# NVIDIA: Free prototyping on build.nvidia.com model endpoints, up to 40 requests per minute for most models, no per-token billing

> Markdown copy of https://perq.sh/offers/nvidia-build-free-endpoints. Index of every page for agents: https://perq.sh/llms.txt. Search API and MCP server: https://perq.sh/agents.

- Status: live
- Category: LLM APIs
- Offer type: free tier
- Credit value: Free prototyping on build.nvidia.com model endpoints, up to 40 requests per minute for most models, no per-token billing
- Eligibility: Anyone with an NVIDIA developer account
- How to claim: Sign in on build.nvidia.com and generate an API key.
- Claim URL: https://build.nvidia.com
- Source URL: https://build.nvidia.com/api/runtime/content/help-center-faq.yaml
- Last verified: 2026-11-11T06:20:52-05:00 (Nov 11, 2026, 6:20 AM ET), HTTP 200
- Notes: FAQ: "All models on build.nvidia.com are free to prototype with." After rate limits, use partner endpoints or deploy a NIM. Separate from nvidia-inception.

> Source quote (verbatim from the source page):
> "The free tier runs on rate limits - up to 40 requests per minute (RPM) for most models, with no per-token billing."

Page: https://perq.sh/offers/nvidia-build-free-endpoints