decolua/9router Alternatives

Use it when you want a drop-in peer with an even wider free-provider pool and MIT license, if token compression is less important.

Never stop coding. Free MIT AI gateway: one endpoint, 359 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by hundreds of contributors

Use it when you want a vendor-neutral local router for AI agents that you configure fully yourself rather than using 9Router's prebuilt free/token-saving pipeline.

One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.

Use it when you prefer a Go-based proxy that turns free subscription backends into compatible APIs and don't need 9Router's token-saver.

Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build, Muse Code, Davin as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini Series, GPT Series, Grok Series, Claude model through API

Use it when the clients you must support are Codex and Claude Code and you want a lightweight universal provider proxy for any LLM.

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

Use it if GPL-3.0 is acceptable and you need client-to-API protocol conversion across Antigravity, Codex, Grok and custom providers.

Self-hosted multi-protocol AI API proxy for Antigravity, Codex, Grok, Kiro, OpenAI, Claude, and custom providers. Supports OpenAI-compatible API, Claude API, Gemini protocol conversion, GPT, Grok Build, Claude Opus, Gemini Pro, Kimi, MiniMax, provider pools, smart routing, and automatic failover.

Use it when you need a self-hosted shared gateway with a web console, request logs and spend quotas instead of a personal free-model router.

Self-hosted AI gateway for coding CLIs — one OpenAI/Claude/Gemini/Codex-compatible endpoint, with a multi-tenant web console, request logs, and spend quotas.

Use it when you need a neutral model gateway spanning closed, open-source and local models with a Python control plane rather than a coding-tool-specific free router.

Experiential is the open source, zero markup gateway for BYOK, self-hosted and 1000+ marketplace models. It learns from your traffic to cut costs, recommend better models, and train a specialized model you own.

Use it when you want a high-throughput, observable LLM gateway for many providers with logging and cost controls instead of free coding-agent session tricks.

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, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

Use it when you need an enterprise cluster-mode AI gateway focused on low latency and guardrails rather than free coding-account routing.

Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.

Use it when you want a standard unified API gateway across multiple providers with management and analytics, without free-coding-agent routing.

Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.

Use it when you want a LiteLLM-style Go gateway with OpenAI and Anthropic compatibility for general workloads, rather than free-coding routing.

AI gateway / AI control plane / AI proxy written in Go. Unified OpenAI-compatible and Anthropic-compatible API for OpenAI, Anthropic, Gemini, Groq, xAI, Ollama, vLLM and more. A LiteLLM alternative with observability, guardrails, streaming, cost tracking, intelligent routing, sticky sessions, failover, real-time logs and usage tracking. Prod ready.

Use it when self-hosting an OpenAI-compatible gateway with virtual keys and budgets in Python is more important than coding-agent/free features.

Open-source, OpenAI-compatible LLM gateway you run yourself. One endpoint for 40+ providers, with virtual keys, budgets, and usage tracking.

Use it when you want a Go-native enterprise gateway with caching, guardrails and A/B testing rather than a free coding-agent router.

Unified AI Gateway for 30+ LLMs (OpenAI, Anthropic, Bedrock, Azure etc) with Caching, Guardrails, A/B test & cost controls. Go-native Fastest & Scalable AI Gateway LiteLLM & Kong AI Gateway alternative.

Use it when you need an enterprise API platform exposing chat, embedding, speech and image models with billing and rate-limit management under Java.

Bella OpenAPI是一个提供了丰富的AI调用能力的API网关，可类比openrouter，与之不同的是除了提供聊天补全(chat-completion)能力外，还提供了文本向量化(text-embedding)、语音识别(ASR)、语音合成(TTS)、文生图、图生图等多种AI能力，同时集成了计费、限流和资源管理功能。且集成的所有能力都经过了大规模生产环境的验证。

Use it only when your upstream is specifically a GitHub Copilot/Codex/OpenCode account you want to reuse through an OpenAI/Anthropic endpoint.

GitHub Copilot, OpenAI Codex, OpenCode Go, and third-party AI provider gateway with OpenAI and Anthropic API compatibility.

Use it only when a Windsurf/Devin Desktop subscription is the upstream you want to expose to ordinary AI clients.

Turn Windsurf / Devin Desktop's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Kimi, GLM, SWE) into OpenAI-, Anthropic- & Gemini-compatible APIs. Zero-dependency self-hosted reverse proxy for Claude Code, Cline & Cursor. 把 Windsurf/Devin 云端 100+ 模型变成三套兼容 API。

Use it only for zero-cost DeepSeek/GLM/Kimi/Qwen web-UI endpoints via an OpenAI-compatible API, without 9Router's broad fallback/token handling.

Chat2API enables zero-cost access to leading AI models by leveraging official web UIs. It supports providers such as DeepSeek, GLM, Kimi, MiniMax, Qwen, and Z.ai, and seamlessly integrates with tools like openlcaw, Cline, and Roo-Code.

Use it only when the upstreams are your own Claude and ChatGPT subscriptions and you want a local proxy for those two.

Use your Claude and ChatGPT subscriptions in Cursor, Cline, Aider, Claude Code and the Agent SDK — at subscription pricing, not per-token API bills. One local Anthropic + OpenAI-compatible endpoint: either plan answers either wire shape, auto-failover when one hits its limit, multi-seat pooling, live Claude Code drift tracking.

Use it only when you're turning Antigravity/Codex/Copilot accounts into an Anthropic/OpenAI endpoint for Claude Code or Xcode.

Turn Antigravity / codex / github copilot into Anthropic & Openai API compatible server. Usable with Claude Code / Xcode etc.

Use it only when your target sources are Antigravity/Codex and clients are Claude Code/Cursor; not a broad 40-provider router.

Unified Agent Gateway — Enables Claude Code CLI and Cursor IDE to use free AI backends (Antigravity, Codex) through protocol translation

Use it when you need custom request/response hooks and routing logic inside Claude Code rather than a turnkey multi-provider free router.

Build mods for Claude Code: Hook any request, modify any response, /model "with-your-custom-model", intelligent model routing using your logic or ours