Developer Frameworks & Infrastructure
NVIDIA DGX Cloud Lepton
Developer cloud platform for running, scaling, and deploying AI applications and models
Freemium - from $0.001/secondRuns on your deviceEditors pick
GitHub stars
2.8K
2,826 stars
Community forks
199
Open collaboration
License
Apache-2.0
Read the full license
Platforms
macOS - Windows - Linux
Also Web
Last activity
Nov 19
Repository push date
Best for
Exceptional developer experience with elegant Pythonic CLI and photon abstractions
NVIDIA DGX Cloud Lepton (formerly Lepton AI) is a developer platform created to build, deploy, and scale production-grade AI model APIs and full-stack AI services with pythonic simplicity.
Pricing checked Nov 2026
User feedback
No aggregate rating verified
Explore discussions, issues, and documentation to see how this project fits your workflow.
GitHub stars measure repository interest, not customer satisfaction.
Read Prother reviews (0) - write your ownHide Prother reviews
Reviews (0)
HONEST AND VERIFIED ONLYReview NVIDIA DGX Cloud Lepton
Share real experiences on ease of use, feature power, and overall value.
About NVIDIA DGX Cloud Lepton
Founded by Jiaqing Han (co-creator of PyTorch Lightning and ONNX), Lepton AI reimagines AI cloud infrastructure for software developers. With its pythonic CLI and SDK, developers can turn any Python model function into a production-grade, autoscaling, containerized web service with a single command: 'lep photon run'. Lepton eliminates Kubernetes complexities, handles dynamic batching, and provides instant access to premium curated model endpoints.
- Exceptional developer experience with elegant Pythonic CLI and photon abstractions
- Automatic traffic scaling from zero to hundreds of GPU nodes with zero cluster management
- Curated model catalog ready for instant consumption with standard OpenAI SDKs
- Advanced custom networking configurations require enterprise tier support
- Platform credits scale with GPU tier selection
git clone https://github.com/leptonai/leptonai.gitOpen source tool available on GitHub.
Practical Guides & In-Depth Evaluations
More in Developer Frameworks & Infrastructure
See categoryThe layer builders stand on: training frameworks, model hubs, agent orchestration, vector databases, and pay-per-second inference APIs. Repository health, license clarity, and self-hosting paths are part of every listing so teams can evaluate lock-in at a glance.
SiliconCloud
High-performance serverless cloud platform for deploying and inferencing open-source foundation models
Roo Code
Autonomous multi-mode AI coding assistant extension for VS Code and VSCodium
Claude Code
Agentic command line coding tool that lives in your terminal and edits codebases