Replicate Run Models — model skill for tools & renderers

For AI agents: find the right skill in one call — curl -s "https://skills.varg.ai/api/search?q=<what the person wants>" returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the use-case page.

Run Replicate models from code: predictions, webhooks, streaming, file handling and multi-model chains.

What it does

Covers running models on Replicate through its HTTP API and MCP server, with three ways to get output: predictions, webhooks and streaming. It also explains prediction lifetime, file handling and multi-model workflows.

Use when

Install

Example output

https://skills.varg.ai/previews/replicate-run-models.mp4 — Grid of six Wan 2.1 videos generated through Replicate's API, from the 'Wan2.1: generate videos with an API' post (credit: Replicate, https://replicate.com/blog/wan-21-generate-videos-with-an-api)

More tools & renderers skills

Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.