무료 오픈소스 AI Gateway

코딩을 멈추지 마세요.

Route across 352 providers through one OpenAI-compatible endpoint, with automatic fallback.

Start with Cheaper Inference Self-host OmniRoute

352 providers
90+ free tiers
15–95% eligible tokens saved

OpenAI-compatible Free and open source59.6k stars

6 models

Direct list prices compared with Cheaper Inference prices by model
Model	Input price	Output price	Savings
gpt-5.6-lunaOpenAI · text	~~$0.20~~$0.08/ 1M tokens	~~$1.20~~$0.48/ 1M tokens	60% off
gpt-5.6-solOpenAI · text	~~$2.00~~$1.00/ 1M tokens	~~$10.00~~$5.00/ 1M tokens	50% off
glm-5.3Z.ai · text	~~$1.40~~$0.77/ 1M tokens	~~$4.40~~$2.42/ 1M tokens	45% off
deepseek-v4-flashDeepSeek · text	~~$0.083~~$0.05/ 1M tokens	~~$0.18~~$0.11/ 1M tokens	40% off
deepseek-v4-flash-0731DeepSeek · text	~~$0.067~~$0.04/ 1M tokens	~~$0.18~~$0.11/ 1M tokens	40% off
glm-5.3-flashZ.ai · text	~~$0.071~~$0.05/ 1M tokens	~~$0.24~~$0.17/ 1M tokens	30% off

약속

하나의 엔드포인트. 개발을 멈추지 마세요.

한도에 도달하지 마세요

268개의 제공업체에 밀리초 단위로 자동 폴백. 쿼터 초과? 다음 제공업체가 이어받습니다. 다운타임 없음.

최대 95% 토큰 절약

A 12-engine pipeline reduces eligible context by 15–95%. The documented tool-heavy example reduced it by ~89%.

$0으로 시작

90+ free tiers and 56 recurring or keyless free-forever providers. No credit card needed for the keyless quick start.

35 supported integrations

16개 이상의 코딩 에이전트. Claude Code, Codex, Cursor, Cline, Copilot, Antigravity. 하나의 설정으로.

하나의 엔드포인트

OpenAI ↔ Claude ↔ Gemini ↔ Responses API 변환. 어떤 도구든 /v1을 향하면 바로 작동합니다.

프로덕션 수준

서킷 브레이커, TLS 스텔스, MCP（95개 도구）, A2A, 메모리, 가드레일, 평가. 25,000+개의 테스트가 뒷받침합니다.

카탈로그

All behind one endpoint.

A catalog spanning chat, media, search, local runtimes, cloud agents and system integrations.

352 providers

14 Search12 Audio-only2 Upstream proxy3 Cloud agent1 System

25OAuthClaude Code, Codex, Cursor, GitHub Copilot, Kimi Code…

233API keyOpenAI, Anthropic, Groq, NVIDIA, Cerebras, Mistral…

35Web cookieChatGPT Web, Claude Web, Gemini Web, Grok Web…

14LocalOllama, LM Studio, vLLM, llama.cpp…

13No authenticationOpenCode Free, Felo, Pollinations and other keyless routes…

Explore the provider reference

60초 안에 시작

세 가지 명령. 설정 없음.

Install the package, launch the gateway, then point any OpenAI-compatible client at port 20128.

Provider catalog: 352
Routing strategies: 19
Local endpoint: :20128/v1

Step 1: Install

Install the `omniroute` npm package globally.

omniroute: install

$ npm install -g omnirouteadded 1 package

Step 2: Run

Launch the API and dashboard together on port 20128.

omniroute: run

$ omniroute▸ dashboard ✓ http://localhost:20128/dashboard▸ api ...... ✓ serving on :20128

Step 3: Connect your tool

Use `http://localhost:20128/v1`; the keyless `auto` route works on a fresh install.

omniroute: connect

$ curl localhost:20128/v1/models✓ models listed

배터리 포함

모든 것이 내장. 애드온 없음.

라우팅, 복원력, 무료 할당량 소진, 압축, 에이전트 프로토콜. 단일 바이너리, 연결할 플러그인 없음.

스마트 콤보

Set a model to `auto` or build your own combo with 19 strategies and tiered fallback.

Use a ready-made mode or combine 19 strategies around the goal that matters.

메모리

영구적인 대화 메모리. FTS5 키워드 + Qdrant 벡터 검색, 내장.

3-layer resilience

적절한 수준에서 실패하세요. 전체가 아닌. 프로바이더별 서킷 브레이커, 연결별 쿨다운, 모델별 잠금. 다른 키와 모델은 계속 서비스됩니다.

무료 할당량

Pool-deduped accounting across 90+ free tiers.

월 ~1.51B 무료 토큰.

압축

12 composable engines for tool output, context and response style.

Reduce eligible tokens by 15–95%.

MCP Server

A built-in server exposing 110 gateway tools across 33 scopes.

110 tools · 33 scopes · stdio / HTTP

A2A Protocol

A JSON-RPC agent server with 6 skills.

6 skills · JSON-RPC 2.0 · Agent Card

CombosResilienceFree quotaCompressionMCPA2AMemoryProxy controlsGuardrailsCloud agentsEvalsSemantic cacheSkillsAnalytics

Client compatibility

Keep your existing coding tools.

Point an OpenAI-compatible CLI or editor at one local base URL; OmniRoute handles the providers behind it.

Claude Code

Codex CLI

Cursor

Cline

GitHub Copilot

Gemini CLI

OpenCode

Kilo Code

Factory Droid

Continue

Roo Code

Antigravity

Aider

OpenClaw

Goose

Grok Build

Windsurf

Devin CLI

http://localhost:20128/v1

request.sh

curl http://localhost:20128/v1/chat/completions \
  -H "Authorization: Bearer $OMNIROUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"auto","messages":[{"role":"user","content":"Hello"}]}'

신규

이제 VS Code Copilot Chat에서도 사용 가능

OmniCopilot 확장 프로그램을 설치하면 이미 사용 중인 모델 선택기에 모든 OmniRoute 모델이 바로 나타납니다. 새로운 사이드바도, 새로운 채팅 UI도 필요 없습니다.

Official Marketplace

Works in VS Code stable and Insiders. Install from the Marketplace or Extensions view.

Open VSX Registry

공식 스토어를 사용하지 않는 VS Code 포크용. Cursor, Windsurf, VSCodium, Theia, code-server, Gitpod 등.

Copilot 요금제가 필요 없습니다

VS Code 1.122부터는 GitHub 로그인이나 Copilot 구독 없이도 provider 모델을 사용할 수 있습니다. OmniRoute의 무료 모델로 agent mode, tool calling, vision까지.

VS Code Marketplace Open VSX Registry OmniCopilot source

일상의 현실

왜 OmniRoute인가

코딩 AI의 모든 고통에 내장된 해결책이 있습니다. 스크립트도, 감시도 불필요합니다.

Without routing

With OmniRoute

Quota expires unused

Track and drain the allowance you already have

Rate limits stop you mid-task

4-tier auto-fallback in milliseconds

Tool output burns tokens

12-engine compression, 15–95% on eligible content

Expensive APIs add up

Cost-optimized routing can pick the cheapest eligible target

Each tool needs its own setup

One endpoint and one dashboard

A provider is unavailable from your network

Proxy scopes and client-fingerprint controls

One dead key breaks a provider

Breaker, cooldown and lockout isolate the failure

A team shares one subscription

Key pools and fair-share quotas

You need local control of routing data

Local-first storage with encrypted credentials

No spend or health visibility

Usage, quota, savings and latency analytics

1. Subscription2. API key3. Cheap4. Free

솔직한 비교

비교

Capabilities checked against the linked project documentation on 2026-08-30.

Capability	OmniRoute (opens in a new tab)	9Router (opens in a new tab)	LiteLLM (opens in a new tab)	CLIProxyAPI (opens in a new tab)
Providers	352	40+	100+	8+ upstreams
Routing strategies	19	3-tier	retry / priority	round-robin / fill-first
Tiered fallback with UI	Yes	Yes	Manual policy	Multi-account
Token compression	12 engines · 15–95%	RTK / Headroom / Caveman	No built-in pipeline	HTTP compression

Capability	OmniRoute (opens in a new tab)	9Router (opens in a new tab)	LiteLLM (opens in a new tab)	CLIProxyAPI (opens in a new tab)
Built-in MCP server	110 gateway tools	No	MCP client / gateway	No
A2A protocol	Server · 6 skills	No	A2A client / gateway	No
Cloud agents	Codex / Cursor / Devin / Jules	No	No	Sidecar integrations

Capability	OmniRoute (opens in a new tab)	9Router (opens in a new tab)	LiteLLM (opens in a new tab)	CLIProxyAPI (opens in a new tab)
Failure-isolation layers	3: provider / connection / model	Cooldown	Cooldown / retry	Cooldown
Persistent memory	FTS5 + vector	No	Semantic cache	No
Guardrails	PII / injection / vision	No	Yes	Cloaking controls
Eval framework	Built in	No	No	No
TLS fingerprint controls	wreq-js	No	No	uTLS

Capability	OmniRoute (opens in a new tab)	9Router (opens in a new tab)	LiteLLM (opens in a new tab)	CLIProxyAPI (opens in a new tab)
Dashboard stack	Next.js 16	Next.js 16	Next.js	Next.js / React
UI locales	42	10	Not documented	3
OAuth providers	25	6	SSO	CLI auth
Self-hostable	Yes	Yes	Yes	Yes
License	MIT	MIT	MIT + enterprise	MIT

Public README and official documentation snapshot; verify linked sources before purchase or deployment decisions.

어디서든 실행

9 supported ways to run OmniRoute.

하나의 코드베이스, 9가지 실행 방법. 노트북, 서버, 스마트폰, 플러그인. 설치 명령을 선택하면 포트 20128에서 서비스됩니다.

npm

npm install -g omnirouteOpen guide

Docker

docker run … diegosouzapw/omnirouteOpen guide

Desktop

데스크톱

npm run electron:buildOpen guide

ARM

native arm64

Android · Termux

Termux

pkg install nodejs && npx -y omnirouteOpen guide

PWA

Add to Home ScreenOpen guide

OpenCode plugin

OpenCode 플러그인

@omniroute/opencode-providerOpen guide

VS Code

Install OmniCopilotOpen guide

From source

소스

npm install && npm run devOpen guide

Routing

Choose an `auto` route.

Use a ready-made mode or combine 19 strategies around the goal that matters.

Model · fallback enabledautoBalanced default

OpenAI-compatible request

curl http://localhost:20128/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"auto","messages":[{"role":"user","content":"Write a TypeScript retry helper."}]}'

Drain subscription quota

Use quota you already have before touching paid APIs.

priority · fill-first

Spread load

Balance traffic across keys and accounts to reduce rate-limit pressure.

weighted · round-robin · p2c · least-used · headroom

Cheapest first

Route to the lowest-cost eligible target.

cost-optimized

Context-aware

Keep long contexts on models that fit, then relay when needed.

context-relay · context-optimized · cache-optimized

Randomized

Distribute eligible traffic across targets.

random · strict-random

Adaptive scoring

Use 15-factor scoring, last-known-good and reset-aware windows.

reset-window · reset-aware · lkgp · auto · fusion · pipeline

무료 토큰, 정직하게 집계

월 ~1.51B 무료 토큰.

455 catalog entries are deduplicated into 40 recurring pools; only published positive budgets feed the headline.

1.51B

Pool-deduped accounting keeps shared quotas from being counted more than once. No-cap providers stay visible without inflating the token total. Checked 2026-08-30.

View the calculation

Recurring or keyless free-forever providers56

Mistral1B/month
LLM7150M/month
Nara150M/month
Gemini CLI · forever60M/month
Kiro50 credits/month
Qoder · foreverFree catalog
LongCat · forever50M/day
Cerebras1M/day
NVIDIA NIM~40 RPM
Pollinations · foreverNo key
Cloudflare Workers AI · foreverDaily neurons
OpenCode Free · foreverNo-auth catalog

토큰 낭비를 멈추세요

Reduce eligible tokens by 15–95%.

도구 출력, 반복된 컨텍스트, 비대해진 JSON이 모델에 도달하기 전에 압축됩니다. 동일한 의미, 토큰의 일부만. 10개의 조합 가능한 엔진이 당신이 제어하는 파이프라인에 쌓입니다.

Before69 tokens

The function should iterate over the list of items, and for each item, it should check whether the value is greater than zero, and if so, add it to the running total.

After19 tokens

sum all list items where value > 0

Composable pipeline

Session-Dedup
Drop content already sent earlier in the session.
CCR
Archive large blocks and restore them on demand.
Lite
Apply conservative lossless cleanup.
RTK
Filter and deduplicate command and tool output.
Responses Tool Output
Compact Responses API tool payloads.
Headroom
Apply reversible tabular and structured-data compaction.
Relevance
Keep sentences most relevant to the latest query.
Caveman
Use rule-based prose condensation.
Aggressive
Apply stronger configured pruning.
LLMLingua-2
Use code-safe semantic pruning in an isolated worker.
Ultra
Combine high-savings stages with preservation guards.
OmniGlyph
Encode eligible repeated structures compactly.

Profiles

Published profile range~30%x-omniroute-compression: standard

Controls and output styles

Named profiles and active selector
Visual Compression Studio
Anthropic Context Editing
Adaptive context-budget dial
Per-request `x-omniroute-compression` header
Offline eval harness
Token-threshold auto-trigger
Terse prose
Less code (YAGNI)
Terse CJK 文言

Control precedence: request header → combo → profile → adaptive policy → default.

3티어가 아닌 3레이어

적절한 수준에서 실패하세요. 전체가 아닌.

잘못된 키 하나가 프로바이더 전체를 멈춰서는 안 됩니다. 죽은 모델 하나가 키 전체를 죽여서는 안 됩니다. 각 실패는 가능한 최소 범위로 격리되므로 나머지는 계속 서비스됩니다.

model ⊂ connection ⊂ provider

Provider circuit breakerWhen a provider is unhealthy, combo routing skips it until a half-open probe succeeds.

Connection cooldownCool down one key or account while sibling connections keep serving.

Model lockoutLock one rate-limited or unavailable model while other models on the connection remain available.

Network controls

Network routing and local data controls.

Proxy scopes control network routing while local-first storage keeps operational data on your machine.

Three proxy scopes

Route globally, per provider or per individual connection.

Global · per-provider · per-connection
SOCKS5 and HTTP(S) proxies
Proxy marketplace integration

TLS and client fingerprint controls

Match supported provider clients down to selected transport characteristics.

JA3/JA4-capable transport via wreq-js
Provider-specific client profiles
IPv4 and IPv6 egress controls

Private and local-first

Keys, usage and history stay on the host you control.

SQLite on disk with AES-256-GCM encrypted credentials
No OmniRoute account required
Self-host on infrastructure you choose

RussiaChinaIranCubaTürkiye

한눈에 모든 것을

설정 파일이 아닌 완전한 대시보드.

Manage providers, combos, analytics, health and costs at `localhost:20128/dashboard`.

localhost:20128/dashboardExample data

352providers connected

90+free tiers available

198healthy in this example

Claude Code · OAuth · live
Cerebras · free · live
Groq · cooldown example
NVIDIA NIM · free · live

에이전트 네이티브

에이전트를 연결하면 OmniRoute 자체를 구동합니다.

OmniRoute는 단순한 프록시가 아닙니다. 에이전트 프로토콜을 직접 구현합니다. MCP 클라이언트, A2A 네트워크, 또는 클라우드 코딩 에이전트에 연결하면 에이전트가 조작할 수 있는 도구가 됩니다.

MCP Server

110 tools across 33 scopes over stdio and HTTP transports.

110 tools · 33 scopes · stdio / HTTP

claude mcp add omniroute --type http --url http://localhost:20128/api/mcp/stream

A2A Server

6 skills for smart routing, quota, discovery, cost analysis and health reporting over JSON-RPC 2.0.

6 skills · JSON-RPC 2.0 · Agent Card

클라우드 에이전트

하나의 인터페이스로 Codex, Cursor, Devin, Jules를 구동. 태스크 생성, 플랜 승인, 결과 스트리밍, 모두 OmniRoute를 통해 라우팅.

Codex · Cursor · Devin · Jules

라우팅을 넘어서

단순한 프록시가 아닙니다. 플랫폼입니다.

임베디드 서비스

Bifrost(Go 릴레이), 9Router 또는 CLIProxy를 관리형 sidecar로. 또는 완전한 클러스터 프로필로. 대시보드에서 바로 실행하세요.

당신의 지식을, 컨텍스트로

Notion과 Obsidian을 MCP 도구로 연결. 당신의 노트와 vault가 모든 모델의 일급 컨텍스트가 됩니다.

내장 가드레일

모든 라우트에 프롬프트 인젝션 가드, 선택형 PII 삭제, 안전 콘텐츠 필터 정규화. 종속 없는 방어.

게이미피케이션

스트릭, 업적, 실시간 절약. 당신의 사용량을 손에 잡히게.

Guides

Setup guides in three languages

Walkthroughs cover installation, free-provider setup and connecting an IDE.

빠르게 성장하는 활발한 커뮤니티

OmniRoute는 지속적으로 발전합니다. 수백 명의 기여자들이 최첨단을 유지합니다.

Public since February 13, 2026

59,579 stars

View the repository

8,274forks
583contributors
280releases shipped

Snapshot from 2026-09-01

OmniRoute by Cheaper Inference

Choose how you run OmniRoute.

Self-host OmniRoute, or start with Cheaper Inference for a hosted cost-ranked gateway.

Start with Cheaper Inference Self-host OmniRoute

코딩을 멈추지 마세요.

OmniRouteworksevenbetterwithCheaperInference.

하나의 엔드포인트. 개발을 멈추지 마세요.

한도에 도달하지 마세요

최대 95% 토큰 절약

$0으로 시작

35 supported integrations

하나의 엔드포인트

프로덕션 수준

All behind one endpoint.

세 가지 명령. 설정 없음.

Step 1: Install

Step 2: Run

Step 3: Connect your tool

모든 것이 내장. 애드온 없음.

스마트 콤보

메모리

3-layer resilience

무료 할당량

압축

MCP Server

A2A Protocol

Keep your existing coding tools.

이제 VS Code Copilot Chat에서도 사용 가능

Official Marketplace

Open VSX Registry

Copilot 요금제가 필요 없습니다

왜 OmniRoute인가

비교

9 supported ways to run OmniRoute.

npm

Docker

Desktop

ARM

Android · Termux

PWA

OpenCode plugin

VS Code

From source

Choose an `auto` route.

Drain subscription quota

Spread load

Cheapest first

Context-aware

Randomized

Adaptive scoring

월 ~1.51B 무료 토큰.

Reduce eligible tokens by 15–95%.

Composable pipeline

Profiles

Controls and output styles

적절한 수준에서 실패하세요. 전체가 아닌.

Network routing and local data controls.

Three proxy scopes

TLS and client fingerprint controls

Private and local-first

설정 파일이 아닌 완전한 대시보드.

에이전트를 연결하면 OmniRoute 자체를 구동합니다.

MCP Server

A2A Server

클라우드 에이전트

단순한 프록시가 아닙니다. 플랫폼입니다.

임베디드 서비스

당신의 지식을, 컨텍스트로

내장 가드레일

게이미피케이션

Setup guides in three languages

🇧🇷 Complete guide · Português

🇺🇸 Complete guide · English

🇷🇺 Complete guide · Русский

빠르게 성장하는 활발한 커뮤니티

Public since February 13, 2026

Discord

Telegram

WhatsApp 🌍

WhatsApp 🇧🇷

Choose how you run OmniRoute.