Koyeb

What's good about Koyeb

• Per-second billing across the full GPU range
• Multi-GPU configurations (2x, 4x, 8x) available on-demand
• Serverless model removes idle-instance costs

Koyeb GPU prices

7 GPU models across 15 configurations. Rank compares Koyeb's cheapest on-demand listing for each GPU with every provider's cheapest.

What a run costs on Koyeb

24 hours at today's cheapest listing for each GPU, at the size it is listed.

• 1× H100 SXM for 24 hours

  At $2.50/GPU-hr

  $60.00

  $16.68 under the market median rate

• 1× H200 for 24 hours

  At $3.00/GPU-hr

  $72.00

  $36.95 under the market median rate

• 1× L40S for 24 hours

  At $1.20/GPU-hr

  $28.80

  $2.64 over the market median rate

The market median is every provider's cheapest on-demand price for that GPU.

Billing & terms

Per-Second GPU Billing

Charged per second of GPU runtime, with scale-to-zero when idle

Multi-GPU Configurations

Pre-configured 2x, 4x and 8x GPU instances for larger workloads

Saving Plans

Long-term reservations at up to 50% off the on-demand price

Regions

7 regions across the US, EU and Asia on self-serve plans; AWS regions on Scale; Enterprise adds private dedicated locations, BYOC and custom regions

Support

Email and chat support on Pro; Slack cross-connect and 99.9% uptime SLA on Scale; 24×7×365 premium support and 99.99% uptime SLA on Enterprise; documentation and community forum

Watch out for

• Smaller per-cluster scale than dedicated training neoclouds
• Some GPU SKUs require requesting access
• Long-running fixed-instance training is not the primary use case

Features

Serverless GPU Instances

Per-second billing with scale-to-zero across the GPU catalog

Wide GPU Range

From RTX-4000-SFF-ADA and L4 through L40S, A100, H100, H200 and B200

Global Edge Deployment

Deploy applications close to users across multiple regions from a single push

Serverless Postgres

Managed Postgres billed by the second with scale-to-zero on inactivity

Sandboxes

Isolated environments for executing code and running AI agents on the same platform as inference workloads

Getting started

1. Step 1

   Create an account

   Sign up via the Koyeb console using email or GitHub

2. Step 2

   Pick a GPU instance

   Select an instance type from the GPU catalog and configure your service

3. Step 3

   Deploy from Git or container

   Push from a GitHub repo or Docker image and Koyeb handles the rest