Stop burning frontier quota on routine turns. AutoRouter pools your
Claude
and
ChatGPT
plans, brings every leading model into the coding tools you already
use, and routes each turn to the model built for it—on our defaults
or your own rules.
Free · macOS 14 or later
Install
the ChatGPT plugin
Claude Fable 5.1GPT-6 AstraGPT-6.1 SolClaude Opus 5.5Claude Sonnet 5.5Claude Haiku 5.5GPT-6.1 TerraGPT-6 SolGPT-6 Luna
Gemini 4 Argon
Kimi K3.1 Pro
Grok 4.7
DeepSeek V4.1 Flash 1017
GLM 5.3Kimi K3
MiniMax M3.1 FlashGLM 5.3 FlashOne model for everything means overpaying on easy turns and settling whenever another lab is stronger. AutoRouter matches each turn to the model that handles it best.
Codex
Refactor the billing module to use the new ledger API
AutoRouterClaude Opus 5.5Claude plan
GPT-6 AstraChatGPT plan
DeepSeek V4.1 FlashCredits
Examples. Real routes follow your plans and rules.
Your harness shouldn’t lock you into a single lab. AutoRouter brings Anthropic, OpenAI, Google, xAI, DeepSeek, Kimi, Qwen, Z.ai, MiniMax, and more into every supported tool on your Mac.
Start from our defaults, then make them yours. Tell AutoRouter
how you work—“Use Claude Opus for UI design” or “Never send
customer code to open models.” Your rules win, and you can pin
any model on any turn.
Available as a
ChatGPT
plugin.
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
Michael Levin@MichaelLevin
I’ve been using @Auto_Router for a week+ now and
haven’t run out of usage yet whereas I used to
consistently bump into limits. The quality doesn’t seem to be down
at all.
Denis Nazarov@Iiterature
New smart router that
saves you massive token usage on your frontier
subscriptions in harnesses like Codex!
Tiru@tirupathipodugu
Routing renames and small edits to Haiku while
Opus handles the hard parts makes total sense
Bryan Lee@junmobius
I just went through onboarding and played around with my usual
setup and it’s a magical experience to say the least.
Give it a try if you have been struggling with your Claude/Codex
quota :)
Natasha@natashaghoskins
Never wasting tokens again
armand@0xarmand
Being able to use Opus 5.5 In Codex has been a game
changer for me
Dylan Abruscato@DylanAbruscato
It feels like magic. Can’t wait for you all to fall
in love with this product too
Ariel Lillie@ariell_xyz
AutoRouter moves so fast I cannot even keep up
Ian Kar@iankar_
Damn @Auto_Router
saved me almost 100 bucks today
Bull Master@BullMaster_BM
A week without hitting limits and
no quality drop
yitong@yitong
@Auto_Router is dope. Go check it out!
Michael Levin@MichaelLevin
Whatever I do, I'll be using @Auto_Router 🫡
armand type beat@2irl4u
I’m going to burn so many tokens (but save in the process)
T. Costa@tcosta
🖤 Been loving it
Patrick@plantpatt
AutoRouter is Goated
Levi Binkley@itslogos
If you want to be the goat you need to use Goated tools. Been
waiting for this LFG
Michael Levin@MichaelLevin
I’ve been enjoying using @Auto_Router to help
manage my drain better fwiw
Tajwan Tamim@Tajwan_Tamim
Always nice when a tool pays for itself
André@anticustody
The automatic transmission for LLMs
Kris Tan@memokris
Showing the model, cost and reason for each turn is a nice touch.
That makes the routing decisions
easier to follow
Azim@azmoan
Funny thing was that I wanted to follow your model routing
strategy manually - with AutoRouter that's
basically automatic (as the name says)
The SI Maximalist@thesimaximalist
Model switching just got a dance move.
Ian Kar@iankar_
Damn @Auto_Router is insane
Neesh@Neesh774
Lmfao this is actually an insane app to use. WDYM
early access 😭😭😭
bku@bryankuuu
Need this yesterday!
andres@_andresjasso
That’s why my usage hasn’t reached its limit yet!
😍😍😍
Kane@kaneclerke
Gorgeous launch video and a great way to approach prevent/optimise token burn
Jason Marder@JasonMarder
Loving AutoRouter! Beautiful visual and experiential
execution.
Saneel@sanlsrni
One of the more delightful experiences I've had wrt
tooling recently along with @Auto_Router
Stuart Sim@StuSim
If you want to witness a little bit of
beautiful magic today, you should be trying out
autorouter.Com
Alvi@Heyy_Alvi
Simple tools that just get it done
Lucian Mincu@lucianmincu
Probl. The next big thing after OpenRouter and w/
very cool UX. 👊
Dejan Lazeski@lazeskid
So the cheap model does the grunt work n
nobody can tell, that’s smart
Sam Kahler@Kahler_Swift
Locking in, made easy
Kai@kaixweb3
Got my whole stack running on it now
iroh.hl@0x_iroh
The UI and UX is top notch. Great job!
Preston@prestonattebery
This is going to be big
Paying for both a work and personal
Claude
or
ChatGPT
plan? Connect them all once, and AutoRouter paces usage across
every account you own, rolling over seamlessly when any single
plan hits its limit.
Free includes up to 2 subscriptions
Plans
ChatGPT
2 plans connected
Claude
4 plans connected
Even a $200 Max plan runs dry when every file read
and rename hits your top model. AutoRouter spreads work
across your
Claude
and
ChatGPT
subscriptions and moves mechanical turns to fast models, so
your usage limits last through Friday.
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 for fresh input, cache
reads and output. Pro sends 85% of quick and 75% of medium
turns to open models, which its included usage pays for.
No new editor to learn and no API keys to wire up. AutoRouter drops straight into the model picker of the harnesses already on your Mac.
Install the Mac app and sign in with the Claude and ChatGPT subscriptions you already pay for.
Select AutoRouter in Codex, Claude Code, Claude Desktop, T3, or Terminal. Our defaults work out of the box, and every rule is yours to change.
Every turn routes automatically in the background, with live model picks and usage tracked in your menu bar.
Route across your
ChatGPT
and
Claude
subscriptions for free. Pro pools unlimited personal and work
accounts, unlocks every frontier and open-weight provider, and
includes $20 in monthly API credits—with your first
month free.
Your subscriptions only
$0/mo
Free to route across your
subscriptions
Every model and provider
$50/mo
$20 in included API credits each month*
Plus everything in Free
Go ProRolled out to your whole team
Custom
Priced for your team
Plus everything in Pro
Get in touch*Included API credits reset monthly and do not roll over. Connected subscriptions are always used first; paid models outside your plans are billed from included API credits at the provider’s list price plus 10%, and top-up credits never expire. New accounts start with a free month of Pro, including $20 in API credits.
Halve your company’s AI bill and give every developer the strongest model for every turn, rolled out to every Mac in one MDM push with zero data retention.
Your AI tools lose context the moment you switch windows, and no single model catches its own blind spots. AutoRouter already sits across every harness and lab on your Mac, so we’re turning it into a shared intelligence layer for all your AI work.
Never let one model grade its own homework. Claude writes the code; GPT pressure-tests the logic, security, and edge cases before you merge.
Preferences, repo conventions, and task context follow you across every harness, so each one picks up where you left off.
Put the strongest planner, the fastest parallel editors, and the sharpest debugger on the same feature.
Download AutoRouter, connect the plans you already pay for, and keep building in the harnesses you use. Start on our defaults and make the routing yours.
Free · macOS 14 or later
Setup, routing, billing and privacy. Anything else, email support@autorouter.com.
A Mac app that routes AI work across your harnesses. Choose AutoRouter and each task goes to the model that fits, using your connected subscriptions first, every model on Pro, and centralized MDM governance and zero data retention on Enterprise.
No. Hard work always goes to a frontier model, and routine turns go to models that handle them just as well, so you get the same results as running the top model on everything for a fraction of the usage. Many tasks come out better, because each one goes to the model that’s strongest at it.
Codex, Claude Code, Terminal, T3, and Claude Desktop. OpenCode and Pi are coming soon. AutoRouter runs on macOS 14 or later.
Download AutoRouter, connect your subscriptions, and choose it in a supported harness. The app guides you through setup.
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. Quality comes first: a turn only moves to a cheaper model when that model does it just as well. 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.
AutoRouter updates the settings it needs for each supported harness, saving a copy first. Your other preferences stay in place. Disable a harness in AutoRouter’s settings to switch it back.
Yes, it’s built for you. Routing across your subscriptions is free, and Pro connects several Claude and ChatGPT accounts, personal and work included. Routine turns stop eating your frontier usage, and when one account hits its limit, new sessions continue on the next, so you get more from the plans you have before you buy another.
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. On Pro, add as many accounts as you have; when one hits its limit, new sessions move to the next.
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. Pro is $50 a month and includes $20 of monthly model usage, multiple connected Claude and ChatGPT accounts, and every supported provider. Paid models outside your plans are billed at the provider’s list price plus 10%, spent from your included usage first and then from non-expiring top-up credits. New accounts start with a free month of Pro, up to $20 of usage.
In AutoRouter's October 28, 2026 study, an everyday Claude Code task cost an average of $0.110 on Claude Opus 5.5, $0.049 on Claude Sonnet 5.5 and $0.0044 on Claude Haiku 5.5 across 45 runs of five coding tasks at Anthropic's list prices. See the full results and the published method. These are model-level measurements, not a savings estimate for your workload.
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. See AutoRouter for Enterprise or get in touch to roll it out.
Three steps to get started.
Qwen 3.8
