List of Permanent Free LLM API (API Keys)
Streamline your workflow with Lynkr, a CLI tool that acts as an HTTP proxy for efficient code interactions using Claude Code CLI.
Use your Claude and ChatGPT subscriptions in Cursor, Cline, Aider, Claude Code and the Agent SDK: one local endpoint, failover, pooling.
Daily-updated list of free AI models (free LLM APIs), ranked by quality with live status. Plus one OpenAI-compatible endpoint that routes to the best one.
Token Bank — the local LLM gateway that sits between your AI agents and every provider. Know where tokens go · Spend less with smart routing to Ollama, Groq, GitHub Models · Earn by sharing idle quota on a community P2P network. One-click onboarding for Cursor, Claude Code, Codex CLI, Gemini CLI — no agent changes. Full trace, seamless model swap
Open-source AI backend control plane for model routing, agent tools, OpenAI-compatible APIs, and private workspaces.
在原版 ChatGPT / Codex 同时使用 DeepSeek V4.1 Flash 与 GPT。Local loopback router, native Responses API, full tool loops, no fork.
Model router for AI coding agents: installs routing rules, 8 subagents, hooks and a CLI runner so your AI picks model and effort per task and saves tokens
Open-source AI gateway for routing multiple providers through one unified API.
🗼 中转塔台 (Relay Tower): 专为 Sub2API 打造的开源大模型监控调度网关，内置全栈容器编排。支持 Prompt Cache 单主独占切线、流式 TTFT 容灾熔断、Telegram 手机端秒级调度，全面兼容 New-API 上游
Self-hosted AI gateway & LLM proxy: zero-downtime failover, MOA Fusion, token-saving compression. One OpenAI-compatible endpoint for Claude Code, Cursor, Codex, Cline + 40+ providers.
Local multi-model fusion gateway for Codex and OpenAI-compatible API relays
Cut Claude Code & Codex token spend: routes lookups and test runs to cheaper models, converts docs to compact Markdown, shows cost and savings live in the statusline.
One OpenAI-compatible endpoint for all your free LLM keys: quality-waterfall routing with automatic failover
Open-source intelligent router for automatically discovering, ranking, health-checking, and routing requests to the best available free AI models.
Codex Desktop model router: when your 5-hour quota hits 0%, type /dsk to continue the same thread on DeepSeek - with context, MCP tools, and shell intact. No restart, no new chat; /gpt switches back. Unofficial.
⚡ Multi-provider LLM router: 8+ models (OpenAI, Anthropic, Gemini, Groq, Cerebras), WhatsApp/Telegram/Alexa, Hindi/Bengali support, 18 MCP browser tools. GCP-prod. Node.js + Python. MIT.
FreeDSH — free-first multi-model routing, safe core updates and pt-BR/Windows support for DeepSeek Harness. Installable as a DSH bundle (dsh plugin add). Unofficial project.
jevkit: fast typed decisions for agents. CLI and MCP tools (route, triage, guard, grep, rank, compact, judge) on TypeSafe Jev. Zero dependencies.
To associate your repository with the llm-router topic, visit your repo's landing page and select "manage topics."