In this piece
claude-rotate: One Proxy for Multiple Claude Max Accounts
claude-rotate puts one private endpoint in front of several Claude Max or Pro accounts you already own, then moves Claude Code traffic when the active account runs out of usable quota. It removes the logout, browser login and terminal restart loop across laptops, workstations and personal agent pods. The open-source claude-rotate repository is MIT-licensed and deliberately small: one Python proxy process, one configuration file, JSON state and audit logs, with no database.
A proxy can track usage across devices, but it also gains access to credentials and traffic. Anthropic’s credential rules govern which applications can handle that traffic.
For purchasing decisions, see our Claude Code vs OpenCode team-cost comparison. For a gateway that serves a company rather than one owner, start with the production LLM gateway comparison.
Which Claude Code access path fits your workload?
| Your situation | Best fit | Why |
|---|---|---|
| One person owns multiple paid Claude accounts and works across several private devices | Use native Claude Code sign-in | Compare your account’s included allowance and usage credits before adding subscriptions. |
| One paid account occasionally reaches its limit | Wait, change model, or enable usage credits | A proxy adds security and operational work without adding quota. |
| Several employees or customers need shared capacity | Use Team, Enterprise or metered API access | Consumer credentials are the wrong identity, governance and billing boundary. |
| You need per-user budgets, SSO, audit export or contractual support | Use a production gateway and commercial provider plan | claude-rotate has device analytics, not an enterprise control plane. |
Why three Claude Max subscriptions can still stop one session
Separate subscriptions do not become one quota pool. Each login has its own allowance and reset clocks. Anthropic’s current Max plan documentation says session usage resets every five hours, while a weekly limit resets at a fixed time assigned to the account. It also says other weekly, monthly, model or feature limits may apply. A busy AI-agent fleet can therefore exhaust the account currently logged into every machine while paid allowance remains unused on another account.
Manual rotation works, but it is operationally awkward. You interrupt the task, log out, complete browser OAuth for another account, verify the identity, and repeat on each machine. With remote Macs, CI-like personal jobs and long-running loops, the interruption often costs more attention than the login itself.
How claude-rotate works
- Each Claude Code client points
ANTHROPIC_BASE_URLat the proxy and authenticates with its own internal device key. - The proxy replaces that device key with the setup token for the active paid account and forwards the request to Anthropic.
- It reads the
anthropic-ratelimit-unified-*headers returned with responses and stores the observed five-hour and weekly utilization. - When the active quota is exhausted, one synchronized decision selects the next usable account. A short burst limit waits and retries on the same account instead of wasting a warm cache.
- The panel rolls audit records up by device, model and account, including an API-price equivalent. That dollar figure is an estimate of comparable API usage, not Anthropic’s hidden subscription accounting.
Anthropic officially documents both pieces that make the connection possible. Its Claude Code authentication guide documents ANTHROPIC_BASE_URL for a custom endpoint and claude setup-token for a long-lived subscription OAuth token used by scripts or CI. It does not document or endorse multi-account pooling. That distinction matters.
Consume-first rotation protects expiring paid capacity
Round robin looks fair but ignores reset time. Imagine account A has 15% left and resets tonight, while account B has 70% left and resets six days from now. Sending the next request to B can leave A’s remaining allowance to expire unused. claude-rotate’s default consume-first strategy prefers the usable weekly window that resets soonest. In plain terms, it spends the most perishable capacity first.
The proxy also separates quota exhaustion from a short burst limit. A quota rejection can justify changing accounts. A per-minute 429 with retry-after should normally pause and retry on the same account, because rotating would move the burst and discard prompt-cache locality. Thresholds, cooldown and hysteresis reduce account ping-pong before a hard rejection.
What the 101 checks prove, and what they do not
The repository’s test runner currently lists 101 offline checks across rotation logic, analytics, HTTP proxy behavior and stress scenarios. Its published mocked-upstream results include 300 concurrent requests served, 50 parallel SSE streams relayed byte-for-byte, and a quota failure with 100 requests in flight that caused exactly one account switch. A lock serializes the failover decision so the herd does not advance through every account at once.
The maintainer reports these results from a single process with a mocked upstream. That setup measures proxy behavior and overhead. Live reliability, provider latency and behavior with current credentials were outside the published test.
Anthropic’s current credential policy
Claude Code’s legal and compliance documentation reserves subscription OAuth for ordinary use in native Anthropic applications. Developers may not collect, store or intermediate Claude.ai credentials or session tokens, or route consumer credentials for other users. The Consumer Terms, section 3 generally require an Anthropic API key for automated access unless Anthropic explicitly permits it, and prohibit bypassing protective measures. Use Anthropic’s native sign-in for interactive Claude Code and supported API-key authentication for unattended jobs or product gateways.
Safer alternatives when the limit is the real problem
Anthropic’s usage-credit documentation covers Pro, Max and Ultra. Once included usage is exhausted, opt-in credits continue at standard API rates until the monthly cap is reached or the balance runs out with auto-reload off. Max and Ultra have a separate Fable weekly limit. Monthly API credits on eligible plans are a separate balance. Anthropic says most usage credits purchased on or after 7 December 2026 expire after 12 months, subject to local terms.
| Option | Operational effort | Best for | Main tradeoff |
|---|---|---|---|
| Wait or reduce usage | Low | Occasional limits | Work pauses or model quality changes. |
| Usage credits | Low | Unpredictable personal overflow | Variable API-priced spend. |
| Direct API plus production gateway | High | Teams, products and governed automation | Metered cost and platform engineering. |
| Team or Enterprise | Medium | Managed users and organizational controls | Contract, seat and usage economics must be checked. |
Bottom line
Claude-rotate shows how a proxy can centralize quota telemetry. The same architecture makes the proxy a credential store and a point of failure. Use usage credits with a monthly spending cap for personal overflow. Use a commercial account or a supported API gateway for organizational workloads.
