> ## Documentation Index
> Fetch the complete documentation index at: https://docs.fullreach.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Plan limits

> What each tier may run, and the caps every organization shares.

Prices are not on this page: the [pricing page](https://fullreach.ai/pricing) reads them from the billing account. Everything below is what the product enforces.

## Per tier

| Limit                                              | Starter | Pro | Advanced |
| -------------------------------------------------- | ------- | --- | -------- |
| Prompts, pooled across the organization's projects | 50      | 150 | 350      |
| Projects                                           | 1       | 2   | 5        |
| Emerging competitor detection                      | No      | No  | Yes      |

A prompt runs in one market and one language. The same question in a second market is a second prompt, so 40 prompts copied into a second market use 80. No tier limits markets or languages.

A trial lasts 7 days. It runs on the limits of the tier the customer picked, up to Pro's. The picked tier's features are open from the first day.

## Every organization

| Cap                                                              | Value   |
| ---------------------------------------------------------------- | ------- |
| Competitors monitored per project, the tracked brand not counted | 50      |
| Other spellings one brand may carry                              | 20      |
| Live API keys, per organization and again per project            | 20      |
| The widest period a read may ask for                             | 90 days |

## The MCP server's rate limit

60 tool calls per organization per minute. A call over a period wider than 7 days costs one unit for every 7 days it asks for. Every answer carries `X-RateLimit-Limit`, `X-RateLimit-Remaining` and `X-RateLimit-Reset`, so a client can pace itself before the server refuses it.