ZenMux alternatives for Codex and Claude Code
AutoRouter9 min read
Use AutoRouter, the Mac app for Codex and Claude Code, if you code with agents and already pay for a Claude or ChatGPT plan. It lets both apps share those plans, puts 20+ other models in the model picker you already use with no API key, and picks a model for each task on its own. It also works in Cursor, Claude Desktop, T3 and Terminal. ZenMux is a hosted LLM gateway: one ZenMux key reaches 100+ models, paid from ZenMux credits or a ZenMux Builder Plan. OpenRouter, Requesty, Portkey and LiteLLM are the other gateways people weigh against it.
AutoRouter wrote this post, so weigh its rows accordingly. Each claim about another product comes from that product's own docs, site or pricing page, linked where it is used and read on November 17, 2026 unless the sentence says otherwise.
What is ZenMux?
ZenMux calls itself an enterprise LLM platform with a unified API for 100+ AI models from OpenAI, Anthropic, Google, DeepSeek and others (ZenMux). It speaks the OpenAI protocols at zenmux.ai/api/v1 and the Anthropic protocol at zenmux.ai/api/anthropic, names models as provider/model, and serves requests from Cloudflare's edge network (Quickstart, introduction).
- Model routing: set the model to
zenmux/autoand ZenMux scores candidate models on each request against abalanced,performanceorpricepreference, from a list you pass inmodel_routing_config.available_modelsor from its full pool (Model Routing). - Insurance: ZenMux says it compensates for poor performance, hallucinations and excessive latency. Checks run daily on call data and payouts are credited the next day (introduction).
- Pay As You Go: a prepaid balance topped up from $5, with no per-minute request limit, spent at each model's per-token rate (Pay As You Go).
- Builder Plans: Starter at $20, Max at $100 and Ultra at $200 a month, with five-hour quotas counted in Flows, a weekly limit and 10 to 15 requests a minute. ZenMux says the plans are designed for non-production scenarios, and its free plan covers Studio Chat only, with no API access (Subscription Plans).
- Teams: organizations with Admin and Member roles, a shared balance and credit limits per member (Organizations).
ZenMux vs AutoRouter puts the two side by side in one table.
Why look for a ZenMux alternative?
Most developers who code in Codex or Claude Code look because ZenMux adds a second bill and a key to manage. Its Claude Code guide sets ANTHROPIC_BASE_URL to ZenMux, puts a ZenMux key in ANTHROPIC_AUTH_TOKEN, blanks ANTHROPIC_API_KEY and maps other models through the ANTHROPIC_DEFAULT_*_MODEL variables in your shell profile. Its Codex guide exports ZENMUX_API_KEY and adds a ZenMux provider to config.toml. Either way, requests are paid from ZenMux credits or a Builder Plan, not from a Claude or ChatGPT plan:
- You pick the model in your agent. The coding-agent guides set models by name;
zenmux/autois there, but you set up its model list and preference yourself. - Each machine needs its own setup. The Claude Code guide recommends shell profile variables because
envin~/.claude/settings.jsonmay not load on first login or after a logout, and it notes that non-Claude models need full ZenMux IDs. - Builder Plans have limits for coding. They allow 10 to 15 requests a minute, count usage in Flows, and are meant for non-production use; ZenMux points launched or commercial projects to Pay As You Go.
- The insurance terms are short. The docs name what it covers but not the thresholds that trigger a payout.
None of that is a flaw for an app you ship, where one key for 100+ models is the point. It is the reason a developer who already pays for a Claude or ChatGPT plan looks elsewhere.
How is AutoRouter different from ZenMux?
AutoRouter uses the plans you already pay for first and picks a model for each task inside your agent, with no keys or config files to edit. AutoRouter, the Mac app for Codex and Claude Code, adds 20+ frontier and open-weight models to both apps' model pickers, curated and kept current by the AutoRouter team. Choose a model to send requests straight to it, or choose AutoRouter and it works out how hard each task is: your plain-English rules go first, then it considers only models that clear the quality bar for the task. Hard work goes to the strongest model your plans cover, and quick work to the one that costs you least:
The landing page's examples show what that looks like (real routes follow your plans and rules): a commit message is quick work, so a low-cost open model writes it and the plan isn't touched, while a test that only fails on CI is hard, so it goes to GPT-6 Astra on the ChatGPT plan. Every request shows its model, what it cost and why. How AutoRouter picks a model walks through each step.
- Download AutoRouter for macOS from autorouter.com.
- Open it, sign in or create a free account, sign in to your plans, allow Accessibility, and click Enable for each app.
- Start a new session and choose AutoRouter as the model: in Codex, from the model menu under the message box; in Claude Code, with
/model.
Connect Claude, ChatGPT, Grok and Gemini plans, and any of them can run in either app, so your Claude plan works inside Codex and your ChatGPT plan inside Claude Code (how that works). When one account reaches its limit, AutoRouter moves on to the account with the most room left before it spends any credit.
AutoRouter Free costs $0 a month and connects two subscriptions. Pro costs $50 a month with $20 of included usage each month, connects any number of plans and adds every other model at the provider's price plus 10%.
The trade-offs are real. ZenMux runs on any system, serves your own apps and servers as well as coding agents, pays out when output or latency falls short, and covers image and video models in its Studio. AutoRouter runs on macOS 14 or later, works with Codex (the app and the CLI), the Claude Code CLI, Cursor, Claude Desktop, T3 and Terminal, and doesn't serve the API traffic of apps you ship. Its requests pass through AutoRouter's servers on their way to each provider; it doesn't store transcripts, but keeps the message that opens each request, up to 4,000 characters, to review routing (AutoRouter privacy).
Which other ZenMux alternatives are there?
Four gateways cover what people use ZenMux for, each best at one job:
- OpenRouter is best for one prepaid balance across hundreds of models with nothing to run, the closest match to ZenMux's Pay As You Go. It bills inference at each provider's list price and charges a 5.5% fee on credit purchases on its Standard plan, and Claude Code connects with three environment variables (pricing, guide, read November 16, 2026). OpenRouter alternatives compares the hosted options.
- Requesty is best for one hosted bill across 600+ models with spend tracked by repo, branch and developer. Its Free plan allows 200 requests a day on free models, and Pay as you go adds 5% to model prices (pricing, Claude Code docs). Requesty vs AutoRouter compares it in depth.
- Portkey is best for organizations that want budgets, rate limits and request logs on their own provider keys, hosted or self-hosted. Developer is free with 10,000 recorded logs a month and Production is $49 a month; its site now says Portkey is Prisma AIRS AI Gateway, part of Palo Alto Networks (pricing). Portkey vs AutoRouter compares it in depth.
- LiteLLM is best for platform teams that want an open-source gateway on their own servers. It calls 100+ LLMs in the OpenAI format, is MIT licensed outside its enterprise directory, and sells an Enterprise license with SSO, SCIM and audit logs at custom prices (GitHub, Enterprise, read November 16, 2026). LiteLLM alternatives covers self-hosted gateways.
They differ most in who picks the model and what pays for requests:
| Tool | Who picks the model | Runs as | What pays | Price |
|---|---|---|---|---|
| AutoRouter | AutoRouter, per task, after your rules | Mac app, macOS 14 or later | Your Claude, ChatGPT, Grok and Gemini plans first; Pro usage for other models | Free $0; Pro $50/month with $20 of usage |
| ZenMux | You, by model ID, or zenmux/auto by preference | Hosted API | ZenMux credits or a Builder Plan | Top-ups from $5; Builder $20, $100 or $200/month |
| OpenRouter | You, by model ID | Hosted API | OpenRouter credits | List price; 5.5% fee on credits (Standard) |
| Requesty | You, by model ID | Hosted API | Requesty balance | Free tier; 5% markup |
| Portkey | You, by model ID | Hosted, or self-hosted | Your provider keys | Developer free; Production $49/month |
| LiteLLM | You, by model ID | Your servers | Your provider keys | Open source; Enterprise custom |
What is an LLM router? explains the kinds of routers these tools are built on, and Model routers for Claude Code and Codex, compared lines up more of them.
Questions
How much does ZenMux cost?
Pay As You Go is a prepaid balance, topped up from $5, spent at each model's per-token rate. Builder Plans are $20, $100 or $200 a month for non-production use, and the free plan covers Studio Chat only (Pay As You Go, Subscription Plans).
Does ZenMux work with Claude Code and Codex?
Yes. Its Claude Code guide sets the base URL and a ZenMux key as environment variables in your shell profile, and its Codex guide adds a ZenMux provider to config.toml, which the CLI and the app both read (Claude Code guide, Codex guide).
Is ZenMux's zenmux/auto the same as AutoRouter?
No. zenmux/auto is a model name on ZenMux's API that picks a model for each request from a pool, by the preference you set, and bills your ZenMux balance (Model Routing). AutoRouter is a separate Mac app that picks a model for each task inside Codex and Claude Code, after your rules, and uses your plans first.
Does AutoRouter run on Windows or Linux?
No. AutoRouter runs on macOS 14 or later, and Claude Code needs Node 22.18 or later. On Windows or Linux, ZenMux, OpenRouter, Requesty, Portkey and LiteLLM all work, since each is an API you point your tools at.
Sources
- AutoRouter
- AutoRouter privacy
- ZenMux, read November 17, 2026
- ZenMux: introduction, read November 17, 2026
- ZenMux: Quickstart, read November 17, 2026
- ZenMux: Claude Code guide, read November 17, 2026
- ZenMux: Codex guide, read November 17, 2026
- ZenMux: Model Routing, read November 17, 2026
- ZenMux: Subscription Plans, read November 17, 2026
- ZenMux: Pay As You Go, read November 17, 2026
- ZenMux: Organizations, read November 17, 2026
- OpenRouter pricing, read November 16, 2026
- OpenRouter: Claude Code integration, read November 16, 2026
- Requesty pricing, read November 17, 2026
- Requesty: Claude Code, read November 16, 2026
- Portkey pricing, read November 17, 2026
- LiteLLM on GitHub, read November 16, 2026
- LiteLLM Enterprise, read November 16, 2026