Better prices , better uptime , no subscriptions. Featured Models 500+ active models on 80+ providers Featured Agents 250k+ apps using OpenRouter with 4.2M+ users globally The easiest way to go from idea to app An autonomous agent that grows with you The open-source AI coding agent Create an account to get started. You can set up an org for your team later. Credits can be used with any model or provider.

Get your API key Create an API key and start making requests. Fully OpenAI compatible . Recent Blog Posts Server-Side Code Execution Tools for AI Agents, Compared A server-side code execution tool runs the model's commands in the provider's sandbox during your API request, so you don't provision or secure a container. OpenAI, Anthropic, and Google run code for their own models. Our openrouter:shell tool runs commands for any model on the Responses and Messages APIs, and our openrouter:bash tool does the same on the Messages API. This article compares the four on runtime, isolation, persistence, and cost, shows a complete request against our sandbox with the output it returned, and describes the jobs that still need a sandbox platform of your own. Model Routing for Support Bots: Cheap-First FAQ Handling Cheap-first routing sends routine support questions to a small, inexpensive model and escalates selected hard or uncertain requests to a stronger one. This guide compares the three application-side routing patterns, separates what your application owns from what OpenRouter's Auto Router and model fallbacks handle, walks through a support flow with a copyable request, and sets out how to measure escalation rate and cost per resolved ticket. Model Router Benchmarks We now benchmark model routers side by side across six suites. Our Router Index weighs quality, speed, and cost so you can decide if you need a router and pick the best one for your needs.