Comfy API goes live: deploy workflow JSONs as autoscaling GPU endpoints
PurzBeats · x · 2026-10-01
ComfyUI launched Comfy API, a deployment service for workflows.
- Point it at a workflow JSON and it automatically resolves custom nodes, models, LoRAs, and Python dependencies.
- Everything, including the ComfyUI version, is pinned into a versioned Build with an immutable release, so what you test is what ships.
- Deploys as an autoscaling endpoint on RTX PRO 6000, H100, H200, or B200 GPUs.
Related event: ComfyUI Launches Comfy API for One-Click Workflow Deployment(3 posts)→
More from Infra
- Dell ships first Vera Rubin NVL72 rack-scale systems in volume, citing unprecedented NVIDIA partnership — yenkel · 2026-10-01
- Shibaura Tech's Ozaki Scheme II lands in CUDA 13.4, squeezing FP64 from AI-focused GPUs — udmrzn · 2026-10-01
- Microsoft ships WSL 3.0: WSL containers goes GA, run Linux containers with GPU passthrough without Docker — udmrzn · 2026-10-01
- AI Inference Provider Passes 500B Tokens, Pushes Autopilot to Boost Supplier Earnings — gajesh · 2026-10-01
- Cerebras COO sells $78M in stock to zero as OpenAI reportedly skips WSE chips — TheZachMueller · 2026-10-01
- Indie dev ternary-quantizes Qwen 27B to 7.3GB, keeps image skills for ComfyUI — udmrzn · 2026-10-01