Help Center/Code & engines
Choosing a model in Prompt to Browser Game
Which Claude Opus model to pick for browser-game generation, what each costs, and when to use each.
Prompt to Browser Game runs only on Anthropic's Claude Opus models. The picker sits under "Advanced: AI model" in the prompt box and shows the credit price for the mode you have selected. Every model is available on every plan; your credit balance decides what you can run.
Claude Opus 5.5 (default, 500 credits quick / 1,450 Advanced): the newest and strongest Opus, and also the cheapest per build. If you are unsure, use this one.
Claude Opus 5 (600 / 1,800): the previous Opus generation. Solid on complex games; pick it if you prefer how it writes games.
Claude Opus 4.8 (600 / 1,800): the last of the Opus 4 line. Useful if you want results close to games you built on older versions.
"Quick" and "Advanced" refer to the pipeline, not the model. Quick is one Opus call; Advanced is three passes (design, skeleton, implementation) with the model doing dedicated work at each stage, and is available on the Indie plan and higher, and to any account holding credits from a credit pack. Refines are priced by the size of the game being edited, and the price is shown on the button before you run it.
Prices are set so every build covers its worst-case Anthropic cost, and anything that fails is refunded automatically. If your balance is below the cheapest build, the tool links you to credit packs and plans.
Tip
If you have your own Anthropic API key, add it at /dashboard/api-keys and tick "Use my Anthropic key" (Indie plan and higher). Every generation then costs just 1 GameFoundry credit regardless of the model, and Anthropic bills your account directly.