simonw/llm-openrouter

LLM plugin for models hosted by OpenRouter

What it solves

llm-openrouter is a plugin for the llm command-line utility that allows users to access a vast array of models hosted by OpenRouter, providing a unified interface for prompting different AI models from the terminal.

How it works

The plugin integrates OpenRouter's API into the llm tool. Once installed and configured with an API key, users can list available models, set aliases for frequent models, and run prompts against them. It supports OpenRouter's Responses API and the older Chat Completions API.

Who it’s for

Developers and power users who use the llm CLI tool and want a single point of access to multiple AI models from various providers via OpenRouter.

Highlights

  • Broad Model Access: Access to numerous models via a a single API key and CLI interface.
  • Multimodal Capabilities: Support for image attachments (URLs or file paths) for compatible vision models.
  • Structured Output: Integration with llm schemas to control JSON output structure for compatible models.
  • Advanced Tooling: Support for tool calls, including OpenRouter's hosted server-side tools for web search, web fetch, and a sandboxed shell.
  • Reasoning Control: Options to specify reasoning effort and summaries for models that support it (e.g., GPT-5).
  • Provider Routing: Ability to specify provider-specific requirements, such as quantization levels, via JSON options.
  • Model Management: Commands to list, filter (e.g., free models), and inspect API key usage and rate limits.

Related

  • Project
    taketwo/llm-ollama

    A plugin for the LLM CLI tool that enables interaction with models hosted on local, remote, or cloud-based Ollama servers.

  • Project
    simonw/llm-gemini

    A plugin for the LLM CLI tool that provides API access to Google's Gemini models, supporting multimodal inputs and server-side tools like Google Search.

  • Project
    projectdiscovery/aix

    A command-line tool for interacting with OpenAI's LLM APIs, allowing users to query models like GPT-3.5 and GPT-4.0 directly from the terminal.

  • Project
    simonw/llm

    A CLI tool and Python library for interacting with multiple LLMs, both via remote APIs and local installations, featuring built-in logging and structured data extraction.

  • Project
    fruitbars/simple-one-api

    simple‑one‑api is an open‑source Go gateway that unifies multiple LLM providers behind OpenAI‑compatible endpoints, adds capacity‑aware key scheduling, four‑layer rate‑limiting, a built‑in React chat UI, a visual config console, and a Wails desktop client. It can be run as a single binary, Docker container, or desktop app, and stores its configuration in SQLite.