← Back to Multos AI

Code Mode

60% cost reduction on every request

Reduces tool definitions from ~3,500 tokens to ~600 tokens by batching operations into execute_multos_code(). Combined with prompt caching, saves up to 72%.

How it works

Instead of exposing 22+ individual tools, Code Mode uses 4 core tools: file_read, file_write, shell, and execute_multos_code. The LLM writes Python code that executes all operations in a single call. 83% reduction in tool definitions.

Try Code Mode Today

42 AI models, 71 skills, 9 deploy targets — all in one platform.

Get Started Free