# Track Your Usage Credits are the universal currency that powers everything your AI employees do. ## TL;DR 1 credit is roughly $0.01. Every time an employee thinks, completes a task, makes a voice call, or uses a paid tool, it costs credits. Faster, simpler AI models cost fewer credits. You can see your balance in the top-right corner of your workspace at all times, and a full breakdown under Settings, Subscription, Credit Usage. ## What Is a Credit? A credit is the billing unit for all AI work on the platform. Instead of tracking individual costs for each type of activity, everything is measured in credits. This keeps things simple: you have a credit balance, your employees use credits when they work, and you top up or upgrade when you need more. **1 credit is approximately $0.01 USD.** Your plan gives you a monthly credit allowance, and you can buy more anytime. ## What Costs Credits ### AI Usage (the biggest factor) Every time an employee thinks, responds, or processes information, it uses an AI model. The cost depends on which model tier the employee is using. | Tier | Speed | Best For | Relative Cost | |------|-------|----------|---------------| | **Fast** | Quickest responses | Simple lookups, formatting, drafts, quick Q&A | Lowest (roughly 10x cheaper than Advanced) | | **Standard** | Balanced | Everyday tasks, conversations, analysis | Medium | | **Advanced** | Most capable | Complex reasoning, long documents, nuanced work | Highest | You choose the model tier per employee in their settings. Fast is great for routine work and saves credits. Advanced is best for tasks that need deeper thinking. ### Other Credit Costs | Activity | Cost | When It Applies | |----------|------|-----------------| | **Compute runtime** | 1 credit per minute | While a workflow is actively running | | **Task completion** | 0.25 credits per task | Each time a task is marked complete | | **Voice calls** | ~3 credits per minute | During a voice conversation (speech and listening) | | **Meeting attendance** | ~1.5 credits per minute | While your employee is sitting in a live Meet, Zoom, or Teams call | | **Image generation** | 4 or 8 credits | Standard quality (4) or HD quality (8) per image | | **Connected app calls** | 0.05 credits per call | When using Gmail, Slack, Notion, or other connected apps | ### What Does NOT Cost Credits - Web Search, file management, task creation, journal entries, sprint management - Workflow starts (0 credits) - Internal processing like database queries and cache lookups - Using a local AI model through Ollama (zero AI credits, though runtime and task credits still apply) ## Where to See Your Credit Balance ### The Credit Bar (always visible) Look at the **top-right corner** of your workspace. You will see your current plan name, a progress bar showing how much of your monthly allowance remains, and the percentage left. This updates in real time as your employees work. **Click the credit bar** to open a dropdown with more detail: - Your remaining credit count - A progress bar and usage percentage - A breakdown of where credits went this billing period: AI usage by tier, compute runtime, tasks completed, and voice calls - Click any row (like AI Usage) to expand it and see per-model usage - Quick links to upgrade your plan or view full usage history ### Per-Message Cost Every chat message from your employee shows how many credits it cost. Click the inspect button on any message to see a detailed breakdown: input tokens, output tokens, and tool usage. ## Credit Usage Page (Full Details) For a complete picture, go to **Settings (gear icon in the sidebar), Subscription, Credit Usage**. This page has three sections: ### Credit Usage (current billing period) A detailed table showing every category of spending: | Category | What It Tracks | |----------|----------------| | **AI Usage** | Credits spent on AI processing, expandable by tier (Fast, Standard, Advanced) and then by individual model | | **Tool Calls** | Credits for paid tools (image generation, connected apps) | | **Internal** | Credits used by behind-the-scenes AI systems (safety checks, memory processing) | | **Compute Runtime** | Credits for workflow execution time | | **Tasks Completed** | Credits for completed tasks | | **Voice Calls** | Credits for voice conversations | ### Credit Grants A table of all bonus credits you have received: welcome bonus, promo codes, referral rewards, and credit pack purchases. Each row shows the date, source, and amount. ### Usage History A month-by-month breakdown of your credit consumption. Expand any month to see the detailed category breakdown for that period. ## How to Earn FREE Credits ### Referral Program Invite friends to the platform and you both earn credits. Here is how: 1. Go to **Settings (gear icon), Subscription, Get Free Credits** 2. You will see your personal referral link and stats 3. **Share your link** by copying it, or **send an email invite** directly from the page 4. When someone signs up using your link, you both receive bonus credits 5. You can earn referral credits for up to 10 successful signups The page shows your invites sent, how many were accepted, and total credits earned. ### Welcome Bonus Every new account starts with 1,000 credits at no cost. This is enough to test the platform, have several conversations, and complete a few tasks before deciding on a plan. ### Promo Codes Occasionally, promotional codes are available that grant bonus credits when you sign up. These are applied during registration and show up in your Credit Grants table. ## Credit Alerts You do not need to watch your balance constantly. The platform notifies you automatically: | Threshold | What Happens | |-----------|--------------| | **25% remaining** | You receive an in-app notification that credits are getting low | | **15% remaining** | A more urgent notification warns you credits are running critically low | | **0% remaining** | A final notification tells you credits are exhausted | Each alert fires only once per billing period, so you will not be spammed. ## What Happens When Credits Run Out When your balance hits zero: - The chat input is disabled and a "Credits Depleted" overlay appears - Any active streaming response stops - Voice calls end automatically - The credit bar in the header pulses red - Scheduled tasks skip silently until credits are available again **To resume:** upgrade your plan, buy a credit pack, or wait for your next billing period when your monthly credits refresh. Everything comes back online automatically once credits are available. ## Tips & Tricks - **Use Fast-tier models for routine work.** Quick lookups, formatting, and simple drafts cost roughly 10x less than Advanced models. Switch employees to Fast when they do not need deep reasoning - **Check the credit bar dropdown regularly.** It shows exactly where your credits are going this month, broken down by category - **Set up referrals early.** Each successful referral earns you credits for free, and your friend gets a bonus too - **Buy a credit pack for temporary spikes.** If you have a big project but do not need a higher plan permanently, a one-time pack keeps you going without changing your subscription ## Frequently Asked Questions **Q: What happens when credits run out?** A: All AI work pauses. Chat is disabled, scheduled tasks skip, and voice calls end. You are warned at 25% and 15% remaining. Top up or wait for your next billing cycle to resume. **Q: Can I see how many credits a single message costs?** A: Yes. Every message shows its credit cost. Click the inspect button for a full breakdown by model and token type (input, output, reasoning). **Q: Do unused credits roll over to the next month?** A: No. Monthly plan credits and top-up pack credits both reset at the start of each billing period. **Q: Are local AI models (Ollama) free?** A: Yes, for AI processing. If an employee uses an Ollama model running on your machine, zero credits are charged for the AI thinking. Compute runtime and task completion credits still apply. **Q: Can I set a credit budget per employee?** A: Not yet. Credits are tracked at the account level across all your organizations. Per-employee budgets are planned for a future release. **Q: What is the difference between Fast, Standard, and Advanced?** A: These are model tiers. Fast models respond quickly and cost the least, great for simple tasks. Standard models balance capability and cost for everyday work. Advanced models are the most powerful for complex reasoning but cost more per message. **Q: How are credits tracked if I own multiple organizations?** A: Credits are tracked per user, not per organization. If you own two organizations, your usage across both counts against the same credit balance.