One AI layer for every team, under your control

AutoRouter brings every leading model into the tools your engineers already use, and puts rollout, policy and spend in one place.

Contact sales

One-push MDM · Zero data retention · SSO and SCIM

Deploy

Push to all Macs

Jamf Pro Connected

AutoRouter.mobileconfig Signed

Macs412

Installed404

Pending8

Team	Installed	Status
Platform	142 of 142
Data	96 of 100	4 pending
Payments	64 of 64
Mobile	102 of 106	4 pending

Policy

Publish

Rule set

RecommendedCustom

Allowed models

11 of 14

Rules

Use

Claude Opus 5.5 in /payments.Payments

Use

GPT-6.1 Sol for debugging.All teams

BudgetsMonthly

Reporting

Export

October$9,840

Saved$3,910

TeamProjectTicketTag

Recurring budget $13,000

Fiscal year starts

Data retention

Require zero data retention

Applies to

Whole orgSpecific teams

Models11 of 14 allowed

Claude Opus 5.5
GPT-6.1 Sol
Gemini 3.1 Pro
MiniMax M3.1 Flash
DeepSeek V4.1 Flash	Blocked
Kimi K3	Blocked

Routes to the latest models

Claude Fable 5.1

GPT-6 Astra

GPT-6.1 Sol

Claude Opus 5.5

Claude Sonnet 5.5

Claude Haiku 5.5

GPT-6.1 Terra

GPT-6 Sol

GPT-6 Luna

Gemini 4 Argon

Kimi K3.1 Pro

Grok 4.7

DeepSeek V4.1 Flash 1017

GLM 5.3

Kimi K3

MiniMax M3.1 Flash

GLM 5.3 Flash

Control

Roll out in one push. Govern from one place

Deploy through Jamf or any MDM, then set the models, budgets and rules each team works with.

One-push MDM

Push a signed profile to every Mac. Engineers have nothing to set up.
Team policies

Choose the models each team can use, with exceptions when the work calls for it.
Budgets and attribution

Set recurring budgets and see spend by team, project or tag.

Security

Your code stays yours

Every prompt from every tool passes one policy boundary that you control.

Zero data retention

Route only to endpoints that never store, log or train on your code.
Approved models only

Models outside your policy never appear in an engineer’s picker.
SSO, SCIM and audit

Provision seats through your identity provider, with no shared API keys and a record of every turn.

Half the cost.
Every pick explained

Hard work stays on frontier models and routine turns move to fast ones. Every turn shows which model ran and why.

Move billing onto the ledger APIDone

Time: 9m 00s
Tokens: 126.5k
On your plans: $0.00
Saved vs. top model: $2.41

03m6m9m

Plan the move to the ledger

Claude Opus 5.5

Migration plan · Hard 2m 30s 38.2k tokens

Clean this up a bit

Claude Sonnet 5.5

Unclear ask · Medium 4m 30s 61.5k tokens

Rename the old helpers

MiniMax M3.1 Flash

Rename · Easy 6.4s 2.1k tokens

Review the diff

GPT-6 Astra

Big diff · Hard 1m 18s 24.7k tokens

Build the settings screenDone

Time: 12m 00s
Tokens: 115.8k
On your plans: $0.00
Saved vs. top model: $2.21

04m8m12m

Build it from the Figma frame

Claude Opus 5.5

UI work · Your rule 5m 30s 58.4k tokens

Wire the toggles to the API

Claude Sonnet 5.5

Two files · Medium 2m 15s 21.7k tokens

Fix the typos in the labels

MiniMax M3.1 Flash

Copy edit · Easy 8.6s 1.8k tokens

Keep edits when offline

GPT-6 Astra

Offline sync · Hard 3m 23s 33.9k tokens

Fix the auth test on CIDone

Time: 9m 00s
Tokens: 89.7k
On your plans: $0.00
Saved vs. top model: $1.71

03m6m9m

Find why auth only fails on CI

GPT-6 Astra

Fails on CI · Hard 3m 42s 44.3k tokens

Compare the CI and local env

Claude Sonnet 5.5

Config diff · Medium 1m 24s 14.9k tokens

Fix the clock in the test

GPT-6.1 Sol

You picked it 3m 11s 27.6k tokens

Run the suite and sum up

MiniMax M3.1 Flash

Summary · Easy 11.0s 2.9k tokens

Write tests for the ledgerDone

Time: 6m 00s
Tokens: 64.2k
On your plans: $0.00
Saved vs. top model: $1.22

02m4m6m

Test every ledger endpoint

Claude Sonnet 5.5

Test suite · Medium 2m 18s 26.3k tokens

Make these better

Claude Sonnet 5.5

Unclear ask · Medium 1m 36s 19.4k tokens

Cover the rounding edge cases

Claude Opus 5.5

Edge cases · Hard 1m 27s 16.1k tokens

Update the README

MiniMax M3.1 Flash

Docs · Easy 9.7s 2.4k tokens

Commit the checkout fixesDone

Time: 54.0s
Tokens: 17.9k
On your plans: $0.00
Saved vs. top model: $0.34

018s36s54s

Sum up the staged changes

MiniMax M3.1 Flash

Summary · Easy 9.8s 4.6k tokens

Write the commit message

MiniMax M3.1 Flash

Commit message · Easy 6.4s 2.1k tokens

Split out the config change

Claude Sonnet 5.5

Two changes · Medium 23.7s 8.9k tokens

Draft the pull request

MiniMax M3.1 Flash

PR summary · Easy 6.6s 2.3k tokens

Every lab, one approved catalog

Choose the labs and models each team may use, billed and governed in one place.

AutoRouter

Frontier 30%Strong 45%Fast 25%

ChatGPT plan

GPT-6 Astra

GPT-6.1 Sol

GPT-6 Luna

Claude plan

Claude Opus 5.5

Claude Sonnet 5.5

Pay per use

Grok 4.7

Gemini 3.1 Pro

Qwen 3.8

MiniMax M3.1 Flash

Kimi K3

DeepSeek V4.1 Flash

Org rules in plain English

Write a rule once, like “Keep payments code on zero-retention models,” and it holds on every Mac.

Use GPT-6.1 Sol for debugging.Yours
Never use Kimi K3 on customer code.Yours
Use Claude Opus 5.5 for anything in /payments.Yours
Use Claude Opus 5.5 for UI design.12 turns this week
Use GPT-6 Astra for debugging.Overridden by yours
Use MiniMax M3.1 Flash for quick edits.21 turns this week
Use DeepSeek V4.1 Flash for renames.38 turns this week
Use your plans before credits.Every turn
Keep the same model while a task continues.Every turn

Models that check each other’s work

AutoRouter already sits across every tool and lab, so we’re building review and shared context across them.

Cross-model review

One model writes the code and another reviews it before it merges.
Shared context

Repo conventions and task context follow engineers from tool to tool.
Coordinated agents

The best planner, editors and debugger work on the same feature.

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. Oct 29
Denis Nazarov@Iiterature New smart router that saves you massive token usage on your frontier subscriptions in harnesses like Codex! Oct 22
Tiru@tirupathipodugu Routing renames and small edits to Haiku while Opus handles the hard parts makes total sense Nov 4
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 :) Oct 27
Natasha@natashaghoskins Never wasting tokens again Oct 22
armand@0xarmand Being able to use Opus 5.5 In Codex has been a game changer for me Oct 26
Dylan Abruscato@DylanAbruscato It feels like magic. Can’t wait for you all to fall in love with this product too Oct 22
Ariel Lillie@ariell_xyz AutoRouter moves so fast I cannot even keep up Oct 27

Ian Kar@iankar_ Damn @Auto_Router saved me almost 100 bucks today Oct 23
Bull Master@BullMaster_BM A week without hitting limits and no quality drop Oct 30
yitong@yitong @Auto_Router is dope. Go check it out! Oct 23
Michael Levin@MichaelLevin Whatever I do, I'll be using @Auto_Router 🫡 Nov 4
armand type beat@2irl4u I’m going to burn so many tokens (but save in the process) Oct 21
T. Costa@tcosta 🖤 Been loving it Oct 21
Patrick@plantpatt AutoRouter is Goated Oct 21
Levi Binkley@itslogos If you want to be the goat you need to use Goated tools. Been waiting for this LFG Oct 22
Michael Levin@MichaelLevin I’ve been enjoying using @Auto_Router to help manage my drain better fwiw Oct 27
Tajwan Tamim@Tajwan_Tamim Always nice when a tool pays for itself Oct 23

André@anticustody The automatic transmission for LLMs Oct 22
Kris Tan@memokris Showing the model, cost and reason for each turn is a nice touch. That makes the routing decisions easier to follow Oct 23
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) Oct 23
The SI Maximalist@thesimaximalist Model switching just got a dance move. Oct 31
Ian Kar@iankar_ Damn @Auto_Router is insane Oct 27
Neesh@Neesh774 Lmfao this is actually an insane app to use. WDYM early access 😭😭😭 Oct 26
bku@bryankuuu Need this yesterday! Oct 24
andres@_andresjasso That’s why my usage hasn’t reached its limit yet! 😍😍😍 Nov 3
Kane@kaneclerke Gorgeous launch video and a great way to approach prevent/optimise token burn Oct 24

Jason Marder@JasonMarder Loving AutoRouter! Beautiful visual and experiential execution. Oct 22
Saneel@sanlsrni One of the more delightful experiences I've had wrt tooling recently along with @Auto_Router Oct 28
Stuart Sim@StuSim If you want to witness a little bit of beautiful magic today, you should be trying out autorouter.Com Oct 23
Alvi@Heyy_Alvi Simple tools that just get it done Oct 28
Lucian Mincu@lucianmincu Probl. The next big thing after OpenRouter and w/ very cool UX. 👊 Oct 22
Dejan Lazeski@lazeskid So the cheap model does the grunt work n nobody can tell, that’s smart Oct 22
Sam Kahler@Kahler_Swift Locking in, made easy Oct 26
Kai@kaixweb3 Got my whole stack running on it now Oct 28
iroh.hl@0x_iroh The UI and UX is top notch. Great job! Oct 22
Preston@prestonattebery This is going to be big Oct 22

Start with one team

We’ll help you pilot AutoRouter with one team, then bring it to the whole org.

Contact sales

Trying it yourself first? Download for Mac, free.

Questions

Anything else, email sales@autorouter.com.

How do we deploy AutoRouter across our Macs?

Push the signed app and its configuration profile through Jamf, Kandji or any MDM. Engineers sign in with SSO and get routed models in their tools, with no API keys to set up.

How does zero data retention work?

Turn it on for the org or for one team, and AutoRouter routes only to endpoints that never log, keep or train on prompts and code. Models that don’t meet the policy are blocked.

How do budgets and spend reports work?

Set recurring budgets by team or seat, with exceptions when a launch needs more. Spend and savings break down by team, project or any tag you define.

Can our engineers try it first?

Yes. AutoRouter is free on the Claude and ChatGPT plans an engineer already has, so anyone can try it on their own Mac before a rollout.

One AI layer for every team, under your control

Deploy

Policy

Reporting

Data retention

Roll out in one push. Govern from one place

One-push MDM

Team policies

Budgets and attribution

Your code stays yours

Zero data retention

Approved models only

SSO, SCIM and audit

Half the cost.
Every pick explained

Every lab, one approved catalog

Org rules in plain English

Models that check each other’s work

Cross-model review

Shared context

Coordinated agents

Start with one team

Questions

Downloading AutoRouter

Help shape AutoRouter for teams

One AI layer for every team, under your control Every lab’s best model, governed for your whole org Every model, every tool, one set of rules

Roll out in one push. Govern from one place Every Mac, every team, one control plane

One-push MDM

Team policies

Budgets and attribution

Your code stays yours

Zero data retention

Approved models only

SSO, SCIM and audit

Half the cost.Every pick explained Frontier where it counts.Half the bill everywhere else Every turn traced.Every dollar explained

Every lab, one approved catalog

Org rules in plain English

Models that check each other’s work

Cross-model review

Shared context

Coordinated agents

What people say about AutoRouter

Start with one team Talk to us about your rollout

Questions

One AI layer for every team, under your control

Roll out in one push. Govern from one place

Half the cost.
Every pick explained

Start with one team