Works in
Claude Code
and
Codex
AutoRouter automatically picks the right AI model for each task, using the plans you already pay for first.
Free · macOS 14 or later
Codex
Claude Code
OpenAI
Anthropic
Google
xAI
DeepSeek
Moonshot
Z.ai
MiniMax
Qwen
AutoRouter reads each turn for difficulty and the kind of work, then sends it to the model that fits. Hard tasks get a powerful model; routine tasks use a lighter one to help your plans last longer.
Examples. Real routes follow your plans and rules.
Codex
Refactor the billing module to use the new ledger API
AutoRouterClaude Opus 5.5Claude plan
GPT-6 AstraChatGPT plan
DeepSeek V4.1 FlashCredits
AutoRouter works with your
Claude
and
ChatGPT
subscriptions, so your plans last longer.
Savings vary with your task mix and model choices. This
illustrative comparison shows how plans can last longer than
using a frontier model for every task; it is not a measured
customer result. The provider logos illustrate the range
available in each tier, not the providers used to calculate
these lines.
An example week of 30% hard, 45% medium and 25% quick turns,
at
Claude Opus, Sonnet and Haiku 5.5 list prices with cached input at a
tenth of input. Pro sends 85% of quick and 75% of medium turns
to open models, which its included usage pays for.
See which tasks use the most AI, which models ran them, and where the money went.
Frontier and open-weight models, curated and kept current, with
no keys or endpoints to set up. They appear in
Codex
and
Claude
Code beside the models you already have.
Start from our recommended rules, then add your own the way you’d say them in plain English.
GPT-6.1
Sol
for debugging.Yours
Kimi
K3
on customer code.Yours
Claude Opus
5.5
for anything in /payments.Yours
Claude Opus
5.5
for UI design.12 turns this week
GPT-6
Astra
for debugging.Overridden by yours
MiniMax M3.1
Flash
for quick edits.21 turns this week
DeepSeek V4.1
Flash
for renames.38 turns this week
Give your team the models they need, with clear spending reports, shared rules, and budgets you control.
No new app to learn and nothing to configure. AutoRouter shows up in the model picker you already use.
A small Mac app that connects to the plans you already have.
Pick AutoRouter from the model menu in Codex, or with
/model in Claude Code.
AutoRouter picks the model for each task while you keep working.
Route across your
ChatGPT
and
Claude
subscriptions for free. Pro adds every other model, with $20 of
usage each month.
Your subscriptions only.
$0/mo
Free to route across your
subscriptions
Codex
and
Claude
Code
Every model and provider
$20/mo
$20 of included usage each month*
Plus everything in Free
Start ProRolled out to your whole team.
Custom
Priced for your team
Plus everything in Pro
Get in touch*Included usage resets each month and doesn’t roll over. New accounts get Pro free for their first month, or until $20 of usage is spent, whichever comes first. Usage is billed at the provider’s price plus 10%; credits you top up never expire.
Download AutoRouter, choose it in
Codex
or
Claude Code, and stop paying frontier prices for routine turns.
Free · macOS 14 or later
Setup, routing, billing and privacy. Anything else, email support@autorouter.com.
A Mac app that adds AutoRouter as a model in Codex and Claude Code. Choose it, and every turn goes to the model that fits: your ChatGPT or Claude plan when it covers the work, and, on Pro, every other model when it doesn’t.
Codex, in the app and the CLI, and Claude Code. More apps are on the way. AutoRouter runs on macOS 14 or later.
Download the app, sign in to your plans, and enable
AutoRouter for Codex or Claude Code, then restart the app.
Choose AutoRouter as the model: in Codex, from the model
menu under the message box; in Claude Code, with
/model.
It reads each turn for its difficulty and kind of work, then weighs your plans’ limits and your rules, then balances cost, quality and speed. A model your plan covers can win over a stronger paid one, because it costs you nothing extra. How AutoRouter picks a model explains the process; routing and quality and Auto mode vs AutoRouter cover the tradeoffs.
Yes. AutoRouter’s models appear in your app’s model picker beside the ones you already have. Choose any of them and your turns go straight to it; AutoRouter routes only while it’s the model selected.
You start with AutoRouter’s recommended rules. Add your own the way you’d say them, like “Use GPT-6.1 Sol for debugging,” and where yours and ours differ, yours win. Rules are strong guidance rather than a guarantee; to always use one model, pick it in the model picker.
It adds AutoRouter to each app’s own settings, Codex’s
config.toml and Claude Code’s
settings.json, after saving a copy of each
file. Your other settings stay as they are. Disable an app
in AutoRouter’s settings to switch it back.
Yes, first. In Codex, OpenAI models run on your ChatGPT plan; in Claude Code, Claude models run on your Claude plan. Connect the other subscription in settings to use your Claude plan inside Codex, or your ChatGPT plan inside Claude Code.
No. Pro gives you every model, with $20 of usage each month.
On Pro, your usage covers OpenAI and Anthropic models until the plan’s limit resets. With none left, those turns stop and ask you to top up, while turns your plans still cover keep working.
Routing across your ChatGPT and Claude subscriptions is free. Free models and every other model come with Pro: $20 a month with $20 of usage each month. Paid models are billed at the provider’s price plus 10%, from that usage first and then from credits you top up; free models cost nothing. New accounts get Pro free for their first month, or until $20 of usage is spent, whichever comes first.
Pro includes $20 of usage each month. It resets monthly and doesn’t roll over. Top up any time: credits you buy never expire.
Requests pass through AutoRouter’s servers on their way to each provider, and we don’t store transcripts. We keep the message that opens each turn, up to 4,000 characters, to review routing, along with records of the model chosen, tokens and cost. The Privacy Policy has the details.
Everything in Pro, plus deployment through your MDM; org rules, models and budgets; spend reporting; zero data retention; and SSO, SCIM and an audit log. Get in touch to roll it out.
Three steps to get started.