A router that sends Claude, Codex, and Cursor work to cheaper models
Weave Router is a for such as Claude Code, Codex, and Cursor. It looks at each and chooses which model should handle it.
It works like an Anthropic or OpenAI endpoint, so coding tools can connect to it as if they were calling those services. It can send easier work to faster and cheaper models such as , GLM 5.2, and Kimi K2.6, while keeping harder work for such as Opus 4.8 and GPT 5.5.
The need came from Weave using AI for almost all coding work and seeing costs rise, especially after tokenizer changes in Opus 4.7. The aim is to avoid paying for the strongest model on every task while still using it when the task needs it.
Key points
- The tool plugs into such as Claude Code, Codex, and Cursor.
- It chooses a model separately for each .
- It can route simpler work to cheaper models and harder work to .
- The project was driven by rising AI coding costs after Opus 4.7 tokenizer changes.
- It presents itself like an Anthropic or OpenAI endpoint for easier integration.