Compute for agents
Beam sources bare-metal servers around the world and turns them into VMs, sandboxes, task queues, functions and endpoints. Cheap machines for background jobs, big ones for builds, GPUs when you need them, and only pay while your code is running.
curl -fsSL https://www.beam.cloud/install | shWe buy hardware in bulk and pass along the savings: VMs from $0.0306 per hour, H100s from $1.83 per hour, your first 1 TB of storage included, and no egress fees.
Beam powers agents and AI products at:
“Beam is powering hands-down the best developer experience to run models on GPUs easily at scale. Best decision on the infra side for us this year so far.”
– Louis Morgner, Co-founder @ Jamie
Sandboxes are isolated computers for untrusted code, like LLM outputs and agent tool calls. Each sandbox starts in about half a second with its own filesystem and networking. It can be paused, snapshotted, and restored.
Run one or thousands. Expose a port to get a preview URL, or attach a GPU when you need one.
2 vCPU and 8 GiB for $0.319 per hour, billed by the millisecond.
from beam import Sandbox
sb = Sandbox(cpu=2, memory="8Gi").create()
print(sb.process.run_code("print(2 + 2)").result)
url = sb.expose_port(3000)Pricing
Billed by the second. You don't pay anything when a VM is paused, and there are no minimum commitments or egress fees.
USD, billed by usage
- Whole GPU machines from $0.44 per hour, and 8-GPU clusters with InfiniBand by quote. See GPU prices.
- Volumes are free up to 1 TB, then $0.021 per GB-month.
- Running a lot of compute? Talk to us about volume pricing, or bring your own cloud.
Speed
Agents spend more time waiting for machines than running on them, so Beam keeps the wait short. We virtualize CPUs and GPUs directly on bare metal, with fast local NVMe disks next to the compute.
- Sandboxes start in about half a second, and memory snapshots let new ones start with processes already running.
- VMs resume with RAM and running processes intact in about a second.
- Set an idle timeout, and paused VMs wake when a request arrives.
- Serverless apps keep containers warm for as long as you set with
keep_warm_seconds, then scale to zero.
“Beam is amazing. I tested the CLI and in 5 minutes had something running on the cloud.”
– Leonardo Cuco, CTO @ Ween.ai