Attributing AI Cost to People and Tools

Multi-Router attributes every dollar of AI spend to the person and the tool behind it, down to the model, vendor and region, with a budget for each person and each tool, set once in a policy.

Rahul Singh, Founder, Multi-Router 6 min read

Employees in every department now use AI tools, and each department uses different ones. Engineers work in Claude Code and Codex, marketing drafts campaigns in Claude Desktop, sales researches accounts before calls, and support summarizes long ticket threads. Each of those tools sends requests to a model, and each request costs money. As that spend grows into a real line item, a company needs to know exactly where it goes: which people, which tools, which models, which vendors and which regions, and whether each team is on track for the month. That takes attribution that is precise to the request and accurate to the cent.

Attributing Spend With Multi-Router

Multi-Router tracks every person and every tool they use independently. Alice in Claude Code and Alice in Codex are two separate lines of spend, and inside each one every model she uses is tracked on its own. Every person belongs to an organization, such as Engineering or Marketing, so the same spend also adds up by department.

Each request is priced the moment it completes, from the exact model, vendor, variant and region that served it, at the price in effect at that time. Input, output, cache read and cache write tokens are each priced at their own rate, so the cost reflects what the vendor charges, and the savings from prompt caching show up per person and per tool. Each request also records the region that served it, so cost and data residency are visible side by side.

The cost is counted against the person and the tool, and it appears within seconds:

Where What it shows
The person's pageSpend this period across all their tools, and each tool's spend against its budget.
The PortalThe person's own spend by day, their pace, and their spend on each model.
TrafficEvery request with its person, model, vendor, region, tokens and cost.
BudgetsSpend, status and pace for each budget, with spend by person and by model.
A

Alice Chen

activeMember

alice@example.com

OperatorManaged agentsPortal

Account roster Suspend Offboard
Access
Operator + agents
Organizations
1 of 2
Agents active
2 of 2
Spend this period
$181.00 / $300.00
Lifecycle
active
Sign-in
SSO linked

Access

Edit
Operator access
On · role Member
OrganizationsEngineering· Member
Managed agents
On·Portal
Engineering· Standard Engineering

AI agents

Claude CodeactiveEngineering · key …7Qx2 · issued Nov 7, 2026
Set up 12 days ago · last used 4 minutes ago · router rt_9Hk3Ws7PzQ
$142.60 of $200 this month · $57.40 left
Rotate keySetup helpTrafficRetire
CodexactiveEngineering · key …4Lm8 · issued Nov 14, 2026
Set up 5 days ago · last used 2 hours ago · router rt_3Tq8Vd5JxN
$38.40 of $100 this month · $61.60 left
Rotate keySetup helpTrafficRetire

Policies

Engineering
Standard Engineering
Revision 3 · Claude Code, Codex
Claude Code $200, Codex $100 per person per month

Activity

Lifecycle events, newest page first.

activeNov 7, 2026
Actor: usr_8Wc2Hn5RzE

Identity

Email
alice@example.com
Account role
Member
Sign-in
SSO linked
Person ID
per_2Fk7Ms4QbY
User ID
usr_8Wc2Hn5RzE
Created
Nov 7, 2026
Updated
Nov 14, 2026

Budget

Claude CodeMonthly · resets Dec 1
$142.60 of $200$57.40 left
CodexMonthly · resets Dec 1
$38.40 of $100$61.60 left
Alice Chen's page in the dashboard: Claude Code at $142.60 of $200 and Codex at $38.40 of $100 this month, each tracked and budgeted on its own.

The Employee Portal

The Portal is where each person sets up their AI tools. A person signs in with their work email, sees the tools their policy grants, and sets each one up with a key of their own, the settings to paste into the tool, and a check that confirms it works. There is nothing for IT to configure by hand on anyone's laptop, and every request from then on is attributed to that person and that tool.

Each tool has its own page in the Portal. It lists the models the person can use, with their spend and cap on each, and shows their spend against their budget, their pace, and the date they will reach their budget at that pace. Models the policy does not allow are refused. A person who needs more can request additional budget from the same page, and an approver receives an email and approves or denies it in the dashboard. A person can also issue themselves a new key at any time, and their spend and budget carry over to it.

Your AI agents

2 set up · budgets reset Dec 1

Add an AI agent
AI agentThis monthAt this paceStatus
Claude Code
3 models approved · key sk-mr-7Qx2…
$142.60 of $20071%
cap in 8 days
$7.51/day
nearing capDetails
Codex
2 models approved · key sk-mr-3Fp8…
$38.40 of $10038%
won’t reach cap before reset
$2.02/day
on trackDetails
Budgets are monthly and reset Dec 1, 00:00 UTC (in 12 days). Set by Engineering IT for Standard Engineering.
The Portal for Alice Chen: Claude Code and Codex, each with its own spend, budget and pace for November.

Fine-Grained Budgets

Each person has their own budget for each tool. Alice can have $200 a month for Claude Code and $100 a month for Codex, and each budget alerts, pauses and resets on its own, so reaching her Codex budget leaves Claude Code working.

Inside each tool budget, a model can have its own limit. On a $200 Claude Code budget, Claude Opus 5 can be limited to $120, so a person uses the most capable model for the work that needs it and keeps working on the other models once Opus reaches its limit.

Budgets also cover more than one person:

Budget covers Example
A team or departmentEngineering's total across every person and tool, $20,000 a month.
A chosen set of toolsA pilot group's tools, each with its own limit.
A tagEverything carrying the tag, including tools set up later, with a total for the group and a limit for each member.

Budgets stack. A department budget, a person's budget for a tool and a model limit all apply together, and the first one reached takes effect, so a department can have a monthly ceiling while each person keeps their own budget inside it.

Rules decide what happens as spend grows: an email at 80%, an alert when spend is projected to reach the limit within the next hour, and a pause at 100% until the period resets. Alerts also go to the systems the company already uses, by webhook to Slack, an on-call service or a finance tool, and every webhook is signed so the receiver can verify it came from Multi-Router. An admin can raise any limit for the current period when a launch or a deadline needs it.

The Budgets page shows every budget's spend, status and pace, and each budget's usage shows spend over time, by person and by model. Traffic exports to CSV for chargeback to cost centers.

Engineering · org_3Fh8Wq2LdK

All budgets

New budget
Status:
allnearingimminentcapped
Search budgets…
Total spend
$12,480
Effective limits
$20,000
Capped
0
Imminent
0
Nearing
0
Unpriced traffic
0.2%
Budgets
1–4 of 425 / page
ColumnsUpdated
NameScopePeriodSpend / effective limitUsedStatusUpdated
Standard Engineering · Claude CodePolicy1 request
bdg_2Lk5Pz8NcV
Tag · Standard EngineeringMonthly
$5,840/$200 per person
—No cap3h ago
Standard Engineering · Claude Codebdg_2Lk5Pz8NcVTag · Standard EngineeringMonthly
Detailed usage →
Managed by policy: limits and rules are set by the policy. Budget Overrides and approvers can still be set here.Open policy
Spent
$5,840
Effective limit
—
Remaining
—
Per-person limit
$200base
Period
Nov 1 – Nov 30resets Dec 1
Pending requests
1
People over cap
0 of 34
Spend per day · daily · Nov 1 – 30
Spend
$0$200$400$600
Nov 1
Nov 8
Nov 15
Nov 22
Nov 29
Request approvers
Requests on
Emailed when someone asks for a higher limit in the Portal. The Portal hides its request button while this list is empty.
dana.okafor@example.com
name@example.com
Add
1 of 10
Budget Overrides · this period
Nov 1 – Nov 30 · UTC. Each override replaces one limit until the period ends.
Add Budget Override
TargetBase limitEffective limitChangeSet by
No Budget Overrides this period. Every limit is at its base.
Pending requests
1 pending
Approving raises this person's limit for this period. Adjust the amount before approving.
Priya ShahClaude Code
Nov 19, 09:42 UTC
Limit $200 → requested $300 (+50%)
I am running the payments service migration this week and I am at $196.10 of $200 with 11 days left in the month.
Approve at$300+50% from $200
DenyApprove
Standard Engineering · CodexPolicy
bdg_5Wc7Hq3MzA
Tag · Standard EngineeringMonthly
$1,215/$100 per person
—No cap3h ago
Data Science pilot
bdg_9Bv3Rt6YfJ
Routers · 4Monthly
$2,960/$4,000
74%On track4d ago
Engineering
bdg_4Hn8Ws1KdT
OrgMonthly
$12,480/$20,000
62%On track9d ago
Limits are server-resolved effective limits for the current UTC period.
Budgets for Engineering: the department budget at $12,480 of $20,000 and the Standard Engineering budgets for Claude Code and Codex, with a pending request for more budget.

Policies

All of this is set once, in a tools policy, for a group of people. A policy sets the tools a group can use, the models each tool allows, the budget per person for each tool, the limits for each model, and the rules that act on them.

Policy Tool Per person Model limits Rules
Standard EngineeringClaude Code$200 a monthClaude Opus 5 at $120Email the team lead at 80%, pause at 100%
Standard EngineeringCodex$100 a monthEmail the team lead at 80%, pause at 100%
Go-to-MarketClaude Desktop$40 a monthEmail the team lead at 80%, pause at 100%

Everyone on a policy gets their own budgets the moment they set up a tool, and one edit to the policy applies to all of them.

People · Engineering
policyeditingpolicy:standard-engineering
CancelSave changes
People
4
3 set up
AI Agents
1
Claude Code
Spend this period
$288 of $600
resets Oct 1 · 14 days
Revision
3
everyone set up is on 3
AI AgentsClaude Code is being set up · save it before adding another
Claude CodeEditing
Ready · save to add it to the policy
Anthropic API · global$200/mo per person3 models2 rules
RoutingAnthropic API · global
Route
Region
Region2 regions · 1 with every model
globalAll 12 modelsus9 of 12 models
Credentials
Anthropic productionAPI keyanthropicall regions
This key carries no region, so there is nothing to reconcile.
Models3 of 12 served
ServeModelVersionWire idPrice / 1M in · out
Claude Fable 5
anthropic/claude-fable-5
5claude-fable-5$10.00 / $50.00
Claude Fable 5.1
anthropic/claude-fable-5.1
5.1claude-fable-5-1$10.00 / $50.00
Claude Haiku 4.5
anthropic/claude-haiku-4.5
4.5claude-haiku-4-5$1.00 / $5.00
Claude Opus 4.5
anthropic/claude-opus-4.5
4.5claude-opus-4-5$5.00 / $25.00
Claude Opus 4.6
anthropic/claude-opus-4.6
4.6claude-opus-4-6$5.00 / $25.00
Claude Opus 4.7
anthropic/claude-opus-4.7
4.7claude-opus-4-7$5.00 / $25.00
Claude Opus 4.8
anthropic/claude-opus-4.8
4.8claude-opus-4-8$5.00 / $25.00
Claude Opus 5
anthropic/claude-opus-5
5claude-opus-5$5.00 / $25.00
Claude Opus 5.5
anthropic/claude-opus-5.5
5.5claude-opus-5-5$4.00 / $20.00
Claude Sonnet 4.5
anthropic/claude-sonnet-4.5
4.5claude-sonnet-4-5$3.00 / $15.00
Claude Sonnet 4.6
anthropic/claude-sonnet-4.6
4.6claude-sonnet-4-6$3.00 / $15.00
Claude Sonnet 5
anthropic/claude-sonnet-5
5claude-sonnet-5$2.00 / $10.00
A model switched off stays listed and is refused at request time.
Budget$200/mo per person · 1 model cap
Period
MonthlyResets on the 1st, 00:00 UTC

Each person on this policy gets $200 for Claude Code. Resets on the 1st, 00:00 UTC.

Per-model caps
Claude Opus 5anthropic/claude-opus-5
$
per person, inside the total
Add a model cap

A model cap sits inside each person's total and cannot exceed it.

Budget rules2 rules
NotifyAt 80% of the per-person cap → email lead@example.com
Condition
% of
Actions
Add action
BlockAt 100% of the per-person cap → block requests
Condition
% of
Actions
every request, until the period resets
Add action
Add rule2 rules · 1 notify · 1 blockCollapse all

A rule watches the per-person cap, every model cap, or one model cap, and fires when spend reaches a line. Email and webhooks send once per period; block answers 429 until reset.

Discard changesSave Claude Code
Claude Desktop
The desktop app · not on this policy
Organization
Engineering
Created
Jun 12, 2026
Created by
Priya Shahpriya@example.com
Revision
3 · Sep 2, 2026

Save Claude Code before saving the policy.

Spend this periodOpen in Budgets
$288of $600
Claude Code$288 of $600
3 of 4 on this page have spent.
History
  • Revision 3 · Claude Code
    Sep 2, 2026 · Priya Shah (priya@example.com)
  • Revision 2 · Claude Code
    Jul 21, 2026 · Priya Shah (priya@example.com)
  • Policy created
    Jun 12, 2026 · Priya Shah (priya@example.com)
Claude Code on the Standard Engineering policy: the allowed models, a $200 monthly budget per person, Claude Opus 5 limited to $120, and rules at 80% and 100%.

With directory sync, attribution follows the company's org chart. Directory groups assign each person's organization and policy, so when a person moves to another team in the identity provider, their policy and their spend move with them. When a person leaves, their tools stop and the record of their spend stays. Part 3 of Rolling Out AI Company-Wide covers directory sync in detail, and the Budgets & Spend Control docs cover every budget setting.

Start for free

Create a router, set your SDK base URL to Multi-Router and see the cost of every request.