mcpField
L
llm-models

llm-models

github.com/inference-shAgent workflows7891.0k installsUpdated 2w ago
Repository

About llm-models

llm-models is a skill for calling language models through OpenRouter with the inference.sh CLI. It is for users applying LLMs to coding, writing, analysis, and agent workflows, and lists model options alongside an app that selects a model automatically.

Key features

  1. 01Call multiple language models through the CLI
  2. 02List models and their app IDs
  3. 03Search model apps by name
  4. 04Use an app that selects a model automatically
  5. 05Pass a system prompt

Use cases

  1. 01Generate, review, or debug code
  2. 02Write content, summaries, and translations
  3. 03Analyze data or conduct research
  4. 04Add LLMs to agent workflows

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/inference-sh/skills --skill llm-models

After installing, type/llm-modelsin Claude Code to confirm it loaded.

Details

From the project README

Install the belt CLI skill: npx skills add belt-sh/cli

LLM Models via OpenRouter

Access 100+ language models via inference.sh CLI.

LLM Models via OpenRouter

Quick Start

Requires inference.sh CLI (belt). Install instructions

belt login

# Call Claude Sonnet
belt app run openrouter/claude-sonnet-45 --input '{"prompt": "Explain quantum computing"}'

Available Models

ModelApp IDBest For
Claude Opus 4.5openrouter/claude-opus-45Complex reasoning, coding
Claude Sonnet 4.5openrouter/claude-sonnet-45Balanced performance
Claude Haiku 4.5openrouter/claude-haiku-45Fast, economical
Gemini 3 Proopenrouter/gemini-3-pro-previewGoogle's latest
Kimi K2 Thinkingopenrouter/kimi-k2-thinkingMulti-step reasoning
GLM-4.6openrouter/glm-46Open-source, coding
Intellect 3openrouter/intellect-3General purpose
Any Modelopenrouter/any-modelAuto-selects best option

Search LLM Apps

belt app search "openrouter"
belt app search "claude"

Examples

Claude Opus (Best Quality)
belt app run openrouter/claude-opus-45 --input '{
  "prompt": "Write a Python function to detect palindromes with comprehensive tests"
}'
Claude Sonnet (Balanced)
belt app run openrouter/claude-sonnet-45 --input '{
  "prompt": "Summarize the key concepts of machine learning"
}'
Claude Haiku (Fast & Cheap)
belt app run openrouter/claude-haiku-45 --input '{
  "prompt": "Translate this to French: Hello, how are you?"
}'
Kimi K2 (Thinking Agent)
belt app run openrouter/kimi-k2-thinking --input '{
  "prompt": "Plan a step-by-step approach to build a web scraper"
}'
Any Model (Auto-Select)
# Automatically picks the most cost-effective model
belt app run openrouter/any-model --input '{
  "prompt": "What is the capital of France?"
}'
With System Prompt
belt app sample openrouter/claude-sonnet-45 --save input.json

# Edit input.json:
# {
#   "system": "You are a helpful coding assistant",
#   "prompt": "How do I read a file in Python?"
# }

belt app run openrouter/claude-sonnet-45 --input input.json

Use Cases

  • Coding: Generate, review, debug code
  • Writing: Content, summaries, translations
  • Analysis: Data interpretation, research
  • Agents: Build AI-powered workflows
  • Chat: Conversational interfaces

Related Skills

# Full platform skill (all apps)
npx skills add inference-sh/skills@infsh-cli

# Web search (combine with LLMs for RAG)
npx skills add inference-sh/skills@web-search

# Image generation
npx skills add inference-sh/skills@ai-image-generation

# Video generation
npx skills add inference-sh/skills@ai-video-generation

Browse all apps: belt app list

Documentation

Comments

Markdown supported