Skip to Content
IDEsCursorUsage dashboard

Cursor usage, billing and limits

Dashboard at a glance

What you needWhere to find it
Dashboard URLcursor.com/dashboard 
Current usage (spent, tokens)Usage tab → Spent, Token breakdown
Remaining allowanceUsage tab → Remaining allowance
Reset dateUsage tab → Reset date
Billing & spending capBilling tab → subscription, Usage-based pricing, Spending limit
When allowance hits zeroNamed API models pause unless Usage-based pricing is on → On-demand charges accrue until Spending limit or cycle reset

Sign in with the same account as the Cursor app. Official docs: Usage and limits .

What this page helps you do

The official Cursor dashboard shows numbers. This page explains what those numbers mean and what to do next:

See usage → understand the charge → identify the model consuming it → decide whether to change model, limit spending, or wait for reset.

That interpretation is why engineers bookmark this page alongside cursor.com/dashboard.

Why is Cursor charging me?

Unexpected charges usually trace to one of these meters on cursor.com/dashboard :

Charge driverWhat it isWhere you see it
Included allowance exhaustedMonthly USD pool on your plan is used upUsage → Spent near plan limit; Remaining allowance near $0
API-model usageNamed models (Sonnet, GPT, Opus, etc.) draw from the API poolUsage → Token breakdown by model; pool meter in Usage
First-party / Auto usageAuto, Composer 2.5, Grok 4.5 draw from a separate First-party models poolUsage — check both pool meters after heavy agent weeks
Usage-based pricingContinue at API rates after included usage runs outBilling → Usage-based pricing toggle
On-demand chargesPay-as-you-go line items after allowance is goneUsage → On-demand charges
Spending limitHard cap on on-demand spend (not a plan feature by itself)Billing → Spending limit
Billing-cycle resetAllowance refills on the cycle date — unused balance does not roll overUsage → Reset date; Billing → Manage Subscription

If On-demand charges are climbing while Remaining allowance still shows headroom, you may be burning the API pool on frontier models while First-party allowance looks fine — check both meters and the per-model Token breakdown.

How much Cursor usage do I have left?

  1. Open cursor.com/dashboard  and click Usage.
  2. Find Spent — included allowance used so far this cycle (USD).
  3. Find Remaining allowance — what you have left before exhaustion or on-demand billing.
  4. Check Reset date — when the cycle rolls over and allowance refills.
  5. If Remaining allowance is close to zero, check On-demand charges and whether Usage-based pricing is enabled under Billing.

Before a long Agent session, glance at Remaining allowance. If the API pool is low, switch to Auto or Composer so work draws from the First-party models pool instead.

How do I check my Cursor usage?

  1. Go to cursor.com/dashboard .
  2. Click Usage.
  3. Review Spent, Remaining allowance, On-demand charges, and Token breakdown by model.
  4. Note the Reset date — unused allowance does not roll over.

For a mid-session snapshot while coding, use the in-editor usage indicator in the sidebar; reconcile against the dashboard after heavy weeks.

Where is the Cursor usage dashboard?

What you needWhere to go
Usage this cycle (spent, remaining, tokens)cursor.com/dashboard  → Usage
Subscription, usage-based pricing, spending capcursor.com/dashboard  → Billing
Quick snapshot while codingIn-editor usage indicator (sidebar)
Team per-user usageTeams dashboard 

Official URL: https://cursor.com/dashboard  — sign in with the same account as the Cursor app.

When does Cursor usage reset?

Cursor usage resets on the Reset date shown on the Usage tab. Unused Remaining allowance does not carry into the next billing cycle.

To confirm billing-cycle timing, open Billing → Manage Subscription. Team admins can also use the Analytics API  for org-wide cycle views.

Where can I see Cursor billing?

cursor.com/dashboard → Billing:

SettingPurpose
Subscription tierPlan and renewal
Usage-based pricingContinue at API rates after included usage runs out
Spending limitHard cap on on-demand charges
Manage SubscriptionPlan changes and usage reset time

Tab completions are unlimited on individual plans — you meter Agent, Chat, and named-model API calls.

How do I set a Cursor spending limit?

  1. Open cursor.com/dashboard  → Billing.
  2. Enable Usage-based pricing if you want on-demand usage after included allowance runs out.
  3. Set Spending limit to the maximum on-demand charges you accept per cycle.

Set the limit before enabling usage-based pricing on a team account — on-demand charges can accrue quickly on frontier models.

What happens when I reach my Cursor usage limit?

When Remaining allowance hits zero:

  1. Named API models (Sonnet, GPT, Opus, etc.) stop for Agent/Chat unless Usage-based pricing is enabled.
  2. If usage-based pricing is on, On-demand charges accrue at API rates until you hit Spending limit or the Reset date.
  3. Auto and Composer may still work — they draw from the separate First-party models pool, which has its own meter on the Usage tab.

Compare Spent + Remaining allowance against your plan’s published limits (Usage and limits ). Mitigations: enable usage-based pricing with a cap, switch Agent defaults to Auto / Composer, or wait for cycle reset.

Can I see Cursor token usage by model?

Yes. On Usage → Token breakdown, Cursor splits tokens per model into:

FieldMeaning
SpentIncluded allowance used so far (USD)
Remaining allowanceLeft before exhaustion or on-demand billing
On-demand chargesPay-as-you-go after included usage (if enabled)
Token breakdownInput, cache write, cache read, output by model
Reset dateCycle rollover

What the dashboard does not show: full prompt text, per-file attribution, or third-party provider invoices — those live in provider consoles when you BYOK. Cursor shows Cursor-metered usage for models routed through Cursor’s infrastructure.

Two usage pools

Individual plans track two pools that reset monthly:

PoolModelsAllowance
APINamed models you pick — Sonnet, GPT, Opus, etc.Monthly USD; scales with plan — Usage and limits 
First-party modelsAuto, Composer 2.5, Grok 4.5Separate, more generous meter

Frontier models burn the API pool fastest. Auto and Composer use the First-party pool — default them for routine agent work.

Queries about Auto + Composer vs API usage pool breakdown refer to this split. Check both meters in the dashboard after a heavy week.

Usage vs plan limits

Compare Spent + Remaining allowance against your plan’s published limits (Usage and limits ). When the API pool nears zero:

  1. Enable usage-based pricing with a spending limit (Billing tab), or
  2. Switch Agent defaults to Auto / Composer, or
  3. Wait for cycle reset on the date shown in Usage

Team admins use the Analytics API  and Admin API  for org-wide views — individual dashboard tabs show account-level meters only.

In-editor usage indicator

Quick remaining allowance snapshot while coding. Use mid-session; reconcile against the dashboard after heavy weeks.

Teams and admin dashboards

SurfaceAudienceShows
Teams dashboard AdminsPer-user usage, seat management
Analytics API AdminsProgrammatic usage export
cursor.com/dashboardIndividualYour pools and billing

Non-Auto third-party models on Teams: API rates plus Cursor Token Rate .

Debug from token groups

After a heavy Agent week, use Token breakdown to see which group dominates:

Dominant groupLikely fix
InputShorten rules; disable MCP
Cache readNew chat per task
Cache writeNarrow attachments
OutputAuto/Composer; tighter prompts

Guardrails

  • Set a spending limit in Billing before enabling usage-based pricing
  • Know which pool you are drawing from
  • Team admins: analytics in Teams dashboard
Last updated on