llm-models

Access over 100 LLMs including Claude and Gemini via inference.sh CLI and OpenRouter.

688|95|Updated Jan 31, 2026
One-click install
npx skills add https://github.com/inference-sh/skills --skill llm-models-inference-sh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: llm-models
Source: https://github.com/inference-sh/skills/tree/main/tools/llm/llm-models
Command: npx skills add https://github.com/inference-sh/skills --skill llm-models-inference-sh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a unified interface to access a vast array of Large Language Models (LLMs) through the inference.sh CLI, simplifying AI model selection and integration for various natural language tasks.

Core Features & Use Cases

  • Unified LLM Access: Interact with over 100 LLMs, including Claude, Gemini, Kimi, and GLM, via a single API.
  • Cost & Performance Optimization: Automatically selects the best model based on cost and performance, with fallback options.
  • Use Case: Developers can easily switch between different LLMs for tasks like code generation, content creation, or complex reasoning without modifying their core application logic.

Quick Start

Use the infsh app run command to call Claude Sonnet with a prompt explaining quantum computing.

Frequently Asked Questions about llm-models

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I access multiple LLM APIs like Claude and Gemini through a single interface?

You can access over 100 LLMs like Claude and Gemini through a single interface using the inference.sh CLI. It provides a unified API for diverse models, enabling programmatic interaction for tasks like code generation and reasoning.

What is the best way to switch between different language models for code generation without changing application logic?

The best way to switch between language models without modifying application logic is using a unified LLM access interface. The inference.sh CLI automatically selects the best model based on cost and performance with fallback options.

Can I use the inference.sh CLI for AI assistants and complex reasoning tasks?

Yes, you can use the inference.sh CLI for AI assistants and complex reasoning tasks. It supports accessing over 100 Large Language Models including Claude, Gemini, Kimi, and GLM for diverse natural language processing requirements.

Does inference.sh support automatic fallback and cost optimization for LLM APIs?

Yes, inference.sh supports automatic fallback and cost optimization for LLM APIs. It automatically selects the best model based on cost and performance, ensuring resilient and optimized programmatic interaction with diverse language models.

How do I call Claude Sonnet via the inference CLI for content generation?

You can call Claude Sonnet for content generation by using the infsh app run command with a specific prompt. This provides direct programmatic interaction with the model through the unified inference.sh interface.