Rent a GPU for AI inference
The agent secures a GPU rental for a specific model within a set budget, handling payment and provisioning automatically.
How it works
Moves money or places ordersOperations and infrastructure
The agent first identifies the appropriate template for the desired model (e.g., qwen3-8b-awq). It then searches for available offers and selects the cheapest option that fits the requirements. Before renting, it checks the user's balance or initiates a top-up via x402 if funds are insufficient. Finally, it creates the rental with a hard budget cap to prevent overspending.
Prompt
Paste this into an agent that has the servers below connected. Adjust the names and dates to your own.
Prompt for Rent a GPU for AI inference
Find the cheapest GPU that fits qwen3-8b-awq and rent it within a 2 USDC budget.MCP servers it needs
Source
The vendor page this playbook is drawn from, and the passage that supports it.
The agent spends only your prepaid USDC or USDT balance on Base.AI agents · AmpleRun