How Usage & Credits Work
How Apogee meters AI usage - fair use on paid plans with rolling session and weekly limits, a one-time allowance for trials, all tracked as a percentage rather than a dollar figure.
How Usage & Credits Work
Every account has a usage limit for AI research. Paid plans run on fair use, with rolling session and weekly limits. Trials start with a one-time allowance. This page explains what drives usage, how to read it, and what happens when you reach a limit.
How Usage Is Measured
Every time you interact with Apogee - through the chat client, via MCP, or when a scheduled briefing runs - an AI model processes your request. Usage is not a fixed number of requests: some requests use more of your limits than others. Two things drive how much a request uses:
- How much text the model processes - both the input (your question plus the context and sources pulled in) and the output (the response). Longer, deeper research uses more than a quick lookup.
- Which model runs - more capable models use more per unit of text. Apogee selects the model for the task; there is no preset to choose.
Usage is tracked and reported as a percentage, not as a dollar amount. There is nothing to denominate in tokens or dollars on your side - the interface shows how much of each limit is used and when it resets.
What Counts as Usage
Different activities use different amounts of your limits:
- Short factual lookups (e.g., "What's the status of HR 1234?") use very little.
- Detailed analysis (e.g., "Compare these two bills and summarize the differences") uses more, because the model reads and reasons over more text.
- Research queries that search across multiple data sources use the most - the research agent may call several internal tools in sequence, each adding to the total.
- Follow-up questions in the same conversation include earlier messages as context, so a long conversation gradually uses more per message.
Practical example: A quick question like "Who sponsors HR 5678?" uses only a sliver of your limits. A detailed research request like "Find all AI regulation bills this Congress and summarize their approaches" uses noticeably more, because the agent searches multiple sources and reasons over far more text.
Where Usage Comes From
Your limits are shared across every way you use Apogee. Each source draws from the same balance.
Chat Client
When you send a message in the chat client, the model reads your message plus the conversation history and generates a response. If the research agent calls tools while answering, those internal calls are part of the same request.
MCP Connections
If you connect via MCP (through Claude Desktop, Claude Code, Cursor, or another MCP client), tool calls and AI processing draw from the same limits as the chat client. There is no separate allowance - all usage is pooled.
Briefings
Briefings (scheduled monitoring) draw from your limits when they run. Each run triggers a research query on your behalf to search sources and generate a summary. Briefings run on a schedule and use the same limits as the rest of your work. They keep running on schedule even after you reach a limit.
How Limits Work
Paid plans (Personal Research and Research Pro) run on fair use. There is no monthly cap. Instead, two rolling limits apply, and both show as a percentage on the Billing page:
- Session limit - a rolling window that covers a burst of work. It frees up again as the window moves forward.
- Weekly limit - a rolling limit across the week. It frees up again as the week moves forward.
Normal research does not run into either limit. See pricing for the current plans.
Trials start with a one-time usage allowance. Every new account tries Research Pro until a one-time usage allowance runs out. The allowance shows as a percentage, has no end date, and does not renew. When it is used up, the account keeps free-tier access until you subscribe to a paid plan.
Apogee does not disclose usage in dollar terms. The billing page and the in-product usage indicator both show a percentage, never a dollar figure. This is deliberate - a percentage is a stable signal regardless of how any individual request is priced internally.
Looking up public legislative and government records - bill status, sponsors, floor votes, and the like - never consumes your limits. Usage is consumed by AI-generated analysis and, for a small set of licensed or proprietary data sources the product designates as premium, by access to that data. Staff lookups are counted separately. See Staff lookups below.
Staff lookups
Staff lookups draw on licensed staff data, so they have their own allowance and do not use your research limits.
- Personal Research includes 5 staff lookups a month.
- Research Pro includes staff lookups across Congress and the states, subject to fair use. Research Pro also tracks staff on Folios and sends briefings when key staff change.
- Trials include staff lookups as part of the one-time allowance.
What Happens When You Reach a Limit
Reaching a limit never triggers an extra charge. There is no spending cap to configure and no auto top-up to manage.
- Generation pauses until the limit resets. The session limit resets as its rolling window moves forward. The weekly limit resets as the week rolls forward. Data lookups (bill status, sponsors, and the rest of the public record) keep working, since they never drew from your limits in the first place.
- Your existing conversations and data are unaffected - previous chats, folios, files, and past briefings all stay readable.
- Briefings keep running on their schedule regardless of where your limits stand.
- A trial allowance does not reset. When it is used up, the account moves to free-tier access until you subscribe. See pricing.
Reading Your Usage
You can see your usage in two places:
- Billing page - apog.ai/billing shows what percentage of each limit has been used, and when it resets. There is no dollar figure to check.
- Usage indicator - A compact indicator in the chat client turns red as a limit runs low. Selecting it opens the full usage view.
Plans
Every plan includes every intelligence capability and every data source. The plans are Personal Research, Research Pro, and Workflow Solutions (scoped on a call for teams). See pricing for what each plan includes and what it costs.
Tips for Getting More From Your Limits
Be specific in your questions
Vague questions like "Tell me about healthcare policy" make the agent search broadly and write long answers. Specific questions like "What committees is the BIOSECURE Act assigned to?" use far less of your limits.
Reuse what is already in context
When the agent retrieves data (bill status, news articles), that data stays in the conversation. Follow-up questions about the same data use less than starting a fresh search.
Start a new conversation for a new topic
Each message carries the earlier conversation as context, so a very long thread uses more per message. Starting a new conversation for an unrelated question resets that context.
Frequently Asked Questions
Does MCP usage count against my limits?
Yes. Whether you use the hosted chat client or connect via MCP (Claude Desktop, Claude Code, Cursor, and so on), tool calls and AI processing draw from the same limits.
Do data lookups use up my limits?
No. Simple data retrieval (searching bills, fetching news, checking status) never consumes your limits. Usage comes from AI processing - generating analysis, summaries, and research synthesis - and from a small set of licensed premium data sources. Staff lookups have their own monthly allowance.
Can I set a spending limit or pay for extra usage?
No. Paid plans run on fair use with rolling session and weekly limits, and there are no overage charges. If you consistently reach a limit, see pricing for a plan with more room.
What if I need to keep working after I reach a limit?
Wait for the limit to reset. The Billing page shows when. If you reach limits regularly, see pricing for a larger plan.
Do briefings count against my limits?
Yes, briefings draw from the same limits as a query you run yourself, but they keep running on schedule even after you reach a limit.
Why does a long conversation use more over time?
Each message includes the prior messages as context so the response stays coherent. As the conversation grows, each new message sends more text. Starting a new conversation resets this.
Can I see exactly what I used, in dollars?
No. Apogee does not show usage in dollar terms anywhere in the product. The billing page shows usage as a percentage and the date each limit resets.