Unified OpenAI-compatible API
Provides a single endpoint described as 100% OpenAI compatible for accessing AI providers through a common application interface.
New API
Freemium
New API is an open-source, self-hosted AI gateway for developers and teams. It provides a unified OpenAI-compatible endpoint for connecting multiple AI providers, selecting models, configuring channels, and monitoring usage on their own infrastructure.
什么是 New API？
New API is an open-source, self-hosted AI gateway and asset management system for developers and teams. It centralizes access to more than 30 AI providers, including OpenAI, Claude, and Gemini, through a unified interface and a 100% OpenAI-compatible API endpoint.
The gateway is designed to simplify provider management and application integration. Users can configure provider channels, set priority settings, select from more than 100 listed models, and connect existing applications through a common API. Because it is self-hosted, deployment is intended for infrastructure controlled by the user or organization.
New API also includes usage analytics for monitoring usage, tracking costs, and reviewing performance. Its plugin marketplace extends the gateway with generation tasks such as image, video, music, and lyrics generation.
New API 能做什么？
Multi-provider access
Connects more than 30 AI providers, including OpenAI, Claude, Gemini, and other providers listed by the product.
Model selection
Offers access to more than 100 models across multiple providers, with examples shown on the product site including GPT, Claude, Gemini, DeepSeek, Llama, and Mistral models.
Channel configuration and routing
Lets users add and configure provider channels with priority settings, supporting organized provider management and routing choices.
Usage and cost analytics
Provides analytics for monitoring usage, tracking costs, and reviewing performance so teams can evaluate their AI infrastructure.
Generation task plugins
The official plugin marketplace includes adapters and generation plugins for tasks such as image, video, music, and lyrics generation, with listed plugins for services including Google Veo, Sora, Kling, and SunoAPI.
使用场景
“Consolidating provider access”
Teams using several AI services can place those providers behind one gateway and use a common API surface instead of wiring each application to separate provider endpoints.
“Integrating existing AI applications”
Developers can connect applications that use the OpenAI-compatible API pattern, while managing provider channels and model choices centrally.
“Operating a self-hosted AI layer”
Organizations that want the gateway on infrastructure they control can deploy New API as a self-hosted access layer for their AI applications.
“Comparing model and provider options”
Teams can select from models across multiple providers and configure channel priorities when evaluating different services for an application.
“Adding media-generation capabilities”
Users can extend the gateway with marketplace plugins for supported generation tasks, including video, image, music, and lyrics workflows.
常见问题
What is New API?
New API is an open-source, self-hosted AI gateway and asset management system that connects multiple AI providers through a unified interface.
Which providers does New API support?
The site says New API supports more than 30 AI providers and specifically names OpenAI, Claude, and Gemini. Its plugin marketplace also lists adapters or generation plugins for services such as Google Veo, OpenAI Sora, Kling, Doubao, and SunoAPI.
Does New API provide an OpenAI-compatible API?
Yes. The product describes its endpoint as 100% OpenAI compatible, allowing applications to integrate through a common API interface.
Can New API track AI usage and costs?
Yes. Its usage analytics feature is described as supporting usage monitoring, cost tracking, and performance optimization.
Is pricing published on the website?
The supplied pricing URL currently returns a 404 page, so verified prices, plan limits, and billing terms are not available from the provided sources.
快速信息
- Product type
- Open-source, self-hosted AI gateway
- Primary users
- Developers and teams
- Provider coverage
- 30+ AI providers
- Model coverage
- 100+ models
- API format
- OpenAI-compatible endpoint
- Source domain
- newapi.ai
New API 替代品
LiteLLM
docs.litellm.ai
通过兼容 OpenAI 的 Python SDK 或代理调用和管理 100 多种 LLM。
AIMLAPI
aimlapi.com
AIMLAPI provides one API and billing key for accessing a catalog of AI models for chat, reasoning, image, video, audio, voice, search, embeddings, code, and related tasks. It is intended for developers and teams that want to compare and use models from multiple providers through a common platform.
ZenMux
zenmux.ai
面向企业的 LLM 平台，提供统一多模型 API 与智能路由
Router by Ramp
router.com
Router by Ramp is an LLM gateway that gives applications one API endpoint for accessing models from multiple providers. It routes eligible requests based on cost, quality, and availability while providing usage and spend visibility.
CometAPI
cometapi.com
CometAPI is a unified, OpenAI-compatible API layer for accessing more than 500 text, image, video, and audio models through one key. It helps developers and teams compare models, centralize billing, and switch providers without maintaining separate vendor integrations.
Vercel AI Gateway
vercel.com
Vercel AI Gateway gives developers one API surface for hundreds of text, image, video, and audio models across multiple providers. It centralizes model access, routing, fallback, billing, and observability while supporting AI SDK, OpenAI, and Anthropic workflows.