Home / Inference APIs / Beam

Beam

Open Source Free Trial

Open-source serverless GPU cloud with sub-second cold starts and auto-scaling

Beam is a serverless cloud platform for AI inference, sandboxes, and background jobs. It provides sub-second cold starts via checkpoint restore, auto-scaling to thousands of instances, and persistent sandboxes. Supports Python, Node.js, and arbitrary Docker images with built-in task queues, cron jobs, and web endpoints. Powered by Beta9, an open-source GPU cloud engine that can be self-hosted. A100s and H100s start at around $1.35/hr with per-second billing.

Pricing: Pay-as-you-go

Hosting Cloud + Self-hosted

Pricing Usage Based, from $0.15/hr (T4 GPU)

HQ 🇺🇸 United States

Founded 2021

Visit website →

Suggest changes

Screenshot of Beam webpage

Beam Alternatives

Explore 56 products in the Inference APIs category. View all Beam alternatives.

evroc

European-sovereign cloud and inference APIs running open-source models on NVIDIA Blackwell GPUs in EU data centers

Theta EdgeCloud

Decentralized GPU cloud for AI inference, training, and containerized workloads

Open Source

deepinfra

Run the top AI models using a simple API, pay per use. Low cost, scalable and production ready infrastructure.

Free Trial From $0.02/M tokens

Cerebras

Ultra-fast inference on custom wafer-scale hardware with OpenAI-compatible API

Free Trial From Free tier available

Airon

Dedicated bare-metal GPU infrastructure for AI workloads, hosted in Nordic datacenters

From $1.24/hour

AiQu

Swedish GPU infrastructure and LLM hosting platform with API-first deployment, no Kubernetes required

Free Trial From 49 SEK/month

View all Inference APIs tools ≫

Is your product missing?

Add it here →