Articles from openrouter.ai

Ori Eval helps developers find the best AI model for their application by running automated evaluations on their own code, prompts, and data using an LLM judge and tool assertions.

Ori Eval tests your agent and model on custom prompts, verifies tool calls, scores answers with an LLM judge, so you catch regressions and pick the best model before shipping.

The article explains how to configure Claude Code to trigger asynchronous, non-blocking code reviews via a Stop hook that launches a Codex‑based reviewer through OpenRouter, keeping workflow uninterrupted.

OpenRouter offers a unified API for hundreds of AI models, with integration options via raw API, typed Client SDKs, or higher‑level Agent SDK for building tool‑enabled agents.

OpenRouter provides a unified API to browse, filter, and retrieve details for over 400 AI models, including pricing, capabilities, and provider info.

OpenRouter's Fusion plugin runs a panel of models in parallel, judges their responses for consensus and contradictions, and feeds structured analysis back to the calling model for a better final answer.

OpenRouter's Fusion, which synthesizes outputs from multiple language models via a judge model, outperformed individual frontier models including GPT-5.5 and Claude Opus 4.8 on deep research tasks, with a budget panel achieving near-frontier performance at half the cost.

OpenRouter ranks live LLM usage by tokens and spend, showing DeepSeek, Anthropic, and others dominating across general, agent, and code tasks.

An empirical study of over 100 trillion LLM tokens on OpenRouter reveals rising open-weight adoption, dominant roleplay and coding tasks, and a 'Glass Slipper' retention effect.