cheaper-inference/OmniRoute

★ 82,401⑂ 12,169

Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax.

Open on GitHub ↗Homepage ↗

About cheaper-inference/OmniRoute

cheaper-inference/OmniRoute is an open-source project on GitHub, mainly written in TypeScript. Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. It currently holds 82,401 stars and 12,169 forks with 457 open issues, and was last pushed on 2026-10-29 (repository created 2026-02-13).

Project Overview

Git Homed tracks it on the AI Agent Skills Trending board and on the AI AI Agent Skills Trending list.

GitHub Repository Details

Repository cheaper-inference/OmniRoute · default branch release/v3.8.53 · size 2454354 KB · watchers 472 · source: GitHub REST API and repository README

README

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/OmniRoute Dashboard

🚀 OmniRoute — The Free AI Gateway

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/OmniRoute — Never stop coding. Every AI tool → 377 providers — 150+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot & Antigravity into FREE Claude / GPT / Gemini with auto-fallback. RTK + Caveman stacked compression saves 15–95% tokens (~89% avg) — never hit limits. 377 AI providers · 150+ free tiers · ~1.62B free tokens/mo · 20 routing strategies · $0 to start.

💰 ~1.62B Tokens / Month Across Third-Party Free Tiers

Bring your own provider accounts. This is an estimated aggregate across separately eligible third-party free tiers, not a token grant from OmniRoute. Sign up, obtain credentials where required, and connect the providers you can use; each provider controls its limits, availability, and terms.

> Stacking free tiers by hand is painful — dozens of SDKs, dozens of rate limits, and no idea how much you actually have. OmniRoute catalogs 484 free-tier entries across 34 recurring pool keys and computes the token headline from the 17 pools with a published positive monthly budget plus five per-model Groq caps, deduplicated by shared pool. Quotas that only open after a regional identity check (today: ModelScope) are shown apart, +~6M behind regional identity verification, and never summed into the headline. The result stays visible on the dashboard (/dashboard/free-tiers).

Animated summary of the live /dashboard/free-tiers page. Full methodology (pool dedupe, credit tiers, provider terms): docs/reference/FREE_TIERS.md.

> _{These figures are re-audited every two weeks against the live catalog and move both ways — a provider ends a free tier and the number drops; a new one lands and it climbs. We publish what the catalog actually computes, never a rounded-up best case.}

⭐ Star the repo if OMNIROUTE helped you save money and make your work easier.

💬 Join the community

👋 Follow the maintainer — get new providers, releases & tips first:

Questions, provider tips, roadmap & support → Discord · Telegram · WhatsApp 🌍 Global / 🇧🇷 Brasil / Portal

📈 The Gateway Keeps Growing

| | v3.8.50 | v3.8.51 | v3.8.53+ | | ------------------------- | :-----------------------: | :---------: | :-------------------: | | 🌐 Providers | 352 | 358 | 377 | | 🧠 Unique chat model IDs | 1320 | 1374 | 1475 | | 🖼️ Modality Bridge | 🆕 vision + audio + video | ✓ | ✓ | | 📡 Radar free catalog | 🆕 opt-in | ✓ | ✓ | | ⚖️ Quota-aware scheduling | 🆕 Quota-Share | ✓ | ✓ | | 📊 Quota telemetry | 🆕 live | ✓ | ✓ | | 🧰 Headless mode | — | — | 🆕 serve --headless | | 🛤️ LTS rail infra | — | — | 🆕 release channels | | 🔎 Model discovery API | — | — | 🆕 /v1/models/query |

→ Roadmap — riding the rail to v3.9.0 LTS

🧩 Available

🚀 Start	🚀 Quick Start	📦 Install	🆓 Connect a provider
💡 Learn	💥 The Promise	🤔 Why OmniRoute	🏆 What Sets Apart
⚙️ Features	🎯 Combos	🌐 Providers	🔌 CLI & MCP
	🗜️ Compression	🖥️ Where It Runs	🔒 Private
👀 See it	🎬 In Action	✨ What's New	🤖 Compatible CLIs
💚 Support	💚 Support / Donate	💬 Community	💖 Sponsors
📦 Project	🛠️ Tech Stack	📖 Docs	👥 Contributors

🌐 In 67 languages

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/English (en)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Português — Brasil (pt-BR)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Português (pt)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Español (es)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Français (fr)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Italiano (it)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Deutsch (de)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Nederlands (nl)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Русский (ru)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Українська (uk-UA)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Polski (pl)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Čeština (cs)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Slovenčina (sk)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Română (ro)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Magyar (hu)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Български (bg)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Dansk (da)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Suomi (fi)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Norsk (no)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Svenska (sv)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/中文 — 简体 (zh-CN)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/中文 — 繁體 (zh-TW)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/日本語 (ja)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/한국어 (ko)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/ไทย (th)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Tiếng Việt (vi)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Bahasa Indonesia (id)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Bahasa Melayu (ms)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Filipino (phi)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/हिन्दी (hi)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/ગુજરાતી (gu)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/मराठी (mr)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/தமிழ் (ta)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/తెలుగు (te)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/বাংলা (bn)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/اردو (ur)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/فارسی (fa)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/العربية (ar)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/עברית (he)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Türkçe (tr)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Azərbaycan (az)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Kiswahili (sw)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Ελληνικά (el)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Hrvatski (hr)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Српски (sr)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Lietuvių (lt)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Eesti (et)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Latviešu (lv)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Slovenščina (sl)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Malti (mt)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Gaeilge (ga)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/ಕನ್ನಡ (kn)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/മലയാളം (ml)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/ଓଡ଼ିଆ (or)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/ਪੰਜਾਬੀ (pa)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/नेपाली (ne)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/සිංහල (si)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/မြန်မာ (my)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/ខ្មែរ (km)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Hausa (ha)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Yorùbá (yo)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Igbo (ig)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/አማርኛ (am)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Oʻzbekcha (uz)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/ქართული (ka)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Հայերեն (hy)

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Bosanski (bs)

🆓 Install, connect a provider, then route through one endpoint

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/Three steps: install and start OmniRoute, connect an eligible provider with your own account or API key, then point your tool at localhost:20128/v1 using an OmniRoute API key and model auto. Routing depends on available eligible connections and provider limits.

# After connecting a provider, copy your OmniRoute key from Dashboard → Endpoints:
curl http://localhost:20128/v1/chat/completions \
  -H "Authorization: Bearer YOUR_OMNIROUTE_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"auto","messages":[{"role":"user","content":"Hello!"}]}'

_{auto needs an eligible route. A fresh installation can have no eligible keyless targets, and a keyless provider may reject third-party clients. Providers marked tos: avoid, including Kiro, are excluded from automatic routing by default; connecting an account does not override that setting. See the Free Tiers Guide before choosing a provider.}

_{📦 Copy-paste quickstart scripts for Python, Node.js, PHP, and cURL → examples/quickstart/}

💥 The Promise

🤔 Why OmniRoute?

https://github.com/cheaper-inference/OmniRoute/blob/HEAD/OmniRoute request flow: your IDE or CLI (Claude Code, Cursor, Cline…) calls one local endpoint (http://localhost:20128/v1); the OmniRoute Smart Router (RTK + Caveman compression, 20 routing strategies, circuit breakers, TLS stealth, MCP, A2A, guardrails) can fall back across 4 provider tiers while an eligible healthy target remains — Tier 1 Subscription, Tier 2 API Key, Tier 3 Cheap and Tier 4 Free.

🤝 Supported by our Open Source Friends

Want to join as an Open Source Friend? These are the companies that back open source and help keep OmniRoute moving — and we say publicly where every token they give us goes. Reach out: [email protected]

Kimi
_{Moonshot AI} Thanks to Kimi (Moonshot AI), our founding Open Source Friend, for backing this project! Kimi is the AI lab behind the open-weight K2 and K3 model families — Kimi K3 delivers a 1M-token context window, native vision and frontier-level coding at a fraction of closed-model prices, and works out of the box with Claude Code, Codex and every coding tool OmniRoute serves.

What Kimi's support powers: Kimi's API credits power OmniRoute's AI-validated release pipeline — the merge validation powered by Kimi K3 stage that reviews every pull request before it ships — plus day-to-day feature development. First-class Kimi support ships on both rails: the direct Kimi API (kimi-k3) and the Kimi Code coding plan (OAuth and API key). OmniRoute is also the first Brazilian open-source project in Kimi's support program. Get a Kimi API key with 15% extra credits →