Dockerless Serverless GPUs: How I Built a Fast, Cheap AI SaaS with RunPod Flash

This walkthrough of FlashFun.dev shows how RunPod Flash runs dedicated serverless GPUs from pure Python decorators with no Dockerfiles, cutting image generation cost from the 3–4 cents per image charged by hosted APIs like Google Vertex AI to between $0.00033 and $0.002 per image. The app races SDXL Turbo on a 24 GB GPU against Flux.1 Schnell on a 48 GB GPU behind a Cloudflare Worker, D1 and R2 stack, using scale-to-zero, model loading in container __init__, low-step distilled models and async polling to keep costs down. Benchmarks put pure GPU inference at 297ms against 1.1s total wall-clock time, with over 70% of latency spent on queuing, dispatch and base64 serialization.