Spraay Compute & Futures

Rent GPU compute, run AI model inference (LLM chat, image, video, speech-to-text, text-to-speech, embeddings), and buy prepaid compute-futures credits — all paid in USDC over x402, no API keys and no accounts. Use this skill whenever an agent needs to rent GPU time, run or batch model inference, generate images/video/audio, create text embeddings for RAG, estimate compute cost before spending, or lock in discounted compute by prepaying into a compute-futures credit balance. Trigger it for any phrasing like "rent GPU", "run inference", "generate an image/video", "transcribe audio", "text to speech", "get embeddings", "prepay compute", "compute credits", or "compute futures", even when x402 or Spraay is not named.

by @plagtech·MIT-0