Announcements & Insights
New models, functionality, ecosystem updates, and analysis from the OpenRouter team.
The 2025 State of AI Report
Introducing the 2025 State of AI report, in partnership with a16z. The largest empirical look yet at how developers and organizations use language models in the real world.
Is Implicit Caching Prompt Retention?
Should customers consider providers that have implicit caching as “ZDR”?
Provider Variance: Introducing Exacto
Does the same model perform differently across different providers?
1 million free BYOK requests per month
Every customer gets 1,000,000 “Bring Your Own Key” (BYOK) requests per month for free.
The First-Ever Image Model Is Up on OpenRouter
SOTA image generation, character consistency, and multi-image outputs—now live with Gemini 2.5 Flash Image Preview.
GPT-5 is now live
GPT-5 is here on OpenRouter — long-context, built for complex reasoning and code workflows.
Audio Inputs and PDF URLs for Apps
Add voice input and send PDFs by URL, on any model.
Presets: How To Seamlessly Transfer Model Configurations Across Apps
Customize once and use everywhere. Server-side presets now simplify your model workflows.
New Privacy-Focused Provider Drop: Venice
Venice joins OpenRouter as a new provider, offering its flagship uncensored model for private, powerful, and non-restrictive AI.
Use OpenRouter Models in Cursor: Try it with Moonshot AI's Kimi K2
Explore it in action: See how effortlessly you can run Kimi K2 in Cursor using OpenRouter’s flexible model routing.