inference.sh CLI — 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.

Log in to inference.sh and run its catalog of AI apps — image, video, audio, LLMs, search — from one CLI.

What it does

Sets up and drives inference.sh's belt CLI: logging in (or setting INFERENCE_API_KEY for agents), browsing apps and running them with JSON input. The catalog spans FLUX, Veo, Seedance, Grok, OmniHuman and many more for image, video, 3D, LLM and search tasks.

Use when

Install

Models it drives: flux_dev, veo_3_1, seedance_2, grok_imagine, omnihuman_v1_5

Example output

https://skills.varg.ai/previews/infsh-cli.mp4 — inference.sh's demo of an agent (Hermes Agent) driving the inference.sh CLI: it generates 'a cat with a top hat in anime style' with p-image, then animates it with p-video; the clip shows the terminal and the resulting video (credit: inference.sh (@inference_sh), https://x.com/inference_sh/status/2033891339176116299)

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.