Credits & Limits

How the 3D AI Studio MCP connector spends credits: website prices, the free plan, personal or team credits, confirmations for large requests, refunds and rate limits.

Updated October 2026

The connector uses your normal 3D AI Studio credits. This page explains exactly when credits are spent, how to keep control of your spending, and which limits you might run into.

How credits work through an assistant

  • Same credits, same prices. Every generation costs exactly what it costs on the website. There is no surcharge and no separate wallet. See What You Can Do for prices.
  • Charged when a job starts. Credits are deducted when 3D AI Studio accepts a generation, not when the assistant merely talks about it.
  • Automatic refunds. If a generation fails, the credits are refunded automatically, exactly as on the website.
  • No double charges for repeats. If your assistant accidentally sends the same request twice in quick succession, it runs once and you are charged once.
  • Free actions. Checking your balance, listing models, showing results, uploading images, and (on paid plans) browsing your library and organizing projects cost nothing.

Personal or team credits

When you connect an assistant, the sign in page asks Use credits from:

  • Personal (the default): generations use your own credits. Works on every account: without a paid plan you get the free plan.
  • A team you belong to: generations use that team's credits. Needs an active paid plan on the team, so every team member can use it, including members without a plan of their own. If the team requires two-factor authentication, turn it on for your account first.

Options you can't use right now are greyed out with the reason, and the first usable one is preselected. The choice is saved for that connection. Teams show up as a badge next to the connection in Settings → AI Assistants (MCP). To switch, disconnect the assistant and connect it again, then pick the other option.

If you leave a team, connections that used its credits stop working and show Team access lost. Disconnect and connect again to choose a new credit source.

Staying in control of spending

  • Your assistant only generates when you ask. It does not start generations on its own.
  • Ask before you spend. "How much would that cost?" or "what's my balance?" are always free and always answered.
  • Large requests ask first. Unusually expensive requests need your confirmation before any credits are spent. Depending on your assistant, you see an approval prompt or the assistant asks you in the chat. Routine generations run straight away so the conversation does not stall.
  • See what each assistant spent. Settings → AI Assistants (MCP) lists every connected assistant with when it was last used, how many actions it ran, and how many credits it has spent.
  • Stop it at any time. Disconnecting an assistant takes effect immediately. See Managing Connections.

To keep chats focused, assistants are asked not to bring up credit amounts unless you ask. If you want cost updates while you work, just say "tell me what each generation costs".

Not enough credits

If a request costs more than your balance, nothing is charged. Your assistant tells you the cost and your current balance, for example:

"This would cost 70 credits but the balance is only 40."

Top up or change your plan on the pricing page, then ask your assistant to try again.

Limits

These limits are the same whether you use the website or an assistant. They exist to keep generation fast and reliable for everyone.

LimitWhat happensWhat to do
Generations per minute, per modelStarting many generations with the same model in a short burst pauses the next one. Your assistant is told how many seconds to wait, and nothing is charged for the paused requestNothing. Your assistant waits and continues. If it gives up, ask it to try again
Uploads per hourUploading many images in a short time returns "Upload limit reached (... per hour on the current plan)"Wait a little, then upload again. Higher plans have a larger allowance
Images per requestUp to 4 images per generation request, up to 10 (GPT Image 2.5) or 14 (Nano Banana) input images for editsSplit bigger jobs into several requests
Multi view input2 to 4 views for most 3D models, up to 8 for Hunyuan 3.1Use the most informative views

Batching many models? Tell your assistant something like "generate these 12 props one after another". It paces the requests and picks up where it left off if it hits a per minute limit.

Free plan

You can try the connector free. On a free account (or after a paid plan ends) your assistant can use, with your free credits:

Included freeDetails
Prism 3.1 3D modelsPreview settings: fast textures, standard geometry, no PBR. From text or one image
GPT Image 2.5 FlareGenerate and edit images at low quality, 1K, one image per request
Background removal and uploadsSame as on paid plans
Your connector resultsShow and download the models and images your assistant made

Everything else is part of the paid plans: full-quality 3D (standard, detailed and extreme textures, detailed geometry, PBR, polygon limits), the other 3D models (P2, P1, Hunyuan 3.1, Meshy 7.1), multi view input, format conversion (FBX, OBJ, STL, USDZ, 3MF), low poly and retopology, UV unwrapping, materials, sound effects and speech, the other image models, and your dashboard library and projects.

Free generations work in assistant apps such as Claude, ChatGPT, Cursor, Claude Code, Codex, VS Code and OpenCode. Scripts and custom integrations that call the connector directly need a paid plan to generate; they can still check the balance, list models and read earlier results.

When you ask for something that needs a paid plan, your assistant tells you and gives you a link to upgrade. Upgrading applies instantly: there is no need to reconnect, just ask again.

Every paid plan includes the full connector at the same credit prices as the website. See plans

  • Team members can connect with the team's credits whenever the team has a paid plan, even without a plan of their own.
  • If your own plan ends, personal connections keep working on the free plan. Your models stay in your dashboard.
  • If a team's plan ends, connections that spend that team's credits stop working and show Plan required in Settings. After the team plan is renewed, they work again; if one does not, connect it again.

Frequently Asked Questions

On this page