cd /news/large-language-models/do-not-add-an-llm-router-until-you-c… · home topics large-language-models article
[ARTICLE · art-55850] src=dev.to ↗ pub= topic=large-language-models verified=true sentiment=· neutral

Do Not Add an LLM Router Until You Can Defend Each Downgrade

A developer released Frugon, an MIT-licensed CLI tool that analyzes OpenAI-compatible request/response logs to help teams decide which LLM calls can be downgraded to cheaper models without sacrificing quality. The tool generates a reviewable hypothesis for cost savings by comparing candidate models and estimating costs, rather than applying blanket downgrades. Frugon also includes a capture mode that logs requests locally for analysis.

read2 min views1 publishedJul 12, 2026

When an LLM bill grows, the tempting answer is a blanket model downgrade. That is usually the wrong first move. A support classification, a retrieval rewrite, and a complex planning step do not have the same failure cost.

The useful question is: which calls have evidence that they can be cheaper?

Frugon is an MIT-licensed, Python 3.10+ CLI that analyzes OpenAI-compatible request/response JSONL logs. Its stated purpose is to compare candidate models, estimate costs, and propose a split between calls that might move and calls that should remain on the baseline. See the README, project configuration, and v0.2.4 release.

The interesting part is not a headline saving. It is converting a bill into a reviewable hypothesis:

That sequence is boring in the best way. It creates an artifact an engineering team can challenge, reproduce, and roll back.

Frugon also includes frugon capture

. Its capture implementation runs a local HTTP server, forwards OpenAI-compatible completion requests to the configured upstream, and stores canonical JSONL records locally.

This deserves normal production scrutiny. Logs can contain prompts and responses; retention and redaction are still your responsibility. Optional quality measurement uses your own provider keys, so it is a real provider-boundary decision, not a free offline proof. The source also validates upstream schemes and strips sensitive headers on cross-origin redirects—good defensive detail, but not a substitute for your own review.

Frugon looks most useful for teams that already retain compatible call logs and need a defensible downgrade shortlist. It is less useful if you have no representative task set, because a cost estimate cannot prove output quality.

Not tested / not run: this is a public-documentation and source review only. I did not install, execute, benchmark, or validate Frugon in a production workload. The project’s MIT license and public repository are linked for further review.

── more in #large-language-models 4 stories · sorted by recency
── more on @frugon 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/do-not-add-an-llm-ro…] indexed:0 read:2min 2026-07-12 ·