Introducing Lab: A full-stack platform for training your own agentic models Build, evaluate and train on your own environments at scale without managing the underlying infrastructure. Giving everyone their own frontier AI lab.

We are not inspired by a future where a few labs control the intelligence layer So we built a platform to give everyone access to the tools of the frontier lab If you are an AI company, you can now be your own AI lab If you are an AI engineer, you can now be an AI researcher

Lab unifies everything you need for post-training research into one platform + Environments Hub + Hosted Evaluations + Hosted Training + Deployments & Inference Without needing to worry about the costs of massive GPU clusters or the headaches of low-level algorithm details

Lab is built around environments, which include: + A dataset of tasks + A harness for the model + A rubric to score performance Use environments to train models with RL, evaluate capabilities, generate synthetic data, optimize prompts, experiment with agent harnesses and more.

Just run `prime lab setup` and start your coding agent to set up your own AI lab.

Hosted Training Create your environment, configure your training run, and we handle the rest. No worrying about managing infrastructure, GPUs, or low-level algorithms. We’re launching with agentic RL, and adding support for SFT and other algorithms in the near future.

Hosted Evaluations + Run evals using our hosted inference, sandboxes, and more + Visualize results and raw outputs + Share results on the Environments Hub

Beyond our own INTELLECT-3 model, Lab lets you run reinforcement learning on a wide range of open models. From Nvidia, Arcee, Hugging Face, Allen AI, Z AI, Qwen, and many more launching soon. We’re also launching with experimental multimodality support.

Deployments & Inference Large-scale production deployments of your fine-tuned models on shared hardware Built to evolve towards a future of continual learning, where models learn in production as training and inference collapse into a single loop.

Infrastructure Lab is built on the same stack we used to train INTELLECT-3. Each run gets a dedicated orchestrator, with multi-tenant LoRA for training and inference. Enabling shared hardware across runs, high efficiency, per-token pricing.

Over the past few weeks in private beta, more than 3,000 RL runs were completed by individuals and companies from around the world. Starting today, we’re opening it up to everyone.

Get started with your first training run

Blog

holy shit what a name

I like having something comprehensive for this - instead of getting another fine-tuning API. Prime really cookin' here - and try out their tool, it's fine!

And we're just getting started! 😉

insane

man the aesthetic is peak, 2001 lfg

This is really cool! It wasn't clear to me from the summary, does this support sandboxed code execution environments at scale?

waow

love the branding!

Love this - congrats guys :)

it’s been a blast using this, super super excited for the launch!

Incredible!

@willcb @willcb congrats on the launch!

congrats on the launch!

hey babe, new prime intellect lab just dropped

sickkk!! congrats on the launch ⚡️

Amazing work, well done team & congrats on the launch!

hell yeah

thank you for building, this is exactly what i needed

this video is so fucking sick wow

and we are out of Beta! congratulations! 🎉

Many environments => curriculum learning => de wae

Amazing work! This is incredible

great name

open thinky

Super cool!

pretty crazy cool stuff

can u guys have max plans now

congrats!!! 🦋

Congratulations guys 🥳

Let’s goooo 🔥🔥🔥

Let's goooooooo

Prime W

Ayyyyy new models!

So sick another prime W