Verifiers
A library of modular components for creating RL environments and training LLM agents.
RESEARCH
Frontier Research
Run large-scale reinforcement learning experiments on open infrastructure, from pretraining to post-training and evaluation.
FIG. 01 / SPIN-UP
Minutes
To launch a multi-node run
FIG. 02 / ENVIRONMENTS
2,500+
Open-source RL environments
FIG. 03 / REPRODUCIBILITY
100%
Declarative, versioned experiments
Environment Hub
Access and contribute to 2,500+ open-source RL environments and a community of researchers and developers.
Request trainingFrontier research shouldn’t be gated by closed clusters. Spin up multi-node training runs in minutes, checkpoint across regions, and reproduce results with environment definitions that live alongside your code.
From supervised fine-tuning to large-scale RL, the same stack — Verifiers, Prime-RL, and Sandboxes — covers the full post-training loop.
Every experiment is declarative: environments, reward functions, and evaluation suites are versioned artifacts you can share, fork, and cite.
Platform
Everything this solution needs. None of the overhead.
1
Multi-Node in Minutes
Launch distributed runs on InfiniBand-connected clusters with SLURM or Kubernetes.
2
Cross-Region Checkpoints
Checkpoint and resume anywhere, without babysitting storage or networking.
3
Versioned Artifacts
Environments, rewards and eval suites are artifacts you can share, fork and cite.
4
Full Post-Training Loop
SFT through large-scale RL and evaluation on one consistent stack.
PI is the closed-loop AI stack where models observe their own failures, generate new training signal, and improve — without you writing a single reward function.
Deploying with
At industry standards
FIG. 01 / EFFICIENCY
3.2×
Avg. improvement per cycle
FIG. 02 / VELOCITY
48 h
First improvement deployed
FIG. 03 / SCALE
100B+
Parameters on-stack
FIG. 04 / LABOR
0
Reward functions written
Self-generating eval suites
Auto-instrumented agents
RL across 2,500+ environments
Serverless model inference
Real-time training observability
Production data flywheel
[ What teams say ]
"We used to spend two weeks curating evals. PI generates better evals from failures in two hours. We just don't think about reward engineering anymore."
2 wks → 2 hEval curation time
Compute. Find reliable compute operated globally from a single GPU to largest clusters.
On demand
Instant access to 1-256 GPUs. Use your GPUs across clouds in a single platform.
- 1.1
SLURM, K8s Orchestration
Orchestrate dynamic workloads with enterprise-grade scheduling and container automation.
- 1.2
Infiniband Networking
Scale distributed training with high-bandwidth interconnects across nodes.
- 1.3
Grafana Monitoring Dashboards
Visualize metrics in real time with customizable dashboards for full system observability.
Liquid Reserved Clusters
Request large-scale clusters from 50+ providers. Sell-back idle GPUs to our spot market.
- 2.1
Get quotes from 50+ datacenters within 24 hours
One request, parallel bids for options, from H100, H200, to B200, B300, GB300 NVL72
- 2.2
Re-sell idle GPUs back to our spot market
Resell idle nodes on our spot market with no manual ops. Reclaim capacity instantly when you need it.
- 2.3
Direct assistance from our research and infra engineering team
Dedicated solutions engineer from cluster bring-up through steady-state
[ Ready? ]
Your model should get smarter while you sleep.
Engineers, at full stride. Point PI at your checkpoint — first improvement in about 48 hours.