Controlling credits
GenieForge usually includes monthly credits in your subscription for AI and related platform usage. This page is about controlling spend, not quoting exact prices. For current plan numbers, use https://genieforge.ai, your billing settings, or support@genieforge.ai.The rule of thumb
Credit usage reflects work performed, not how big a screen looks. A small page can still be expensive if it needs heavy data processing, many integration calls, large file analysis, or lots of plan-and-rebuild loops. A large dashboard can be cheap if it reuses what you already have.Build vs Chat
Preview clicks and ordinary page browsing are not the same as asking the AI to rebuild features.
Active build time
On Credit Usage, active build time is how long the agent spent working on Build requests. It excludes idle gaps while you think. Long active time often means large plans, repeated failures, or broad rebuilds.What tends to cost more
- Broad prompts that rebuild many surfaces at once
- Redoing work that already exists instead of refining
- Large imports, scrapes, or file analysis in the main Build loop
- Syncing a large knowledge collection (search indexing uses credits; looking up a search query does not add a separate charge)
- Fan-out of many long agent loops in automations
- Tight trial-and-error without reading errors from Preview as
What tends to cost less
- Asking for a small, named outcome (“show status on the Clients page”)
- Reusing what already works
- Moving bulk work off the interactive Build loop (background runs)
- Scheduled jobs that do one deterministic step instead of a full agent turn
- Testing with Preview as before another Build turn
- Using Chat mode once the capability exists
- Picking a cheaper model when the work is light (see Choosing a chat model; the picker shows
$through$$$$)
Conversation credit totals
The credit badge on a Build or Chat thread updates from actual usage after each turn (including nested work attributed to that conversation). Trust the number in the chat top bar and the chats list after a turn finishes; you should not need a manual refresh for them to match.Relative weight (not quotes)
Use these bands to set expectations. They are relative, not credit numbers or dollar amounts.
The same sentence can jump bands if the app already has conflicting schema, or if you ask Build to re-derive everything from scratch. Prefer named, incremental asks once the first slice exists.
How to keep a build predictable
- Approve a clear plan before heavy work.
- Prefer incremental asks over “rebuild the whole app.”
- Put durable preferences in Build Rules so you do not re-argue them every chat.
- Fix role and access issues with Access + Preview as instead of guessing in Build.
- Watch Credit Usage (Build vs Chat, spend by person) for the app. Click a spike day to see which conversations drove it, and open Produced on a conversation (credits badge) to see what was built.
Builder MCP
Applies from a connected MCP client are a flat fee per successful change, not a Build-turn quote. Lookups are free (0 credits). Writes are 5 credits. Page or capability checks, one-off code runs, and eval runs are 10 credits. Failed applies do not charge. Those fees count toward the app’s Build total (filter MCP apply to see only them). Model usage from the same apply (evals, capability runs, sub-agents) shows as a second number on the transcript. The table lives on GenieForge Builder MCP.Exact quotes are hard
The same sentence can expand into very different work depending on existing schema, integrations, and edge cases. GenieForge should not invent a fixed credit quote for a feature. Use active build time, day breakdowns, and recent rows as your signal, and ask support if you need help choosing a plan.Where to look
- App sidebar Credit Usage (admin or owner): Credit usage in an app
- Account billing settings for balance and top-up
- Billing, plans, and credits