Lepton AI / NVIDIA DGX Cloud Lepton - Free Plan
Source: https://www.lepton.ai/
Description
Create account to comment on specific lines or Sign in
+ 1 Lepton AI (now NVIDIA DGX Cloud Lepton) offers a free Basic Plan with no subscription fees and pay-as-you-go pricing. The free plan includes up to 48 CPUs and 2 GPUs concurrently in a single workspace. The platform provides serverless endpoints for popular open-source LLMs with OpenAI-compatible API, dedicated GPU compute billed by the minute, and a Pythonic SDK for building and deploying custom AI services. NVIDIA acquired Lepton AI in April 2025 and rebranded it as DGX Cloud Lepton, connecting developers to tens of thousands of GPUs from a global network of cloud providers.
No comments on this line yet.
+ 2
No comments on this line yet.
+
3
No comments on this line yet.
+ 4
No comments on this line yet.
+ 6
No comments on this line yet.
+ 7 1. Go to lepton.ai (redirects to nvidia.com/en-us/data-center/dgx-cloud-lepton/)
No comments on this line yet.
+ 8 2. Click "Get Started" or "Sign Up"
No comments on this line yet.
+ 9 3. Create an account using your email or a social login (GitHub, Google)
No comments on this line yet.
+ 10 4. After signing in, access the Lepton Dashboard to create a workspace
No comments on this line yet.
+
11
5. Install the Python SDK locally: pip install -U leptonai
No comments on this line yet.
+
12
6. Authenticate your CLI with: lep login and follow the prompts to link your account
No comments on this line yet.
+ 13 7. You are now on the Basic Plan with no subscription fee — you only pay for resources you actually consume
No comments on this line yet.
+ 14
No comments on this line yet.
+ 15 Important:
No comments on this line yet.
+ 16 • The Basic Plan is a single-user workspace
No comments on this line yet.
+ 17 • Rate limit for serverless API endpoints on Basic Plan is 10 requests per minute
No comments on this line yet.
+ 18 • No upfront payment or subscription required — purely usage-based billing
No comments on this line yet.
+ 19 • The platform now redirects to NVIDIA's domain, but the Lepton dashboard and docs remain functional
No comments on this line yet.
+ 20
No comments on this line yet.
+
21
No comments on this line yet.
+ 22
No comments on this line yet.
+ 24
No comments on this line yet.
+ 25 ResourceLimit
No comments on this line yet.
+ 26 Subscription fee$0/month
No comments on this line yet.
+ 27 Max concurrent CPUs48
No comments on this line yet.
+ 28 Max concurrent GPUs2
No comments on this line yet.
+ 29 Workspace users1
No comments on this line yet.
+ 30 Serverless API rate limit10 RPM
No comments on this line yet.
+ 31 StorageFirst 1 GB free ($0.153/GB/month after)
No comments on this line yet.
+ 32 Network egressFirst 10 GB/month free ($0.15/GB after)
No comments on this line yet.
+ 33
No comments on this line yet.
+
34
No comments on this line yet.
+ 35
No comments on this line yet.
+ 37
No comments on this line yet.
+ 38 Lepton AI provides pre-configured serverless endpoints for popular open-source models. All LLM endpoints are fully compatible with OpenAI's API spec — you can use them as a drop-in replacement with OpenAI client libraries.
No comments on this line yet.
+ 39
No comments on this line yet.
+ 40 Since the NVIDIA acquisition, Lepton has shifted from a fixed model catalog to an infrastructure-first platform connecting developers to 10K+ concurrent models across 20+ NVIDIA Cloud Partners. The previous fixed serverless model lineup (Llama 3.x, Mixtral, Mistral 7B) has been superseded by a dynamic model ecosystem.
No comments on this line yet.
+ 41
No comments on this line yet.
+ 42 The platform now focuses on:
No comments on this line yet.
+ 43 • Custom model deployment — bring your own models via the Pythonic SDK
No comments on this line yet.
+ 44 • Pre-built templates — deploy popular open-source models (Llama 4, Qwen3, DeepSeek, etc.) from Hugging Face
No comments on this line yet.
+ 45 • Partner model access — inference through cloud partners (Together AI, Nebius, Scaleway, etc.)
No comments on this line yet.
+ 46
No comments on this line yet.
+ 47 Note: Specific model availability and pricing are dynamic and depend on the cloud partner routing. Check the Lepton dashboard for current serverless endpoints and pricing.
No comments on this line yet.
+ 48
No comments on this line yet.
+ 49 Beyond LLMs, Lepton also offers serverless endpoints for:
No comments on this line yet.
+ 50 • Whisper — audio transcription
No comments on this line yet.
+ 51 • Stable Diffusion — image generation
No comments on this line yet.
+ 52
No comments on this line yet.
+
53
No comments on this line yet.
+ 54
No comments on this line yet.
+ 56
No comments on this line yet.
+ 57 For custom deployments, training, or running your own models, Lepton offers dedicated GPU instances billed by the minute:
No comments on this line yet.
+ 58
No comments on this line yet.
+ 59 GPU TypevRAMRAMvCPUPrice/min~Price/hr
No comments on this line yet.
+ 60 NVIDIA A1024 GB96 GB24$0.0202~$1.21
No comments on this line yet.
+ 61 NVIDIA RTX A600048 GB64 GB8$0.0275~$1.65
No comments on this line yet.
+ 62 NVIDIA H100 80GB80 GB240 GB20$0.0500~$3.00
No comments on this line yet.
+ 63 NVIDIA A100 80GB80 GB192 GB12$0.0535~$3.21
No comments on this line yet.
+ 64
No comments on this line yet.
+ 65 • A100 and H100 instances can scale to 1, 2, 4, or 8 GPUs
No comments on this line yet.
+ 66 • Compute is billed by the minute with no minimum commitment
No comments on this line yet.
+ 67 • On the Basic Plan, you can use up to 2 GPUs concurrently
No comments on this line yet.
+ 68
No comments on this line yet.
+
69
No comments on this line yet.
+ 70
No comments on this line yet.
+ 72
No comments on this line yet.
+ 73 • OpenAI-compatible API — use the standard OpenAI Python/JS client with Lepton's base URL
No comments on this line yet.
+
74
• Pythonic SDK (leptonai) — build models with Python, deploy with lep CLI, no Docker/Kubernetes needed
No comments on this line yet.
+ 75 • Dev Pods — interactive development via Jupyter notebooks, SSH, or VS Code
No comments on this line yet.
+ 76 • Batch Jobs — large-scale training and data preprocessing across multiple nodes
No comments on this line yet.
+ 77 • Custom Model Deployment — deploy any model from HuggingFace or your own code as a service ("Photon")
No comments on this line yet.
+ 78 • Auto-scaling — serverless endpoints scale automatically based on traffic
No comments on this line yet.
+ 79 • Multi-cloud — since the NVIDIA acquisition, the platform connects to 20+ cloud providers (CoreWeave, Lambda, Nebius, Crusoe, AWS, and more)
No comments on this line yet.
+ 80
No comments on this line yet.
+
81
No comments on this line yet.
+ 82
No comments on this line yet.
+ 84
No comments on this line yet.
+ 85 NVIDIA acquired Lepton AI in early April 2025 for several hundred million dollars. Key changes:
No comments on this line yet.
+ 86
No comments on this line yet.
+ 87 • Rebranded from "Lepton AI" to "NVIDIA DGX Cloud Lepton"
No comments on this line yet.
+ 88 • lepton.ai now redirects to nvidia.com/en-us/data-center/dgx-cloud-lepton/
No comments on this line yet.
+ 89 • The legacy Lepton Dashboard remains accessible for existing customers
No comments on this line yet.
+ 90 • Co-founders Yangqing Jia (ex-Alibaba VP, creator of Caffe) and Junjie Bai stayed on post-acquisition
No comments on this line yet.
+ 91 • The platform is being expanded as a GPU compute marketplace connecting 20+ NVIDIA Cloud Partners, including access to NVIDIA Blackwell GPUs
No comments on this line yet.
+ 92 • Future integration with NVIDIA NIM microservices, NeMo, and Cloud Functions (NVCF)
No comments on this line yet.
+ 93
No comments on this line yet.
+ 94 What this means for free plan users: The Basic Plan still exists as of early 2026, but the platform is in transition. Pricing, available models, and plan structures may change as NVIDIA integrates Lepton into DGX Cloud.
No comments on this line yet.
+ 95
No comments on this line yet.
+
96
No comments on this line yet.
+ 97
No comments on this line yet.
+ 99
No comments on this line yet.
+ 100 PlanMonthly FeeMax CPUsMax GPUsServerless RPMUsers
No comments on this line yet.
+ 101 Basic (Free)$0482101
No comments on this line yet.
+ 102 Standard$3019216600Multi-user
No comments on this line yet.
+ 103 EnterpriseCustomCustomCustomCustomUnlimited
No comments on this line yet.
+ 104
No comments on this line yet.
+ 105 The Standard plan adds multi-user workspaces, higher concurrency, dedicated support, and advanced features. Enterprise adds custom SLAs, account management, and 24/7 priority support.
No comments on this line yet.
+ 106
No comments on this line yet.
+
107
No comments on this line yet.
+ 108
No comments on this line yet.
+ 110
No comments on this line yet.
+ 111 • No auto-billing surprise — the Basic Plan has no subscription fee. You only pay for compute, storage, and network you actually use. If you do not spin up any resources, you pay nothing
No comments on this line yet.
+
112
• OpenAI SDK compatibility — to use Lepton's serverless endpoints, just change the base_url in your OpenAI client to https://<model-name>.lepton.run/api/v1/ and use your Lepton API key
No comments on this line yet.
+ 113 • Storage under 1 GB is free — ideal for small experiments and prototypes
No comments on this line yet.
+ 114 • 10 RPM is limiting — the Basic Plan's 10 requests per minute rate limit on serverless endpoints is tight for production use. It is best for experimentation and prototyping
No comments on this line yet.
+ 115 • GPU availability may vary — since DGX Cloud Lepton aggregates across cloud providers, GPU availability depends on the partner network and current demand
No comments on this line yet.
+ 116 • Python 3.10+ recommended — the leptonai SDK works best with Python 3.10 or newer
No comments on this line yet.
+ 117 • Platform is in transition — with the NVIDIA acquisition still relatively recent, expect features, pricing, and branding to evolve. The legacy Lepton dashboard is still available but may eventually migrate fully to NVIDIA's infrastructure
No comments on this line yet.
+ 118
No comments on this line yet.
+
119
No comments on this line yet.
+ 120
No comments on this line yet.
+ 121 Sources:
No comments on this line yet.
+ 122 • NVIDIA DGX Cloud Lepton (lepton.ai)
No comments on this line yet.
+ 123 • Lepton AI Pricing
No comments on this line yet.
+ 124 • Lepton AI Billing and Payments
No comments on this line yet.
+ 125 • Lepton AI Quickstart Guide
No comments on this line yet.
+ 126 • Lepton AI Serverless Endpoints Documentation
No comments on this line yet.
+ 127 • Introducing NVIDIA DGX Cloud Lepton (NVIDIA Developer Blog)
No comments on this line yet.
+ 128 • NVIDIA Announces DGX Cloud Lepton (NVIDIA Newsroom)
No comments on this line yet.
+ 129 • Lepton AI on Artificial Analysis
No comments on this line yet.
+ 130 • Lepton AI GitHub
No comments on this line yet.