Code Mode Delivers 99.2% Cost Reduction by Bypassing Raw Data
Code mode yields a 99.2% cost reduction in our systems
We measured our production systems and found that using Code Mode to bundle 26 tool calls into a single script cut costs by 99.2%. Instead of flooding the model with millions of raw JSON characters, our agents run tasks in a sandbox and only send the final summary. This approach, similar to techniques from Cloudflare and Anthropic, reduces token usage from over 800,000 to just 6,450 for the same triage workflow, proving that keeping raw data out of the context window is a massive efficiency win.
The raw data never has to pass through the model's context.
- shireboy
A maxim I’ve arrived at working w llm every day is “put deterministic things in code, non deterministic in llm”. I do wish the harnesses would be more helpful in this regard. For example I’ve seen tons of scheduled jobs that people wrote in Claude/copilot/etc that could easily have been scripts. They aren’t scripts because the author doesn’t know how to script and they stop at the point the llm does what they want. It isn’t hard to then tell the llm “make a script to do all of the tool calls this prompt needs and then pass the result back to the llm for this non-deterministic part”.
- somnium_sn
I am still a bit surprised that this is not more widely used. Normal inference + tool calls is effectively composition via serialized natural language, whereas Code Mode / Programmatic Tool Calling is using purpose built languages (aka programming languages) for composition and concurrency. It somewhat feels obvious to me that the latter is way more token and latency efficient.
- fg137
The article is so painful to read.
- peterbell_nyc
Yeah, this has been my biggest contention with the models everywhere paradigm. I will definitely use a supervisor pattern and advisor pattern for simpler models when I just want to throw something together interactively with Fable and a few sub-agents. But for anything I am doing repeatedly, I built a deterministic orchestrator to run the steps and I have a hard rule that the skills that run from my repo can only ever be a thin shims calling to my central system so that rather than having agents enrich a person or call an API or do research they fire off predefined multi-step deterministic plays that just might have models for classification generation summarization and/or review.
In addition to the reliability and cost benefits you also then get shared capacity broker capabilities so if you're only able to enrich so many people or only capable of doing so many CI runs if that's all done deterministically you can have some intelligent orchestration in your main server to manage that limited capacity across all your agents that are trying to use it at the same time.
- jonathanlydall
We ultimately switched to this approach with great success for our own product. We stumbled on its success a little by chance.
We have a visual designer and for LLMs to interact with it we originally built a tool per manipulation operation type (e.g. add, edit, delete item - for various item types).
We actually already had a JavaScript API with corresponding .d.ts file for scripting inside our product and one of our clients asked that we also expose this as an MCP tool. I figured sure, should be quite quick and easy, and with Claude Code's help I managed to do it in a single afternoon.
We then found that the LLMs way preferred reaching for this tool, managing with it to get their tasks done with fewer mistakes along the way and in much smaller time frames.
After seeing this and doing some more validation (I've also read that Cloudflare article), we ditched the other tools completely and made a cheat sheet for the LLMs on how to use our API.
Because our API returns decent error messages including stack traces, even if the script fails the LLMs have no trouble making another script to fix their mistake and carrying on from where the error occurred.
In hindsight it really was hardly surprising as LLMs are already aiming to be as good as possible at coding and with JS being so popular I imagine it's particularly good at it.