skills.rest
Aadi-110i
Aadi-110iCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

llm-models

Access Claude, Gemini, Kimi, GLM and other LLMs via OpenRouter through the inference.sh CLI.

Updated Jul 28, 2026
Search Tags:#api#code generation#cli#llm#claude#openrouter#ai models
One-click install
npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill llm-models-aadi-110i
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llm-models
Source: https://github.com/Aadi-110i/PEP-PROJECT/tree/main/skills/llm-models
Command: npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill llm-models-aadi-110i

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Integrating multiple large language models normally requires managing separate API keys, SDKs, and billing accounts for each provider. This Skill unifies access to 100+ models through a single CLI, with automatic model selection and cost optimization. ## Core Features & Use Cases - Multi-Model Access: Call Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, Gemini 3 Pro, Kimi K2, GLM-4.6, and Intellect 3 through one OpenRouter-based interface. - Automatic Model Selection: The openrouter/any-model app picks the most cost-effective model for a given prompt. - System Prompt Support: Pass custom system prompts via JSON input files for controlled assistant behavior. - Use Case: A developer building a coding assistant can prototype with Claude Haiku for cheap iterations, then switch to Claude Opus for complex reasoning tasks by changing only the app ID. ## Quick Start Ask the assistant to run a prompt through Claude Sonnet using the belt CLI, for example: use the llm-models skill to ask Claude Sonnet to explain 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 call Claude API through OpenRouter from the command line?▼

Install the inference.sh belt CLI, run belt login, then execute belt app run with an app ID like openrouter/claude-sonnet-45 and a JSON input containing your prompt. The same pattern works for Claude Opus, Haiku, and other models.

What LLM models are available through OpenRouter?▼

Available models include Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, Gemini 3 Pro, Kimi K2 Thinking, GLM-4.6, and Intellect 3. The openrouter/any-model app automatically selects a cost-effective model for your prompt.

How do I add a system prompt to an LLM API request?▼

Generate a sample input file with belt app sample openrouter/claude-sonnet-45 --save input.json, then edit the JSON to include a system field alongside your prompt. Run the request with belt app run using that input file.

Which Claude model should I use for coding tasks?▼

Claude Opus 4.5 is suited for complex reasoning and coding, Claude Sonnet 4.5 offers balanced performance, and Claude Haiku 4.5 is faster and cheaper for simple tasks. Choose based on task complexity and budget.

What are the prerequisites for using the belt CLI?▼

You need the inference.sh belt CLI installed and authenticated via belt login before running any model. Installation instructions are provided in the inference.sh skills repository documentation.

Related Skills

Explore More Software Engineering Skills→
inference-shinference-sh
723

elevenlabs-tts

Generate speech audio from text using ElevenLabs voices via the inference.sh CLI.

Official
Basic
ajilantonyajilantony

agentic-eval

Evaluates AI outputs via self-critique loops and iterative refinement.

Community
Advanced
leonardoteodorooleonardoteodoroo

rag-implementation

Builds minimal RAG pipelines combining vector stores and document retrieval for grounded answers.

Community
Advanced
global-osglobal-os

ai-gateway

Route AI model requests across providers with failover and cost tracking.

Official
Advanced