Usage

The Usage page gives you a clear picture of how your organisation is consuming its Sprigr Teams plan. Monitor token usage, per-agent activity, cache efficiency, and your position against your plan limit — all in one place.

Accessing the Usage page

Sign in to team.sprigr.com and click Usage in the sidebar (shown as Usage & Billing for the Owner). Every team member can see usage; the billing controls further down the page are visible to the Owner only.

Usage metrics

The Usage page displays several key metrics for the current billing period:

Plan usage and tokens

Tokens are the fundamental unit of consumption. Every message your agents process and every response they generate consumes tokens. Token counts are weighted by model tier and token type (fresh input, cached input, output), so heavier models draw down your allowance faster — see Plans for how this works. The Plan Usage bar shows tokens used against your monthly plan limit, with the percentage consumed.

API calls

A count of the model API calls your agents have made during the current billing period.

Usage chart

The usage chart plots consumption over time and can be filtered by agent. Use it to:

• Spot trends — See if usage is growing steadily, spiking on certain days, or declining
• Plan for upgrades — If you are consistently hitting 80%+ usage, it may be time to upgrade
• Identify anomalies — A sudden spike in usage might indicate an agent loop, a misconfigured workflow, or an unexpected surge in customer interactions

Per-agent breakdown

The agents table shows how much each agent is consuming:

• Agent — The agent’s name
• Tier — The agent’s performance tier (Fast, Standard, Advanced, or Auto)
• Messages — Number of messages handled by this agent
• Tokens In / Tokens Out — Input and output tokens consumed by this agent
• API Calls — Model calls made by this agent
• Cost and % of Total — Shown to the Owner only: each agent’s share of total spend

This breakdown helps you identify which agents are consuming the most resources and whether any agents need optimisation (for example, switching a high-volume, simple agent to a lower performance tier).

Per-model and cache efficiency cards

The Owner also sees two extra cards in the Billing section:

• Per-model breakdown — A stacked bar of token consumption by model tier.
• Cache efficiency — Your cache hit rate and an estimate of how many tokens context caching saved you this period. A higher hit rate means a lower effective cost per message.

Website usage

If your plan includes hosted websites, the Owner also sees a summary of website bandwidth and requests for the period.

Try asking your agent

“Show me which agents are using the most tokens this month and suggest ways to optimise usage.”

Usage thresholds

Sprigr Teams uses a three-level system to manage usage relative to your plan’s monthly token limit:

Normal (under 80%)

Everything works as expected. Your agents respond to messages, workflows run, and all features are available.

Warning (80% to 100%)

The Plan Usage bar turns yellow and shows a warning: “Approaching your monthly limit. Upgrade your plan or enable overage billing below to avoid interruption.”

Note

The warning is informational only — it does not affect any functionality. Your agents continue to work normally. Use this as a signal to review your usage, and either upgrade or enable overage billing before you hit the limit.

Blocked (100%)

What happens at 100% depends on your overage setting:

• Overage billing off (default) — Agent processing is blocked. Agents will not respond to new messages until the next billing cycle starts, you upgrade, or you enable overage billing. The Plan Usage bar turns red: “Monthly token limit reached. Agents are blocked.”
• Overage billing on — Agents keep running. Usage past your allowance is billed at your plan’s overage rate at the end of the cycle.

During a block:

• New messages are not processed; existing conversations and data are preserved
• Workflows do not start new executions

Caution

A block only affects AI-powered features. You can still sign in to the portal, view conversation history, manage settings, and upgrade your plan. Once the limit resets, you upgrade, or you enable overage billing, agents resume processing new messages.

Overage billing

The Owner can toggle overage billing on the Usage & Billing page. When enabled, agents keep running past your monthly limit and the extra usage is billed at $5 per additional 1M tokens at the end of the cycle. Overage is not available on the Free plan, and Enterprise overage is contract-driven. See Plans for details.

Tips for managing usage

• Optimise agent performance tiers — Agents on the Advanced tier consume your token allowance much faster per message than those on Fast or Standard. If an agent handles simple, routine queries, switching it to a lower tier can significantly reduce token consumption.
• Review per-agent usage — If one agent is consuming a disproportionate share, check its persona and tool configuration. Long personas, excessive tool calls, and large knowledge base searches all increase token usage.
• Watch your cache hit rate — Agents that reuse context across turns consume fewer tokens. A low hit rate on a high-volume agent is worth investigating.
• Archive unused agents — Disable agents that are no longer in active use to prevent them from consuming resources if they receive unexpected messages.

Next steps

• Plans — Compare plans and upgrade if you are consistently hitting usage limits.
• Payments — Manage your payment method.
• Agent Settings — Optimise agent performance tiers to manage costs.