Persistent VMs are now available.Learn more

Use cases

Each guide shows a workload running on Beam, with the code to deploy it.

Inference

Deploy open-source LLMs

Serve open-source LLMs behind an autoscaling, OpenAI-compatible API.

See how it works
Training & Fine-tuning

Fine-tune models on GPUs

LoRA and QLoRA fine-tuning on serverless GPUs.

See how it works
Inference

Turn ComfyUI workflows into production APIs

Turn ComfyUI workflows into autoscaling API endpoints.

See how it works
Training & Fine-tuning

Run GPU training jobs on-demand

Start training runs on cloud GPUs from Python and pay only while they run.

See how it works
Task Queues

Fan out batch jobs across thousands of containers

Fan out batch inference and ETL across thousands of containers.

See how it works
Inference

Run Stable Diffusion and Flux as an API

Host SDXL, Flux, and custom checkpoints behind an autoscaling API.

See how it works
Inference

Deploy any Hugging Face model as an API

From model ID to live, autoscaling endpoint with one Python file.

See how it works
Inference

Run Whisper transcription behind your own API

On-demand Whisper transcription behind an autoscaling API.

See how it works
Inference

Serve embedding models for your RAG stack

Host embedding and reranking models on your own endpoints.

See how it works
Inference

Run text-to-speech behind a managed API

Serve open TTS models with hosted audio outputs.

See how it works
Sandboxes

Give your AI agents a safe place to run code

Isolated sandboxes for agent-generated code, booting in seconds.

See how it works
Agents

Run coding agents on persistent cloud VMs

Persistent VMs where Claude Code and Codex can build, test, and run.

See how it works
Agents

Run GitHub Actions 2x faster and 5x cheaper

Self-hosted runners on persistent Linux VMs with Docker.

See how it works
Agents

Run computer use agents on persistent Linux desktops

Linux desktops your agents can screenshot, click, and type in.

See how it works
Sandboxes

Sandboxes for parallel RL rollouts

Forkable, restorable sandboxes for reinforcement learning rollouts.

See how it works
Batch Processing

Run OCR and document extraction at scale

Private OCR and extraction pipelines, one container per document.

See how it works
Inference

Deploy computer vision models at scale

Detection, segmentation, and classification behind managed APIs.

See how it works
Inference

Generative media on serverless GPUs

Text-to-video on H100s with hosted outputs and no reserved GPUs.

See how it works
Pay as you go
billed by the second

Give your agents their own machines

Sign up, install the CLI, and launch a sandbox, VM, or GPU from your terminal or your coding agent.