Multi-subscription router · Tauri desktop app

Merge every AI coding plan into one virtual subscription

Stacked subscriptions but Claude Code can only talk to one vendor at a time? cc-router pools DeepSeek, Qwen, Kimi, MiMo, MiniMax, GLM and Claude quota into one virtual plan — sequential or round-robin, with automatic failover when one hits its rate limit.

MIT open sourcemacOS · Windows · LinuxLocal proxy · data stays on device
cc-router · 127.0.0.1:23456
running
model-opus
round-robin
DeepSeek V4-Pro GLM-5.1
model-sonnet
round-robin
MiniMax M2.7 Xiaomi MiMo
model-haiku
sequential
GLM-4-Flash
model-fallback
catch-all
any unmatched model
— Features

One local proxy. Every coding plan you own.

cc-router spins up an Anthropic Messages compatible proxy on your machine. Claude Code talks to it; it forwards to any provider you configure.

01

18 providers in one router

DeepSeek, Qwen, Kimi, MiMo, MiniMax, GLM, Claude and more — Token Plan, Coding Plan and pay-as-you-go API, all ready to go.

02

Three virtual slots

opus / sonnet / haiku map to real models you choose, dispatched sequentially or round-robin.

03

Automatic failover

Rate limit, 429 or error? The router transparently switches to the next upstream. Your agent never notices.

04

Bring your own endpoint

Built-in providers not enough? Any Anthropic Messages compatible API drops in with first-class scheduling.

05

Usage receipts

Export a token-spend snapshot as PNG, PDF or HTML — monochrome or color, usage-only by default.

06

Trilingual UI

Simplified Chinese, English and Japanese — auto-follow your system or pick manually.

— Architecture

How it works

One diagram: your agent → cc-router → many providers.

CLIENT
Claude Code
POST /v1/messages
opus / sonnet / haiku
X-API-Key: ····
ROUTER running
cc-router
127.0.0.1:23456 · 4 routes · running
model-opus
round-robin
DeepSeek V4-Pro GLM-5.1
model-sonnet
round-robin
MiniMax M2.7 Xiaomi MiMo
model-haiku
sequential
GLM-4-Flash
UPSTREAMS
Upstreams
multi-account · multi-plan
DeepSeek
GLM (Zhipu)
MiniMax
Xiaomi MiMo
Moonshot Kimi
+ 13 more
— Screenshots

See exactly what it does

Configuration, logs, usage receipts — everything in one app.

Virtual model config

Three fixed slots plus a fallback. Bind real models and pick scheduling visually.

Usage receipts

Export shareable token-spend snapshots in seconds — great for archives.

Request logs

Watch every forwarded request live: provider, latency, token spend, errors.

— FAQ

Frequently asked

Without it, your AI agent can only talk to one vendor at a time — small plans run out at the worst moment and you switch configs by hand. With cc-router in front, your agent transparently load-balances and fails over across vendors A, B and C. Three plans behave like one.
Claude Code splits work by difficulty: opus for planning, sonnet for coding, haiku for tool calls. cc-router abstracts those into three virtual slots; each slot binds a set of real models plus a scheduling mode. Requests route by mapping — no more editing settings.json.
Sequential: drain A first, then B. Great cache hit rate, perfect for squeezing two small plans. Round-robin: split traffic evenly, but caches across accounts are independent so total quota burn is higher in exchange for real load balancing.
No. cc-router only forwards requests; the body is passed through nearly verbatim. It does not reverse, jailbreak or bypass anything. Users remain responsible for following each plan's Terms of Service.
No. cc-router is a pure local proxy bound to 127.0.0.1:23456. All forwarding happens on your machine. There is no telemetry or external traffic beyond the provider APIs you configure.
!

Before you install

Provider ToS may not explicitly permit "subscription key behind a third-party proxy with multi-model dispatch." The author is not responsible for accounts being throttled, banned or subscriptions revoked. Software is provided AS-IS.

Ready to make every subscription count?

Download the app