Runware launches Serverless GPUs: $0 while idle, from $0.63/GPU-hour
aziz4ai · x · 2026-10-03
Runware, known for its image-generation infrastructure, launched Runware Serverless, pitched as the lowest-cost way to run custom AI workloads: billing only while running, starting at $0.63 per GPU-hour and $0 when idle. Users deploy Python code or a container, pick a GPU, and configure scaling, while the platform handles scheduling, queues, workers, and routing — a notable budget option for on-demand inference.
More from Infra
- INT21: 2 engineers direct AI to build 20 inference engines in 2 weeks, up to 2.4× faster than SGLang — bingxu_ · 2026-10-03
- Traversal's 5 Levels of Self-Driving Production: Why Coding Agents Make Ops Harder — AI Engineer · 2026-10-03
- How DatologyAI Generated 12 Trillion Synthetic Tokens — And Fixed 4 Pipeline Bottlenecks — AI Engineer · 2026-10-03
- Price-Insensitive Buyer With Billions Seeks 500MW-2GW of Powered Data Center Land — JohnnyNi13 · 2026-10-03
- Running 256k-context open models on 2x RTX 3090 for months: a home server LLM retrospective — knighty1981 · 2026-10-03
- Prime Intellect compresses MLA KV cache in NVFP4, fitting ~50% more tokens than FP8 — TheZachMueller · 2026-10-03