AI News

OpenRouter MCP Upgrade: Model Query Context Reduced by 96%, Installation Can Be Completed by Agents Reading It Themselves

OpenRouterUpdated Nov 10 00:37

AI summary

OpenRouter announced an MCP upgrade, allowing users to directly call 600+ models, the Decisions API, and image, speech, and video generation within agent conversations. Model query responses have been reduced from about 1 MB (about 250k tokens) to 38 KB with pagination, a 96% reduction; video tasks are initiated by the agent and then retrieve a link, no longer stuffing raw bytes into the context. The installation method has changed to having the agent read the installation page and complete it on its own; the official statement says that in its tests, Claude Code improved from 5/8 tasks to 8/8.

Why read this

AI score 53

The original article lists the context usage, video tasks, and installation method changes after the MCP upgrade, which can be used to judge the cost of agents connecting to OpenRouter.

Topics

Tags

Body

Installing is even easier now. Tell your agent to go to https://t.co/nO1wcOJJ79. The page is readable by agents as well as humans, so your agent reads the setup and does it for you. https://t.co/l8MFi8ruwF

Source

OpenRouter