Lepton AI / NVIDIA DGX Cloud Lepton - Free Plan

AI API Free Tiers | Amount: Free plan with up to 48 CPUs + 2 GPUs concurrently, 1 GB storage free, 10 GB network egress free, serverless endpoints at pay-per-token rates | AI-generated | 1/5 InstantSignup and get credits instantly — no credit card, no approval active
2026-02-05
Create account to vote or Sign in Score: 0

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.

Create account to comment on this line. or Sign in

+ 2  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 3

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 4  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 5 Registration (Step-by-Step)

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 6  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 7 1. Go to lepton.ai (redirects to nvidia.com/en-us/data-center/dgx-cloud-lepton/)

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 8 2. Click "Get Started" or "Sign Up"

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 9 3. Create an account using your email or a social login (GitHub, Google)

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 10 4. After signing in, access the Lepton Dashboard to create a workspace

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 11 5. Install the Python SDK locally: pip install -U leptonai

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 12 6. Authenticate your CLI with: lep login and follow the prompts to link your account

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 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.

Create account to comment on this line. or Sign in

+ 14  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 15 Important:

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 16 • The Basic Plan is a single-user workspace

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 17 • Rate limit for serverless API endpoints on Basic Plan is 10 requests per minute

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 18 • No upfront payment or subscription required — purely usage-based billing

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 19 • The platform now redirects to NVIDIA's domain, but the Lepton dashboard and docs remain functional

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 20  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 21

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 22  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 23 Free Plan Limits (Basic Plan)

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 24  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 25 ResourceLimit

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 26 Subscription fee$0/month

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 27 Max concurrent CPUs48

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 28 Max concurrent GPUs2

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 29 Workspace users1

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 30 Serverless API rate limit10 RPM

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 31 StorageFirst 1 GB free ($0.153/GB/month after)

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 32 Network egressFirst 10 GB/month free ($0.15/GB after)

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 33  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 34

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 35  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 36 Available Serverless Models

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 37  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 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.

Create account to comment on this line. or Sign in

+ 39  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 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.

Create account to comment on this line. or Sign in

+ 41  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 42 The platform now focuses on:

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 43 Custom model deployment — bring your own models via the Pythonic SDK

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 44 Pre-built templates — deploy popular open-source models (Llama 4, Qwen3, DeepSeek, etc.) from Hugging Face

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 45 Partner model access — inference through cloud partners (Together AI, Nebius, Scaleway, etc.)

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 46  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 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.

Create account to comment on this line. or Sign in

+ 48  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 49 Beyond LLMs, Lepton also offers serverless endpoints for:

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 50 Whisper — audio transcription

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 51 Stable Diffusion — image generation

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 52  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 53

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 54  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 55 Dedicated GPU Compute Pricing

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 56  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 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.

Create account to comment on this line. or Sign in

+ 58  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 59 GPU TypevRAMRAMvCPUPrice/min~Price/hr

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 60 NVIDIA A1024 GB96 GB24$0.0202~$1.21

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 61 NVIDIA RTX A600048 GB64 GB8$0.0275~$1.65

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 62 NVIDIA H100 80GB80 GB240 GB20$0.0500~$3.00

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 63 NVIDIA A100 80GB80 GB192 GB12$0.0535~$3.21

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 64  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 65 • A100 and H100 instances can scale to 1, 2, 4, or 8 GPUs

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 66 • Compute is billed by the minute with no minimum commitment

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 67 • On the Basic Plan, you can use up to 2 GPUs concurrently

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 68  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 69

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 70  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 71 Platform Features

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 72  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 73 OpenAI-compatible API — use the standard OpenAI Python/JS client with Lepton's base URL

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 74 Pythonic SDK (leptonai) — build models with Python, deploy with lep CLI, no Docker/Kubernetes needed

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 75 Dev Pods — interactive development via Jupyter notebooks, SSH, or VS Code

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 76 Batch Jobs — large-scale training and data preprocessing across multiple nodes

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 77 Custom Model Deployment — deploy any model from HuggingFace or your own code as a service ("Photon")

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 78 Auto-scaling — serverless endpoints scale automatically based on traffic

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 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.

Create account to comment on this line. or Sign in

+ 80  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 81

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 82  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 83 NVIDIA DGX Cloud Lepton Transition

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 84  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 85 NVIDIA acquired Lepton AI in early April 2025 for several hundred million dollars. Key changes:

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 86  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 87 Rebranded from "Lepton AI" to "NVIDIA DGX Cloud Lepton"

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 88 lepton.ai now redirects to nvidia.com/en-us/data-center/dgx-cloud-lepton/

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 89 • The legacy Lepton Dashboard remains accessible for existing customers

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 90 • Co-founders Yangqing Jia (ex-Alibaba VP, creator of Caffe) and Junjie Bai stayed on post-acquisition

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 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.

Create account to comment on this line. or Sign in

+ 92 • Future integration with NVIDIA NIM microservices, NeMo, and Cloud Functions (NVCF)

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 93  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 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.

Create account to comment on this line. or Sign in

+ 95  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 96

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 97  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 98 Paid Plans

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 99  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 100 PlanMonthly FeeMax CPUsMax GPUsServerless RPMUsers

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 101 Basic (Free)$0482101

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 102 Standard$3019216600Multi-user

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 103 EnterpriseCustomCustomCustomCustomUnlimited

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 104  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 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.

Create account to comment on this line. or Sign in

+ 106  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 107

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 108  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 109 Additional Tips

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 110  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 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.

Create account to comment on this line. or Sign in

+ 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.

Create account to comment on this line. or Sign in

+ 113 Storage under 1 GB is free — ideal for small experiments and prototypes

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 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.

Create account to comment on this line. or Sign in

+ 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.

Create account to comment on this line. or Sign in

+ 116 Python 3.10+ recommended — the leptonai SDK works best with Python 3.10 or newer

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 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.

Create account to comment on this line. or Sign in

+ 118  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 119

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 120  

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 121 Sources:

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 123 Lepton AI Pricing

No comments on this line yet.

Create account to comment on this line. or Sign in

+ 130 Lepton AI GitHub

No comments on this line yet.

Create account to comment on this line. or Sign in

Comments

Create account to post a comment or Sign in

No comments yet.

Back