Loading page
Koyeb
Serverless GPUs with per-second billing and global deployment
Inference specialist🇫🇷 FR
Last reviewed May 8, 2026
Koyeb is a serverless platform offering on-demand NVIDIA GPUs from RTX-class up through B200 with per-second billing, scale-to-zero and global edge deployment. Koyeb is joining Mistral AI to build the future of AI infrastructure.
GPU Models
5
From / hour
$0.75
Available GPUs
Hourly on-demand pricing. Click column headers to sort.
Prices last updated: September 16, 2026
Koyeb pricing by GPU
Configurations, price rank, and alternatives for one GPU at a time.
Pros & Cons
Advantages
- Per-second billing across the full GPU range
- Multi-GPU configurations (2x, 4x, 8x) available on-demand
- Serverless model removes idle-instance costs
Limitations
- 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
Key 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
Pricing Options
| Option | Details |
|---|---|
| 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 |
Availability & Support
Regions
Global edge presence across North America, Europe and Asia
Support
Documentation, community forum and paid support tiers
Getting Started
- 1
Create an account
Sign up via the Koyeb console using email or GitHub
- 2
Pick a GPU instance
Select an instance type from the GPU catalog and configure your service
- 3
Deploy from Git or container
Push from a GitHub repo or Docker image and Koyeb handles the rest
Frequently Asked Questions
What GPU types does Koyeb offer?
Koyeb offers various GPU types including A100 PCIE, A100 PCIE, A100 PCIE, A100 PCIE, RTX A6000, A100 SXM, A100 SXM, A100 SXM, A100 SXM, H100 SXM, H100 SXM, H100 SXM, H100 SXM, L40S. Check the pricing table above for current availability and pricing.
How do I get started with Koyeb?
Create an account, Pick a GPU instance, Deploy from Git or container
What are Koyeb's main advantages?
Koyeb's main advantages include: Per-second billing across the full GPU range, Multi-GPU configurations (2x, 4x, 8x) available on-demand, Serverless model removes idle-instance costs.
What are Koyeb's limitations?
Koyeb's main limitations include: 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.
Compare Providers
Find the best prices for the same GPUs and models from other providers
All Koyeb Comparisons
Koyeb vs GPU OutletKoyeb vs gpu.aiKoyeb vs Hexgrid CloudKoyeb vs Lium.ioKoyeb vs RuncrateKoyeb vs RunpodKoyeb vs Vast.aiKoyeb vs VerdaKoyeb vs 1LegionKoyeb vs AceCloudKoyeb vs AtmosComputeKoyeb vs CivoKoyeb vs CrusoeKoyeb vs HyperstackKoyeb vs IO.NETKoyeb vs Lambda LabsKoyeb vs Massed ComputeKoyeb vs ModalKoyeb vs OblivusKoyeb vs Omega GradientKoyeb vs SeewebKoyeb vs SesterceKoyeb vs ShadeformKoyeb vs Together AIKoyeb vs Amazon AWSKoyeb vs CoreWeaveKoyeb vs Cudo ComputeKoyeb vs Denvr DataworksKoyeb vs GcoreKoyeb vs Jarvis LabsKoyeb vs LyceumKoyeb vs Oracle CloudKoyeb vs PaperspaceKoyeb vs SpheronKoyeb vs Deep InfraKoyeb vs DigitalOceanKoyeb vs Microsoft AzureKoyeb vs Novita AIKoyeb vs ScalewayKoyeb vs Thunder ComputeKoyeb vs UpCloudKoyeb vs VultrKoyeb vs Atlas CloudKoyeb vs Compute CheapKoyeb vs DaytonaKoyeb vs GMI CloudKoyeb vs Google CloudKoyeb vs HinodeKoyeb vs HyperbolicKoyeb vs Latitude.shKoyeb vs NebiusKoyeb vs packet.aiKoyeb vs Voltage ParkKoyeb vs ZettabyteKoyeb vs Akamai CloudKoyeb vs AquanodeKoyeb vs BeamKoyeb vs BentausKoyeb vs Beyond.plKoyeb vs EcoHashKoyeb vs fal.aiKoyeb vs Hot AisleKoyeb vs Packet AIKoyeb vs QuickPodKoyeb vs Salad CloudKoyeb vs SwissGPUKoyeb vs TheAI CloudKoyeb vs Theta EdgeCloud