ModelMix front-tier routing dashboard

Auto-route tasks between frontier and budget models for indie devs

Problem

One developer running seven projects found a workflow of using frontier models for kickoff and reviews, and budget models for daily coding, cutting costs by 80%. But the method is hand-rolled: no tool records which model handled which task, what it cost, or how quality changed. Others in the same community debate whether Haiku 5.5 beats 6Luna and want free switching between providers. Everyone picks models by gut feel without cost-quality data.

Solution

A CLI/desktop tool that sits between AI coding agents and API providers, auto-routing by task type: architecture and review go to frontier models, autocomplete and test runs go to budget models. It logs each call's model, tokens, latency, and whether the output was accepted, generating a personal cost-quality dashboard plus head-to-head model comparisons.

Users

Indie devs juggling multiple projects, tech leads at small teams, and heavy AI coding users paying their own API bills.

MVP

A local proxy supporting OpenAI, Anthropic, and Google APIs; built-in default routing for three task types; per-session model, cost, and pass-rate logging; daily/weekly cost-quality reports; a single command to flip global policies.

Revenue

Free tier limited to one project and one routing policy; one-time purchase unlocks multi-project support, custom rules, and team comparison reports.

Why now

The price gap between frontier and budget models keeps widening, but existing comparisons are vendor benchmarks, not personal task data. Developers are already inventing this workflow, proving demand. A local middleware layer has no platform risk for a solo builder.