Use cases
Each guide shows a workload running on Beam, with the code to deploy it.
Deploy open-source LLMs
Serve open-source LLMs behind an autoscaling, OpenAI-compatible API.
See how it worksTraining & Fine-tuningFine-tune models on GPUs
LoRA and QLoRA fine-tuning on serverless GPUs.
See how it worksInferenceTurn ComfyUI workflows into production APIs
Turn ComfyUI workflows into autoscaling API endpoints.
See how it worksTraining & Fine-tuningRun GPU training jobs on-demand
Start training runs on cloud GPUs from Python and pay only while they run.
See how it worksTask QueuesFan out batch jobs across thousands of containers
Fan out batch inference and ETL across thousands of containers.
See how it worksInferenceRun Stable Diffusion and Flux as an API
Host SDXL, Flux, and custom checkpoints behind an autoscaling API.
See how it worksInferenceDeploy any Hugging Face model as an API
From model ID to live, autoscaling endpoint with one Python file.
See how it worksInferenceRun Whisper transcription behind your own API
On-demand Whisper transcription behind an autoscaling API.
See how it worksInferenceServe embedding models for your RAG stack
Host embedding and reranking models on your own endpoints.
See how it worksInferenceRun text-to-speech behind a managed API
Serve open TTS models with hosted audio outputs.
See how it worksSandboxesGive your AI agents a safe place to run code
Isolated sandboxes for agent-generated code, booting in seconds.
See how it worksAgentsRun coding agents on persistent cloud VMs
Persistent VMs where Claude Code and Codex can build, test, and run.
See how it worksAgentsRun GitHub Actions 2x faster and 5x cheaper
Self-hosted runners on persistent Linux VMs with Docker.
See how it worksAgentsRun computer use agents on persistent Linux desktops
Linux desktops your agents can screenshot, click, and type in.
See how it worksSandboxesSandboxes for parallel RL rollouts
Forkable, restorable sandboxes for reinforcement learning rollouts.
See how it worksBatch ProcessingRun OCR and document extraction at scale
Private OCR and extraction pipelines, one container per document.
See how it worksInferenceDeploy computer vision models at scale
Detection, segmentation, and classification behind managed APIs.
See how it worksInferenceGenerative media on serverless GPUs
Text-to-video on H100s with hosted outputs and no reserved GPUs.
See how it worksGive your agents their own machines
Sign up, install the CLI, and launch a sandbox, VM, or GPU from your terminal or your coding agent.