New API screenshot

New API

By QuantumNous
Developer ToolsOpen source / self-hosted

New API: self-hosted AI gateway, routing and usage accounting

Last updated Sep 12, 2026

Claim Tool

What is New API?

New API is a self-hosted AI gateway and model-management project maintained in the QuantumNous repository. It brings provider channels, access tokens, model restrictions, usage statistics and cost accounting into one interface. Teams supply their own authorized model-provider access and operate the gateway in their chosen environment. The gateway supports several API formats, including OpenAI-compatible requests, Claude Messages and Google Gemini. Compatibility has boundaries: the README marks Gemini-to-OpenAI conversion as text-only without function calling, and OpenAI-compatible to Responses conversion as in development. Test the exact endpoints, streaming behavior and tool calls your application uses before switching traffic. Routing features include weighted channel selection, automatic retry after failures and user-level model rate limits. The dashboard supports request-based, usage-based and cache-hit cost accounting, with token grouping and model-access controls. These controls can help organize usage, but retries and a common API format do not guarantee uninterrupted service or identical behavior across providers. The current repository license is AGPLv3. Docker Compose is the recommended quick-start path in the README, which also documents Docker commands with SQLite or MySQL. Running the software still involves infrastructure, operations and upstream model charges. Review the current license, secure your deployment and validate accounting against provider bills. Compare LiteLLM if you also want a Python SDK or a documented gateway for MCP servers and agents.

New API's Top Features

Key capabilities that make New API stand out.

Self-hosted AI gateway and model management

Provider channels, token groups and model restrictions

OpenAI-compatible, Claude Messages and Gemini format support

Documented limits on protocol conversion

Weighted channel selection and failure retries

User-level model rate limiting

Request, usage and cache-hit cost accounting

Docker Compose deployment documentation

Use Cases

Who benefits most from this tool.

Development Teams

Centralize model access and verify endpoint behavior before changing application traffic.

SaaS Companies

Manage authorized model access, quotas and usage accounting for your application.

DevOps Engineers

Operate provider channels and test retries, rate limits, monitoring and deployment recovery.

Finance Teams

Compare gateway usage accounting with provider bills before using it for internal chargeback.

Developers

Evaluate protocol conversion and model routing with your application’s actual requests.

Explore Top AI Use Cases

Tags

AI gatewayLLM routingmodel managementrate limitingusage accountingself-hostedAGPLv3

New API's Pricing

Open source / self-hosted

AGPLv3 source code for self-hosted deployment. No managed New API subscription price is established here; infrastructure and model-provider usage are separate.

Self-hosted New API

Source available under AGPLv3

Operate your own deployment

  • Review the repository license and deployment documentation.

Infrastructure and model access

Depends on your setup

Hosting, operations and provider charges

  • Supply authorized upstream access and account for provider usage.

Watch-outs

  • A gateway does not include free access to every model.
  • Review the full AGPLv3 terms for the way you modify or operate the software.
  • Protocol conversion has endpoint-specific limits; test your application’s required features.

Top New API Alternatives

Q
QuantumNousopen source
1 Tools
View full profile
1 Tools

User Reviews

Share your thoughts

If you've used this product, share your thoughts with other builders

Recent reviews

Frequently Asked Questions

What is New API used for?
New API centralizes provider channels, model access, rate limits and usage accounting in a self-hosted AI gateway.
What license does New API use?
The current repository LICENSE identifies the GNU Affero General Public License version 3, or AGPLv3. Review the complete license for your deployment and modifications.
Does New API support every provider feature through one API?
No. Its README documents specific conversion limits, including text-only Gemini-to-OpenAI conversion without function calling and OpenAI-compatible to Responses conversion still in development.
Does New API support retries and routing?
The repository lists weighted channel selection, automatic retry on failure and user-level model rate limiting. Test failure behavior and limits with your own providers.
How do I deploy New API?
The README recommends Docker Compose and also shows Docker deployment with SQLite or MySQL. Use the current deployment guide and secure your instance before production traffic.
Is a New API deployment free to operate?
Source code is available under AGPLv3, but hosting, operations and model-provider usage can create costs. A managed cloud plan is not established by the reviewed repository sources.
How does New API compare with LiteLLM?
Both can centralize AI model access. LiteLLM also documents a Python SDK, a proxy gateway, MCP integration and a separate enterprise offering. Compare the exact endpoints, controls, license and operating costs you need.