What is Koyeb?
Koyeb is a serverless platform designed to simplify the deployment and scaling of applications globally. It eliminates the need for users to manage operations, servers, or infrastructure, offering a streamlined cloud experience. The platform focuses on high performance, providing access to a range of hardware including CPUs, GPUs, and accelerators from manufacturers like AMD, Intel, and Nvidia. This makes it suitable for intensive workloads such as AI inference and fine-tuning.
Deployments on Koyeb are designed for ease and efficiency. Users can deploy their code, containers, or models using a simple Git push or a CLI command. The platform supports automatic scaling, allowing applications to handle fluctuating demand by scaling from zero to hundreds of servers and back within seconds. With over 50 locations available, Koyeb enables low-latency access and high availability for applications worldwide. It also offers native support for various languages, frameworks, and Docker containers, alongside features like zero-downtime deployments and managed Serverless Postgres with pgvector support.
Features
- High-Performance Hardware Access: Utilize GPUs, CPUs, and accelerators from AMD, Intel, and Nvidia.
- Automatic Scaling: Serverless containers automatically scale from zero to hundreds of instances based on demand.
- Global Deployment Network: Deploy applications across 50+ locations worldwide for improved availability and low latency.
- Any Stack Deployment: Deploy code, containers, or models using Git push or CLI commands.
- Serverless Postgres: Offers fully managed, scalable Postgres databases with pgvector support.
- Ultra-Fast NVME Storage: Access high-throughput NVMe disks for datasets, models, and weights.
- Zero-Downtime Deployments: Built-in continuous deployment with automatic health checks ensures continuous availability.
- Native Networking Support: Supports HTTP/2, WebSocket, and gRPC for accelerated connections.
- Real-time Logs and Instance Access: Troubleshoot issues with real-time logs and direct instance connectivity.
- Built-in Security: Features DDoS protection, encryption at rest and in transit, and secrets management.
Use Cases
- Deploying and scaling AI models for inference.
- Fine-tuning machine learning models on dedicated GPUs.
- Running and managing AI agents.
- Building and hosting scalable SaaS platforms.
- Developing and deploying distributed systems.
- Hosting web applications and APIs with global reach.
- Managing scalable databases with Serverless Postgres.
- Automating infrastructure management for development teams.
FAQs
-
Do I need a credit card to get started?
No, you can start using Koyeb without adding a payment method on the Hobby plan. With the Hobby plan, you can run one Web Service and Database for free. -
Is the Starter plan really free?
Yes, the Starter plan is free and includes a free tier composed of one Web Service, one Database service, and 5 custom domains. The starter plan requires a credit card, and additional Services are charged according to your usage, by the second. -
How are processing and bandwidth charged?
Once you've consumed your monthly free tier, billing starts on a pay-per-use basis. Processing is accounted per second, and billing is rounded up to the nearest unit. Charges are applied at the end of the calendar month. -
How much do additional Services cost?
Services are charged depending on effective usage, starting at $0.000006/second. The price depends on the Instance size and scale you choose. -
Can I deploy with my own domain?
Yes, you can use your own domain, and Koyeb automatically provides SSL. The Starter plan includes 5 free custom domains.
Related Queries
Helpful for people in the following professions
Koyeb Uptime Monitor
Average Uptime
100%
Average Response Time
380 ms
Featured Tools
Join Our Newsletter
Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.