Beam Serverless GPU
Serverless GPU endpoints that turn a Python function into a model-serving endpoint on RTX 4090 and RTX 5090 GPUs that start when a request arrives and stop after traffic stops, billed by the millisecond.
Find alternatives to Beam Serverless GPU
What it does
- Model hosting
- GPU cloud
Sources
- Pricing
-
Pricing page text fetched 2026-11-16 with curl; page quote: "RTX 4090 PCIE 24 GB VRAM".
- Description
-
Company disclosure · 16 Nov 2026
Product page text fetched 2026-11-16 with curl; page quote: "Run your model on RTX 4090 and RTX 5090 GPUs that start when a request arrives and shut down after traffic stops.". The page says "GPU time starts at $0.69 /hr, metered by the millisecond"; the separate /inference page ("Serverless inference for any model") describes the same endpoint product, so it is not a second row.
- What it does
-
Company disclosure · 16 Nov 2026
Product page text fetched 2026-11-16 with curl; page quote: "Run your model on RTX 4090 and RTX 5090 GPUs that start when a request arrives and shut down after traffic stops.". The page says "GPU time starts at $0.69 /hr, metered by the millisecond"; the separate /inference page ("Serverless inference for any model") describes the same endpoint product, so it is not a second row.
- Sold within
-
Entitlement read 2026-11-16 with curl; page quote: "Concurrent vCPUs is the total CPU running at once across VMs, sandboxes, and serverless apps".
- Name
-
Company disclosure · 16 Nov 2026
Product page text fetched 2026-11-16 with curl; page quote: "Run your model on RTX 4090 and RTX 5090 GPUs that start when a request arrives and shut down after traffic stops.". The page says "GPU time starts at $0.69 /hr, metered by the millisecond"; the separate /inference page ("Serverless inference for any model") describes the same endpoint product, so it is not a second row.
- URL
-
Company disclosure · 16 Nov 2026
Product page text fetched 2026-11-16 with curl; page quote: "Run your model on RTX 4090 and RTX 5090 GPUs that start when a request arrives and shut down after traffic stops.". The page says "GPU time starts at $0.69 /hr, metered by the millisecond"; the separate /inference page ("Serverless inference for any model") describes the same endpoint product, so it is not a second row.
Also from Beam
-
Beam Infrastructure service
Cloud that sources bare-metal servers and sells them as persistent VMs, sandboxes for untrusted code, task queues, serverless functions and endpoints, with GPUs from RTX 4090 to B200, billed per second while code runs; prices from $0.06 an hour and H100s from $1.83 an hour are published.
-
Beam Sandboxes Infrastructure service
Isolated cloud sandboxes for agent- and LLM-generated code that start in about half a second, with memory snapshots, GPU attach and port exposure, billed by the millisecond.
-
Beam Virtual Machines Infrastructure service
Persistent Linux microVMs for AI agents, each with its own kernel, durable disk, SSH and browser desktop, that can be paused with memory intact and forked, billed per second while running.
Something wrong here? Send a correction — quote this product id: beam-serverless-gpu.