yangmao.ai · Free API intent page
DGX Cloud Lepton (formerly Lepton AI) Free API Guide
DGX Cloud Lepton (formerly Lepton AI) has a tracked free API path, with $10 free credits and rate limit notes of 10 RPM.
Quick verdict
- Free API: $10 free credits
- Rate limits: 10 RPM
- Best model starting point: Llama 3.3 70B
- Mainland China access: direct or relatively friendly
Provider fit matrix
Lepton AI buyer intent notes
Who should care
Best for developers testing serverless AI inference, hosted open models, and deployment workflows that sit between API providers and custom GPU ops.
Decision trigger
Use Lepton AI when you want deployment flexibility with less infrastructure work than raw GPU servers.
Watch out: Free/trial terms can be account-specific; verify endpoint status, model IDs, and region latency before wiring retries.
Production readiness checklist
Python setup snapshot
Start with the smallest possible chat completion, then move the key to your server-side secret manager before production.
from openai import OpenAI
client = OpenAI(
api_key="your-lepton-key",
base_url="https://llama3-3-70b.lepton.run/api/v1"
)
response = client.chat.completions.create(
model="llama3-3-70b",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)cURL smoke test
Use this to verify endpoint, auth header, model name, response shape, and quota before adding SDK abstractions.
curl https://llama3-3-70b.lepton.run/api/v1/chat/completions \
-H "Authorization: Bearer $LEPTON_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "Llama 3.3 70B",
"messages": [{"role": "user", "content": "Hello from yangmao.ai"}]
}'Free API and pricing notes
$10 free credits
New users get $10 free credits, founded by Yangqing Jia (PyTorch co-creator)
Access and production risk
Mainland China friendly / direct path likely
Founded by Chinese-American team, good China access. API is directly accessible.
Decision checklist
Check DGX Cloud Lepton (formerly Lepton AI) free credits and rate limits.
Compare same-category providers and Mainland China access needs.
Pick the provider with the clearest no-card/free API path for testing.
Credit-change alerts
Want to know when free credits, pricing, or availability changes? Subscribe first, then compare official providers, API gateways, and alternatives.
Subscribe → Get an OpenLLMAPI key → Compare API gateways →Related internal links
Source snapshot
Data source: yangmao.ai provider YAML tracker plus provider docs reviewed by the daily crawler. Official dashboards can change quota and pricing without notice; verify before production.
- yangmao.ai provider id
- lepton
- Official source
- https://build.nvidia.com/explore/discover
- Last updated
- 2026-06-05
- Free tier
- 10M tokens/day
- API credits
- $10 free credits
- Rate limit
- 10 RPM
- Access note
- Founded by Chinese-American team, good China access. API is directly accessible.
FAQ
Does DGX Cloud Lepton (formerly Lepton AI) have a free API?
Yes. Current yangmao.ai record: $10 free credits. Rate limit note: 10 RPM.
Is DGX Cloud Lepton (formerly Lepton AI) OpenAI-compatible?
The recorded setup uses an OpenAI-compatible pattern or SDK-style call. Validate the latest base URL and model names in DGX Cloud Lepton (formerly Lepton AI) docs.
Can I use DGX Cloud Lepton (formerly Lepton AI) from mainland China?
DGX Cloud Lepton (formerly Lepton AI) is marked as relatively direct or Mainland-China-friendly in the current tracker.
What should I do when DGX Cloud Lepton (formerly Lepton AI) credits run out?
Compare the alternatives below, check /en/free-ai-api/, and shortlist official providers or API gateway options before production.
Is Lepton AI closer to an API provider or deployment platform?
It sits closer to an AI deployment/inference platform, so test it when you need hosted endpoints with more control than a generic model router.