FreeAIRepo
← All paid tools

Best free AnyAPI alternatives (open source, 2026)

Updated · 20 repos compared

Short answer

The best free AnyAPI alternative for most people is litellm (62k GitHub stars). kong works on a Mac, according to the project. All 20 options below are open source and run on your own computer or server, so there's no subscription.

AnyAPI (one API for hundreds of AI models) is a paid, closed-source product. The open-source projects below do the same job and run on your own computer or server.

Top picks

  1. 1. Best for: Best overalllitellm62k stars · license not detected · updated today
    Editor's pick#47 TRENDING

    The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropi

    Needs:
    Hardware needs not stated by the project
    Trade-off
    Better than AnyAPI: very active development. Worse: license not detected by GitHub; check it before commercial use.
  2. 2. Best for: Also excellentnew-api50k stars · AGPL-3.0 · updated today
    Editor's pick

    A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for pers

    Needs:
    Hardware needs not stated by the project
    Trade-off
    Better than AnyAPI: very active development. Worse: AGPL: if you run it as a service, you must share your changes.
  3. 3. Best for: Mac userskong44k stars · Apache-2.0 · updated 4d ago

    🦍 The API and AI Gateway

    Needs:
    works on Mac (as stated by the project)
    Trade-off
    Better than AnyAPI: a permissive Apache-2.0 license, very active development. Worse: you install and run it yourself instead of AnyAPI's hosted app.

Comparison

ToolStarsOpen licenseSelf-hostRuns on MacGPU memoryLast update
AAnyAPIPaid · cloud only–browsernone–
litellmEditor's pick#47 TRENDINGThe fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropi62k?today
one-apiEditor's pickLLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。LLM API management & key 37k?9mo ago
new-apiEditor's pickA unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for pers50k?today
gatewayEditor's pickA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.13k?5mo ago
Free-GPT-Grok-Gemini-Claude-APIAnyAPI alternativeAccess GPT-5, o4, Claude 4.5 & Gemini 3 via one API. The best OpenRouter alternative. 国内直连/无需梯子/支持支付宝/Crypto. Get Free Key:216?10mo ago
dsh-our-free-model在 dsh 里装上这个插件即可，无需登录、注册或填 API Key，就能使用包括 DeepSeek V4.1 Flash、Kimi K3 在内的前沿模型——完全免费，不限量。 All you do is install this plugin in dsh: no login, no sign-up, no API key — the frontier models are just there,37k?today
kong🦍 The API and AI Gateway44k?4d ago
llm-action本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）25k?8d ago
TensorRT-LLMTensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT 15k?today
tykOpen Source API and AI Gateway supporting REST, GraphQL, TCP, gRPC and MCP (Model Context Protocol)11k?today
OpenLLMRun any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.13k?today
llm-gatewayOpen Source LLM Gateway 🦚7.6k?2d ago
planoPlano is an AI-native proxy server and data plane for agentic apps. Smart LLM routing, observability, agent orchestration, and guardrails so you stay focused on your agents core logic.7.1k?15d ago
vllmA high-throughput and memory-efficient inference and serving engine for LLMs95k?today
BentoMLThe easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!8.9k?today
evolution-apiEvolution API is an open-source WhatsApp integration API9.9k?3mo ago
opikDebug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.23k?today
promptfooTest your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line 26k?today
ColossalAIMaking large AI models cheaper, faster and more accessible41k?today
quivrAn open-source engine that turns continuous content streams into search and monitoring. Durable ingestion, hybrid search, alerts, and plugins for formats, models and business rules.40k?1d ago

✓ yes · ✗ no · – not stated by the project. Hardware details may be incomplete.

AnyAPI vs open source: what you give up

  • Setup. AnyAPI is ready as soon as you sign up. These projects need installing, usually with Python, Node or Docker.
  • Hardware. Most of these don't state hardware needs; heavier models run much faster with a GPU. 3 mention Mac support.
  • Polish and support. Paid products usually have a smoother interface, managed updates and customer support. Open source gives you privacy, no usage limits and no monthly bill.
  • Maintenance. 16 of 20 were updated in the last 30 days.
  • License. 16 of 20 use a standard open-source license (MIT, Apache, GPL and similar). Check the license before commercial use.

FAQ

Is there a free alternative to AnyAPI?

Yes. We list 20 free, open-source GitHub projects that do the same job as AnyAPI. The most popular are vllm, litellm and new-api.

What is the best open-source AnyAPI alternative?

It depends on your setup. Best overall: litellm. Also excellent: new-api. Mac users: kong. Compare GitHub stars, license and hardware needs in the table on this page.

Can I run an AnyAPI alternative on a Mac?

Yes. According to the projects, kong, vllm and quivr run on macOS.

Do I need a GPU to replace AnyAPI?

Most of these don't state hardware needs. Expect heavier models to run much faster with a GPU.

Are these AnyAPI alternatives really free?

Yes. All 20 are open source on GitHub, and projects that need a paid API key are left out. 16 use a standard open-source license such as MIT, Apache or GPL; check the license before commercial use.

Related: Inference & serving

Context.dev alternativesFirecrawl alternativesMrScraper alternatives