deployment] block sizes the run and is what routes it onto Hosted Training. Save this as configs/full-ft.toml — one trainer GPU and one inference GPU:

name = "reverse-text-full-ft"
max_steps = 100
seq_len = 2048

[ckpt]                                              # save a checkpoint at the end of training

[model]
name = "PrimeIntellect/Qwen3-0.6B-Reverse-Text-SFT"

[deployment]
num_train_gpus = 1
num_infer_gpus = 1

[trainer.optim]
lr = 3e-6

[orchestrator]
batch_size = 64
group_size = 8

[orchestrator.train.sampling]
max_completion_tokens = 512

[[orchestrator.train.source]]
name = "reverse-text"

[orchestrator.train.source.env.taskset]
id = "reverse-text"

[orchestrator.train.source.env.agent.harness]
id = "null"

[orchestrator.train.source.env.agent.runtime]
type = "subprocess"

[orchestrator.renderer]
name = "prime-qwen3"

[inference]

Dispatch it against the volume:

prime train configs/full-ft.toml --volume research

The CLI echoes the GPU type and hourly rate it resolved, then prints a run ID and dashboard link.

5. Monitor progress

Terminal:

prime train logs <run-id> -f

Dashboard: open the link from the previous step for reward curves, rubric scores, and individual rollouts in real time. Stop a run early to release its GPUs and stop the meter:

prime train stop <run-id>

6. Get your weights

Each run writes to its own runs/<run-id>/ directory on the volume:

prime volumes ssh research                  # browse what the run wrote
prime volumes get research runs/<run-id> .  # copy it down

Checkpoints are DCP-sharded and need converting before anything else can load them — see Export to HF format.

Next steps

End-to-End Run

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

Full Fine-Tuning

Config reference, dispatch knobs, and run lifecycle.

Billing

How runs are metered and what gets billed.

Platform Overview

How environments, training, evaluation, and inference fit together.

Inference

Model Factory

Community

Compute

Traces

Libraries

Getting Started

Pick your path

Prerequisites

1. Install the CLI and log in

2. See what you can run

3. Create a volume to keep your weights

Trace storage

4. Launch a run

5. Monitor progress

6. Get your weights

Next steps

End-to-End Run

Full Fine-Tuning

Billing

Platform Overview

​Pick your path

​Prerequisites

​1. Install the CLI and log in

​2. See what you can run

​3. Create a volume to keep your weights

​Trace storage

​4. Launch a run

​5. Monitor progress

​6. Get your weights

​Next steps

End-to-End Run

Full Fine-Tuning

Billing

Platform Overview

Pick your path

Prerequisites

1. Install the CLI and log in

2. See what you can run

3. Create a volume to keep your weights

Trace storage

4. Launch a run

5. Monitor progress

6. Get your weights

Next steps