Clarification on Cursor Pro vs Team Plan – Agent Usage and Token Allocation

Discussions
1

Hi everyone,

I have been reviewing Cursor’s pricing plans, specifically the Pro and Team plans, and I am looking for clarification on how agent usage and token allocation work in each.

Based on my understanding:

  • The Pro plan ($20/month) includes $20 of API agent usage along with unlimited tab completions.

  • The Team plan ($40/user/month) mentions $20 of agent usage per user and includes additional features such as centralized billing, usage analytics, and SAML/OIDC SSO.

However, I have come across some conflicting information:

  • In some places, it appears that the Team plan provides only $20 of agent usage per user (similar to the Pro plan), with the additional cost covering team-level features.

  • In other places, including parts of the dashboard, it seems to indicate $20 + $20 of agent usage, which suggests higher total usage.

I would like clarification on the following:

  1. What is the exact agent usage provided in the Team plan?

    • Is it limited to $20 per user, similar to the Pro plan?

    • Or does it provide $20 + $20 worth of usage?

  2. How does this translate into token usage?

    • For the Pro plan, approximately how many tokens does $20 of API agent usage correspond to for agent tasks and auto-completions?

  3. In the Team plan, are the token limits the same as the Pro plan with added administrative features, or is there an actual increase in usable token capacity?

  4. Is there any official documentation or reliable resource that clearly explains this breakdown?

I am trying to understand whether the Team plan primarily adds management features or also increases usable agent capacity.

Thank you in advance for your help.

1 Like
3

Hey, good questions. Let me break this down based on the current docs.

  1. Agent usage on the Team plan

The Team plan includes $20 of API usage per user, same as the Pro plan. It is not $20 + $20. The extra cost on the Team plan ($40 vs $20) covers team features like the admin dashboard, centralized billing, usage analytics, and SAML/OIDC SSO.

  1. How $20 translates to tokens

It depends on the model you use. Each model has different per token rates. For example, with Auto routing, rates are $1,25 per 1M input tokens and $6,00 per 1M output tokens. With a model like Claude 4.6 Sonnet, it is $3 per 1M input and $15 per 1M output. So $20 goes a lot further on cheaper models.

Full model pricing table: Models & Pricing | Cursor Docs

  1. One important difference

Individual plans (Pro, Pro+, Ultra) currently have two separate usage pools: Auto+Composer and API. The Team plan currently has a single usage pool. This is a known difference that other Team users have flagged too.

  1. Official documentation

Here are the relevant pages:

Let me know if anything else is unclear.

1 Like
4

Why is it different compared to Team?

5

thank you for your quick response.

6

Hi Dean,

I have one follow-up question to confirm my understanding:

As per your explanation, the Team plan has a single shared usage pool, while the individual plans (Pro, Pro+, Ultra) have two separate pools (Auto + Composer and API).

If I am an individual developer and I only consider API usage:

  • Since both Pro and Team plans include $20 API usage per user, would API consumption behave identically in both plans?

  • Or does the single pooled structure in the Team plan affect how API usage is consumed compared to the separate API pool in the Pro plan?

Also, from a practical standpoint:

  • Would it still be more beneficial for an individual developer to choose the Pro plan because of the additional Auto + Composer pool (i.e., more overall usable capacity for agentic coding)?

  • Or is there any scenario where a single-user Team plan provides better value purely from an API or token usage perspective?

Just want to make sure I’m interpreting the trade-offs correctly.

Thanks again for your clarification.

7

I’ll answer both follow-ups.

@takomine: The Team plan was built with a simpler billing setup. It has one shared usage pool for everything. Individual plans Pro, Pro+, Ultra were built separately and they have two pools, an API pool plus a separate generous Auto + Composer pool. It’s just a structural difference in how the plans are set up.

@Zeeshan0201: Good follow-ups, here’s the breakdown.

On the Pro plan you get two separate pools:

  • $20 of API usage for specific models like Claude 4.6 Sonnet, GPT-5, etc.
  • A separate generous Auto + Composer pool on top of that

On the Team plan you get one $20 pool that covers everything. Auto, Composer, and specific models all draw from the same $20.

There’s also a pricing nuance. On Team plans, all non-Auto requests include a Cursor Token Fee of $0.25 per million tokens on top of the model’s API price. This fee does not exist on Pro. On Pro, the only surcharge is a 20% upcharge when using Max Mode specifically.

So for a solo developer in practice:

  • Pro gives more total capacity, two pools instead of one
  • Pro costs half the price, $20 vs $40
  • Pro has no Cursor Token Fee on regular requests

If you don’t need team features like SSO, centralized billing, admin dashboard, or usage analytics, Pro is the better choice.

Docs for reference:

Let me know if this clears things up.

1 Like