Usage and message limits

What is the Usage tab

The Usage tab in Settings is where you monitor your AI message consumption. It shows how many messages your AI agent has sent during the current billing period, how many messages are included in your plan, and which plan you are currently on.

This is the primary destination for questions such as:

• How many messages have I used so far?
• How many messages are left in my plan?
• What plan am I on?
• When does my usage reset?
• Why did my usage increase faster than the number of visible AI replies?

To access the Usage tab, navigate to Settings and select the Usage tab, or go directly to:

https://panel.interlinked-ai.com/en/settings?tab=usage

What you see in the Usage tab

The Usage tab displays a clear summary of your current consumption:

Field	Description
Messages consumed	The number of messages your AI agent has sent in the current billing period
Total included	The total number of messages included in your current plan
Current plan	The name of the plan you are subscribed to (Free, Starter, Pro, or Ultra)

This information allows you to understand at a glance where you stand in the current billing period. If you are approaching your included limit, you can decide whether to monitor usage more closely or consider upgrading your plan.

Included messages per plan

Each plan comes with a fixed monthly message allowance:

Plan	Included messages
Free	500
Starter	5,000
Pro	10,000
Ultra	25,000

For a detailed comparison of all plans, including pricing and billing terms, see Plans and pricing.

How usage points work

Your plan includes a monthly usage allowance. In the panel, that allowance is summarized as messages consumed and messages included. Behind that simple counter, Interlinked uses a points system to measure how much AI work each customer interaction required.

This matters because the same number of visible AI replies does not always equal the same amount of usage. A short answer may consume the minimum amount, while a more demanding interaction can consume more.

The simple case

A short, direct AI reply usually consumes 1 point.

Typical examples include:

• A customer asks for your business hours and the AI sends a short answer
• A customer asks whether you offer pickup and the AI replies directly
• A customer asks for your address and the AI provides it without extra steps

For many everyday conversations, usage stays close to this simple pattern.

What can increase point usage

Point usage can increase when the AI needs to do more work before it finishes the response. Common reasons include:

• Tool-assisted actions — The AI may need to check availability, manage a cart, verify order details, or complete another built-in action before replying.
• Multi-step reasoning — Some requests require the AI to review more context, compare options, or complete several internal steps to produce the final answer.
• Longer context or longer replies — If the AI needs to read a larger amount of conversation history or generate a more detailed answer, the interaction can consume more usage.
• More advanced models — Your selected AI model also affects consumption. More advanced models can use more points than lighter models for the same kind of task.

How the 10,000-token step works

To keep the system fair across simple and demanding interactions, Interlinked also considers how much text the AI had to process in a given model run.

• Every model run starts with a base point
• If that run becomes very large, every additional block of 10,000 tokens adds another point
• Tokens are the small pieces of text the AI processes while reading context and generating a reply

You do not need to count tokens manually. The system calculates this automatically and the Usage tab shows the total consumption for the billing period.

Why the counter may move faster than visible replies

Some customer interactions require more than a basic answer. For example, the AI may need to analyze the request, use a workflow action, and then produce the final reply. When that happens, usage can grow faster than the number of visible messages in the conversation.

This is normal behavior. The Usage tab is the best source of truth for how much of your included allowance has been consumed.

What does not consume usage points

Not every interaction in the Interlinked AI panel counts toward your usage allowance:

• Your own actions in the panel — Navigating the dashboard, viewing CRM entries, managing orders, or configuring settings does not consume usage points.
• Manual replies from the CRM — When you take manual control of a conversation in the CRM and reply as a human agent, those replies do not count against your AI allowance.
• System actions — Internal platform operations such as calendar sync, webhook delivery, or order-status updates do not consume usage points.

When usage resets

Your message usage counter resets at the start of each new billing cycle. The specific behavior depends on your plan:

Paid plans (Starter, Pro, Ultra)

When a new billing period is paid successfully:

1. The usage counter resets to 0 messages consumed
2. Your full included message allowance becomes available again
3. Any overage charges from the previous period are billed separately

This means your usage refreshes every month for monthly subscriptions, or every month within a longer billing term for 6-month and 12-month subscriptions.

Free plan

The Free plan’s 500-message allowance follows the same reset logic. When the billing period renews, the counter resets and you receive a fresh 500-message allowance.

What happens when you reach your limit

The behavior when your included messages are exhausted depends on whether you are on a free or paid plan:

Free plan

When you consume all 500 included messages on the Free plan, the AI agent pauses. It will not send additional responses until the next billing period resets your allowance or you upgrade to a paid plan.

Paid plans

Paid plans include automatic overage usage, which means your AI agent does not stop when you reach the included limit. Instead, it continues operating and extra messages are billed separately at the overage rate for your plan.

This behavior exists to protect business continuity. If your AI agent handles sales, customer support, lead qualification, or appointment scheduling, an abrupt halt in mid-conversation could disrupt critical workflows.

For full details on overage pricing and billing, see Overage usage and extra messages.

Monitoring your usage effectively

Here are practical recommendations for managing your message consumption:

1. Check the Usage tab regularly — Make it part of your routine to review your consumption, especially during high-traffic periods.

2. Watch for approaching limits — If you are consistently reaching 80–90% of your included messages before the end of your billing period, consider upgrading to the next plan. It may be more cost-effective than relying on overage.

3. Understand your conversation patterns — Some businesses have seasonal peaks (holidays, product launches, promotional campaigns) that temporarily increase AI activity. Plan your subscription accordingly.

4. Review overage charges — If you are on a paid plan, check your invoice history in the Billing tab to understand how much overage you are generating each month.

What to do next

• Compare plans — See which plan best fits your usage pattern. See Plans and pricing.
• Understand overage — Learn how extra messages work and what they cost. See Overage usage and extra messages.
• Review your billing — Check your subscription status, renewal date, and invoices. See Billing and subscription management.