openrouter

Route requests to over 200 LLMs via an OpenAI-compatible API.

68|19|Updated Nov 21, 2025
One-click install
npx skills add https://github.com/bobmatnyc/claude-mpm-skills --skill openrouter-bobmatnyc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openrouter
Source: https://github.com/bobmatnyc/claude-mpm-skills/tree/main/toolchains/ai/services/openrouter
Command: npx skills add https://github.com/bobmatnyc/claude-mpm-skills --skill openrouter-bobmatnyc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill simplifies AI model integration by providing a single, OpenAI-compatible API to access over 200 different language models, eliminating the need to manage multiple vendor-specific SDKs and APIs.

Core Features & Use Cases

  • Unified Access: Connect to models from OpenAI, Anthropic, Google, Meta, and more through one endpoint.
  • Intelligent Routing: Dynamically select the best model based on cost, speed, or quality requirements.
  • Streaming & Function Calling: Supports real-time responses and tool integration for complex applications.
  • Use Case: Develop a chatbot application that can seamlessly switch between Claude 3.5 Sonnet for high-quality responses and Gemini Flash for faster, cheaper queries, all managed through a single API.

Quick Start

Use the openrouter skill to send a chat completion request to the 'anthropic/claude-3.5-sonnet' model with the message 'Hello!'.

Frequently Asked Questions about openrouter

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

FAQPage Schema
How do I access multiple LLM providers through a single API?

You can access multiple LLM providers through a single API by using an OpenAI-compatible gateway that routes requests to over 200 models from providers like OpenAI, Anthropic, and Google, eliminating the need for multiple vendor-specific SDKs.

Can I use the OpenAI SDK to connect to Anthropic and Google models?

Yes, you can use the OpenAI SDK to connect to Anthropic and Google models. The unified API gateway integrates via the OpenAI SDK, allowing seamless adoption and switching between different providers like Claude 3.5 Sonnet and Gemini Flash.

What is the best way to optimize LLM costs without switching SDKs?

The best way to optimize LLM costs without switching SDKs is to use intelligent routing. This dynamically selects the best model based on cost, speed, or quality requirements, allowing you to switch to cheaper models for faster queries seamlessly.

How do I send a chat completion request to a specific model using a unified API?

To send a chat completion request to a specific model using a unified API, you target the desired model identifier, such as 'anthropic/claude-3.5-sonnet', through the single endpoint, facilitating access across multiple providers.

Does a unified AI API support streaming responses and function calling?

Yes, a unified AI API supports streaming responses and function calling. It facilitates real-time responses and tool integration for complex applications, alongside vision capabilities across the 200+ available models.

When do I need a unified API gateway for large language models?

You need a unified API gateway for large language models when managing multiple vendor-specific SDKs becomes complex. It simplifies AI model integration by providing a single endpoint to access over 200 models, supporting intelligent routing and real-time responses.