One import. Intelligent routing. Real savings. Flux picks the cheapest model for every request — no config needed.
Teams waste 40% of their LLM budget before they even know it.
Most teams default to the most capable model for every task. $0.01 per request could be $0.001.
You don't know which models work best for your tasks — or which ones are draining your budget.
Humans can't optimize model selection at scale, especially across multiple task types and customers.
A 13-step algorithm with pure heuristics — zero AI calls in the routing path.
Based on real routing optimizations across diverse task types.
No black box — every routing decision is explainable, fast, and tunable per customer.
Routes every request to the optimal model — no config, no guesswork.
Improves routing accuracy from every response. Gets smarter over time.
Real-time analytics showing spend by model, task, and customer.
Set different routing preferences for each of your customers.
<5ms routing latency. Pure heuristics — zero AI calls in the path.
AGPL-3.0 licensed. Self-host with full access to the source. Commercial licensing available — contact fluxllmdev@gmail.com
From our internal benchmarks across diverse task types.
Route simple replies to cheaper models, complex reasoning to Opus — automatically.
Summarization, extraction, classification — each task gets the right model.
Balance quality vs cost per developer tier. Per-customer tuning built in.
Join the waitlist for early access and founding member pricing.
We're an early-stage startup building Flux in the open. For any queries, reach us at fluxllmdev@gmail.com
Drop Flux into any Python project with a single import. No API key required for local routing.
# Install git clone https://github.com/vbc1406/flux cd flux pip install -r requirements.txt from router.flux import make_flux flux = make_flux() decision = flux.route( prompt="Summarize this document...", task_type='summarization' )
No API key. No signup. Just works.