Verified history
Cursor replaced dollar-denominated included usage with plan multipliers and two usage pools
Cursor's pricing and usage-limit pages now describe included Agent usage as extended limits (Pro), 3× Pro (Pro+ at $60/month) and 20× Pro (Ultra at $200/month) across a Cursor-models pool and a third-party-models pool. No effective date is published.
Budget by pool and model rather than by an included dollar figure.
Cursor documents up to 1M-token extended context on usage-based plans
The models and pricing page now lists extended or long context up to 1M tokens for specific models, with 2× input pricing above 272K tokens on some of them; the earlier 200K Max Mode figure no longer appears. No effective date is published.
Large-repository tasks can use far more context than before, at model-specific prices.
Cursor documentation now limits Max Mode to legacy request-based plans
Cursor's Max Mode page now states that Max Mode is available only on legacy request-based plans and is billed at the model's API rate plus 20%; current usage-based plans select a context size directly. The vendor did not publish an effective date, so the detection date is recorded.
Accounts on current usage-based plans should plan context size per request instead of a Max Mode toggle.
Current monitored baseline
HyperObserve currently monitors 3 scoped observations for Cursor. The baseline covers included Agent usage by plan, model context window, Max Mode availability and billing. Each value retains its plan, product, endpoint, region, account, or runtime qualifier so a future change can be compared against the correct scope.
| Constraint | Current value | Scope | Verified source |
|---|---|---|---|
| included Agent usage by planIncluded usage is split into two monthly pools—Cursor models and third-party models charged at provider prices—and on-demand usage continues at API rates once a pool is exhausted. | Pro: extended Agent limits; Pro+: 3× Pro; Ultra: 20× Pro (no dollar amount published) | Individual paid plans (Pro $20, Pro+ $60, Ultra $200 per month) | CursorSep 17, 2026 |
| model context windowSome models bill long context above 272K tokens at 2× input pricing while others keep the same per-token rate; Max Mode extends context only on legacy request-based plans. | Up to 1M tokens with extended or long context on listed models | Usage-based plans; model specific | CursorSep 17, 2026 |
| Max Mode availability and billingCurrent usage-based plans have no Max Mode toggle; they select a context size directly, and a larger context window can increase the tokens a request uses. | Legacy request-based plans only; billed at the model's API rate plus 20% | Legacy request-based plans | CursorSep 17, 2026 |
Tracked constraints and impact
Included agent usage, model context, Max mode, and plan allowances. A change is recorded only when it alters a constraint developers can act on, such as capacity planning, request shaping, model selection, deployment configuration, storage design, retry behavior, or account budgeting.
Cursor Included Agent Usage by Plan
Cursor Included Agent Usage by Plan, verified against Cursor's official documentation with scope, implementation impact, caveats, and a direct check.
Cursor Context Window & Max Mode
Cursor Context Window & Max Mode, verified against Cursor's official documentation with scope, implementation impact, caveats, and a direct check.
Cursor Max Mode Usage Limits
Cursor Max Mode Usage Limits, verified against Cursor's official documentation with scope, implementation impact, caveats, and a direct check.
How a change is verified
- Compare the current first-party statement with the previously stored observation, including the exact plan, model, runtime, endpoint, region, and account scope.
- Separate a true product change from documentation clarification, temporary capacity, configurable account state, or a limit that applies to a different execution path.
- Preserve the old and new values, official source, effective date when disclosed, detection date, and practical impact. If those elements cannot be supported, no historical event is published.
Official sources monitored
These first-party documents support the current Cursor baseline. HyperObserve links directly to them so you can confirm the live wording before making a production decision.
Included monthly usage pools (Cursor models, other models) and plan multipliers
Model table, long/extended context notes, plan tiers, and on-demand usage
Legacy request-based plan availability and API-rate-plus-20% billing