Weave Develops Model Router for Efficient AI Coding Agent Requests

Jun 26, 2026

AI Summary

Weave has created a model router that optimizes requests to various coding agents by selecting the most suitable AI model for each task. This innovation has reportedly reduced costs by 40% without compromising performance, and the router is available for self-hosting or through a hosted service.

Weave has developed a model router that integrates with coding agents like Claude Code, Codex, and Cursor to optimize task requests.
The router intelligently determines which AI model to use based on the nature of the request, balancing cost and performance.
It can utilize both faster, cheaper models and more advanced models as needed, depending on the complexity of the task.
The routing model was trained using data from tens of thousands of agent interactions, rewarding successful task completions.
Weave reports a 40% reduction in token costs since implementing the router, with no noticeable decline in quality or speed.
The router is available under the Elastic License 2.0 for self-hosting, or users can opt for a hosted version at weaverouter.com.

model routingcoding agentscost efficiencyAI developmentWeave

Weave Develops Model Router for Efficient AI Coding Agent Requests

Related Stories

OpenAI discontinues Atlas but enhances AI browsing features in ChatGPT and Chrome extension

Meta launches Muse Spark 1.1, a new AI coding model to compete in the market

Meta introduces AI image generator, raises concerns over use of public Instagram photos

Meta to Begin Production of New AI Chips in September to Reduce GPU Costs