Replicate is a cloud platform for running open-source AI models via a simple API. Run Stable Diffusion, Llama, Whisper, and thousands of community models without managing infrastructure. Pay only for compute time — no GPUs to provision or maintain.
Start coding or describe what you need in plain English
Get completions, functions, or entire solutions
Accept suggestions, test, and deploy
Pay per second of compute. CPU: $0.000100/sec. GPU: $0.000225/sec (T4) to $0.001400/sec (A100).
View pricing on ReplicateOther Coding tools you might like
Medium
Coding
AI-first code editor built on VS Code with deep AI integration.