Picture published by the creator on GitHub.
new-api: Manage team access to AI models through one gateway
Added · Updated
Made by QuantumNous
View profile on GitHub (opens in a new tab)New API gives developers and teams one place to connect model providers, route requests, control access, and track costs.
Start by reviewing its self-hosted gateway setup.
What it does
New API sits between applications and the services supplying their AI models. It provides a consistent connection for clients while centralizing provider selection, access rules, usage records, and costs. This suits developers operating a private model service or managing access for a team.
How to use it
Start with the repository's deployment guidance. After deploying the gateway, connect authorized model services and configure their channels and models in the web console. Set routing preferences and access restrictions, then connect your applications to the gateway. Use the console to try models and inspect usage and audit logs.
Common use cases
- Share authorized model access across a team with user permissions and API key restrictions.
- Switch model providers without configuring every connected application again.
- Manage usage quotas and inspect costs for different usage tiers.
Can I use this?
Requirements You need to host the gateway and obtain the upstream accounts, API keys, services, and permissions it will use. The source does not specify minimum server resources or a complete installation procedure.
Caveat Features such as tools and inputs combining text with other media depend on provider support. The repository's dashboard screenshots contain simulated usage and cost data.
Worth knowing Model features depend on upstream support. Dashboard screenshots use simulated account, usage, price, and cost data. Licensed under GNU Affero General Public License v3.0.
Why it's here
Not trending this week
Last seen on the GitHub trending list on 31 October 2026. It stays on BuildTube so you can still find it.
- 51,564 people have starred it on GitHub.
Numbers checked on 8 November 2026; not refreshed since.
Behind it
View sourceBuildTube has not run or verified this project. Everything above is written from what the creator published.
Made this?
Quick questions
- What is new-api?
- New API sits between applications and the services supplying their AI models.
- What can I use new-api for?
- Share authorized model access across a team with user permissions and API key restrictions; Switch model providers without configuring every connected application again; Manage usage quotas and inspect costs for different usage tiers
- Can I run new-api on my computer?
- It runs on your own computer or server after a local setup.
- What do I need to use new-api?
- A self-hosted deployment and authorized upstream model accounts, API keys, and permissions.
- What license does new-api use?
- Licensed under GNU Affero General Public License v3.0.
More from this week
- Garden Skills Give your coding agent video and web design skills
Install ready-made skills so Claude Code, Cursor or Codex can make short videos, web pages and articles.
- DS Harness Remote Reach your DeepSeek Harness from a phone or browser
Continue your DeepSeek Harness sessions from a phone, another computer or a browser while the work keeps running on your own machine.
- agent-desktop Let AI agents read and click desktop apps
For developers building computer-use agents: agent-desktop lets an AI agent read and operate desktop apps on Mac, Windows or Linux from a command line.
Explore by topic
Post this
Download share imageFor makers
Made this? Show it’s on BuildTube — add the badge to your README or embed the card on your site.
README badge (Markdown)
[](https://buildtube.app/p/gh-quantumnous-new-api/)Embed card (HTML)
<iframe src="https://buildtube.app/embed/gh-quantumnous-new-api/" width="560" height="240" style="border:0;max-width:100%" loading="lazy" title="new-api on BuildTube"></iframe>