LLM API gateway / model routing
LiteLLM is a self-hosted open-source AI gateway that exposes 100+ LLM providers through a unified OpenAI-compatible API, with cost tracking, guardrails, load balancing, and logging.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
when you want a TypeScript/MIT gateway with hundreds of providers and no Python runtime
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
when you want an Apache-2.0 Python gateway spanning closed/local/custom models
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.
when you want a Go-native gateway with caching, guardrails, and A/B tests instead of a Python stack
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.
when you need high-throughput enterprise routing with cluster mode and low overhead
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
when you want a Mozilla-maintained Python gateway with virtual keys and budgets
Open-source, OpenAI-compatible LLM gateway you run yourself. One endpoint for 40+ providers, with virtual keys, budgets, and usage tracking.
when you need an explicit LiteLLM-style gateway in Go with OpenAI/Anthropic compatibility
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.
when you need a TypeScript unified provider router with request management and analytics
Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
when your upstreams are consumer coding CLIs rather than official provider APIs
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
when you want web-chat subscriptions exposed as an API instead of per-provider API keys
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.
when you need a gateway for coding-CLI subscriptions with multi-tenant quotas and logging
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.
when you need routing/fusing specifically for Claude Code and AI agents rather than a general provider proxy
One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.
when you need multi-protocol conversion from AI consumer clients instead of direct provider APIs
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.
when your model source is Windsurf/Devin Desktop rather than a standard LLM provider API
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。
when you want GitHub Copilot/Codex sessions exposed as OpenAI/Anthropic-compatible APIs
GitHub Copilot, OpenAI Codex, OpenCode Go, and third-party AI provider gateway with OpenAI and Anthropic API compatibility.
when you want to reuse Claude/ChatGPT subscriptions with local coding tools instead of buying per-token API access
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.
when you need free/community model endpoints routed to coding agents instead of managed provider integrations
Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits.
when your clients are Codex/Claude Code and you want provider-agnostic protocol translation
Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
when you want x402/USDC crypto payment routing without API-key management
The agent-native LLM router for autonomous agents. Every frontier model behind one wallet, <1ms local routing, USDC payments on Base & Solana via x402.
when you need a Rust agent control plane instead of a Python-first general LLM gateway
Developer Control Plane for your AI Agents
when you need a coding-agent control plane rather than a standalone OpenAI-compatible gateway
The control plane for AI coding agents.
when you want Antigravity/Codex/Copilot sessions exposed as Anthropic/OpenAI APIs
Turn Antigravity / codex / github copilot into Anthropic & Openai API compatible server. Usable with Claude Code / Xcode etc.
when you want Claude Code/Cursor to use Antigravity/Codex free backends through protocol translation
Unified Agent Gateway — Enables Claude Code CLI and Cursor IDE to use free AI backends (Antigravity, Codex) through protocol translation
when you need a Java gateway that also handles embeddings, ASR/TTS, and image generation rather than only chat/LLM calls
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。
when you need programmable Claude Code request/response modding and custom model routing
Build mods for Claude Code: Hook any request, modify any response, /model "with-your-custom-model", intelligent model routing using your logic or ours
These projects were analysed and named litellm among their alternatives. The relationship is not symmetric — how litellm rates them is a separate judgement, made when litellm is analysed in its own right.
calls litellm “Production-grade LLM gateway with 100+ APIs, cost tracking, and load balancing; choose over OmniRoute when you need broad enterprise policy/audit features and can live without the free-tier pool.”
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
calls litellm “Choose for a Python-native AI gateway with SDK integrations and cost tracking, if you can accept a heavier runtime than a single binary.”
LLM 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 redistribution system, unifying multiple providers under a single API. Single binary, Docker-ready, with an English UI.
calls litellm “when you need the widest provider/model coverage plus a Python SDK, trading away Bifrost's microsecond-level overhead.”
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
calls litellm “Pick it for a Python SDK + proxy with budgets, guardrails and load balancing across 100+ providers; heavier runtime than a local TS router.”
The agent-native LLM router for autonomous agents. Every frontier model behind one wallet, <1ms local routing, USDC payments on Base & Solana via x402.
calls litellm “Pick when you need a production gateway over official API keys with cost tracking, guardrails and routing, rather than free reverse-engineered providers.”
The official gpt4free repository | various collection of powerful language models | opus 4.6 gpt 5.3 kimi 2.5 deepseek v3.2 gemini 3
calls litellm “Choose when you want a self-hosted gateway with your own provider keys, cost tracking, and 100+ integrations instead of a hosted free-quota service.”
免费大模型API，支持免费调用GPT、DeepSeek等主流模型，免费额度10000点，每日刷新！另付费价格最低官方1-2折！
calls litellm “Choose when you want a general-purpose LLM gateway with cost tracking, guardrails, and load balancing across many LLM APIs, not just coding agents.”
One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.
calls litellm “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.”
Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits.
calls litellm “Choose it when you specifically need a lightweight LLM API gateway with provider routing, cost tracking, and guardrails, not MLflow's full lifecycle platform.”
The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.
calls litellm “General-purpose LLM gateway with cost tracking and guardrails for API providers; choose over seed only if you don't need client-only API emulation.”
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.
calls litellm “Choose when you already have paid provider keys and need cost tracking, guardrails, and load balancing instead of keyless free access.”
Not just GPT4! Easy to use, Self-Hosted, Unlimited and Free WEB API of the latest A.I. like Gemini, DeepSeek, Claude and GPT
calls litellm “Choose it when you need the broadest provider/SDK ecosystem and Python extensibility, accepting a heavier Python deployment.”
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.