L

Access over 100 language models including Claude, Gemini, Kimi, and GLM via the inference.sh CLI using OpenRouter.

LLM Models

Access 100+ LLMs via inference.sh CLI using OpenRouter with automatic fallback and cost optimization.

Knowledge WorkflowTool OrchestrationAgent Workflow
709 Stars96 ForksUpdated Aug 24, 2026View source
OverviewCapabilitiesQuick start

Skill impact

A focused workflow with measurable value.

Stars

709

Forks

96

Updated

Aug 24, 2026

About LLM Models

Access Claude, Gemini, Kimi, GLM and 100+ LLMs via inference.sh CLI using OpenRouter. Models: Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, Gemini 3 Pro, Kimi K2, GLM-4.6, Intellect 3. One API for all models with automatic fallback and cost optimization.

What LLM Models Can Help You Do

Enables users to run, test, and integrate multiple large language models such as Claude, Gemini, and Kimi through a single CLI interface with cost optimization and fallback support.

Run multiple large language models through a unified CLI interface
Auto-select the most cost-effective model using an automated routing option
Pass custom system prompts and user inputs via inline options or JSON files
Execute multi-step reasoning and coding tasks with specialized models like Kimi K2 Thinking and Claude Opus

Common use cases

01

Generating, reviewing, and debugging source code across projects

02

Drafting written content, summaries, and translations

03

Interpreting data and conducting technical research

04

Building AI-powered agents and automated workflows

05

Creating conversational chatbot interfaces

Quick start

Install command

npx skills add inference-sh/skills@llm-models

Tags

Topics and capabilities

#Agent Skills#Prompt Workflows#Research Automation