Summary
A CLI wrapper that gives you access to 250+ AI models through inference.sh without needing your own GPU. You get everything from FLUX and Veo for images and video, to Claude and Gemini through OpenRouter, plus Tavily and Exa for search, Twitter automation, even 3D generation. The nice part is automatic file uploads when you pass local paths instead of URLs, and you can fire off tasks without waiting if you're orchestrating multiple models. It's really just a thin layer over their API, but that's the point. Install with a curl-to-sh script (checksums verified), run apps with `belt app run`, and you're calling expensive models serverlessly. If you're building agents that need to bounce between different model types, this beats managing a dozen API clients.
Install to Claude Code
npx -y skills add inference-sh/skills --skill infsh-cli --agent claude-codeInstalls into .claude/skills of the current project.
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
An agent that runs the SEO playbooks that move rankings and ships PRs you control.
Get founding access →
Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →Files
SKILL.md
Select a file.
Featured
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →An agent that runs the SEO playbooks that move rankings and ships PRs you control.
Get founding access →Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →
