new-api social preview
model-router51,066AGPL-3.0

new-api

Open-source AI gateway. Self-hosted LLM gateway with OpenAI-, Claude- and Gemini-compatible APIs, model routing, access control, usage tracking and cost accoun…

Updated Oct 31, 2026
Website GitHub Docs
Platforms
docker, web
Pricing
free-open-source
Status
active
License
AGPL-3.0

What it does

Core capabilities at a glance

  • AI Gateway
  • API Management
  • Claude
  • Deepseek
  • Gemini
  • LLM Gateway
  • Model Routing
  • Newapi

Deep dive

The full breakdown - performance, comparisons, and setup

new-api

new-api is a model router/gateway - Open-source AI gateway. Self-hosted LLM gateway with OpenAI-, Claude- and Gemini-compatible APIs, model routing, access control, usage tracking and cost accounting.

Overview

New API is a self-hosted AI gateway for applications, agents, and teams. Connect upstream model services, expose a consistent API to your clients, and manage routing, access, usage, and costs in one place.

Use it to share authorized model access across a team, switch providers without configuring every client again, or operate a private multi-model service with a web console. Upstreams include OpenAI, Anthropic, Google Gemini, Azure OpenAI, AWS Bedrock, Vertex AI, DeepSeek, Qwen, and other compatible services.

Accounts, channels, plugin installation states, usage, prices, and costs shown below are simulated data. The marketplace displays the official plugin catalog. Click an image to view it at full size.

RelayKit provides request, response, and streaming conversion between the four text protocols. Available features depend on the channel, upstream model, and conversion path; protocol-specific tools and fields may not map exactly. WebSocket support also requires a compatible upstream and channel configuration.

This README describes the current source tree. Check the release notes for the version you deploy.

Open http://localhost:3000 and complete the setup wizard to create the administrator account. The 'data' directory persists the SQLite database across container replacements.

new-api is open-source, written primarily in Go, with 51,066 GitHub stars under the AGPL-3.0 license. The latest release is v1.0.0-rc.47 (2026-10-25).

Install

A quick way to get started (always check the official docs for the latest):

docker run --name new-api -d --restart unless-stopped \

How it fits a local-AI stack

new-api runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related model router/gateways in the directory:

Sources

Stats from GitHub, 2026-10-30.

Frequently asked

Quick answers to common questions

What is new-api?

new-api is a model-router tool for local AI workloads. Open-source AI gateway. Self-hosted LLM gateway with OpenAI-, Claude- and Gemini-compatible APIs, model routing, access control, usage tracking and cost accoun…

Is new-api free and open source?

Yes, new-api has 51,066 GitHub stars and is licensed under AGPL-3.0. You can self-host it for free on docker, web.

What platforms does new-api support?

new-api runs on docker, web.

What hardware do I need for new-api?

The hardware requirements depend on which models you run. Check our hardware directory for compatible GPUs and systems. new-api has 51,066 GitHub stars and an active community.

Does new-api support GPU acceleration?

new-api's GPU support depends on your specific setup. Check the documentation for details. For the best performance, pair it with an NVIDIA RTX 4090 or 5090.

What are the best alternatives to new-api?

Popular alternatives include other model-router tools in our directory. Browse our full collection at /tool for comparisons, community reviews, and benchmark data to find the right fit for your workflow.

How much does new-api cost?

new-api is free-open-source. It is completely free and open source to self-host.

Pairs well with

Complementary tools, models, and hardware