Skip to content
Mercury .

Mercury Flux is Mercury Technology Solutions' AI cost optimization layer: a multi-model router that sends each task to the cheapest capable tier (local, cheap, mid, premium), verifies quality with deterministic tests, and learns from outcomes. It is the cost-effective update to Mercury Core and can run as a Booster Pack on Core or as a standalone service.

Multi-model orchestration, LLM cost optimization, agent routing, quality gates, token ledgers, self-hosted inference

Mercury Technology Solutions, Mercury Flux, Mercury Core, Herdr Core, OpenClaw, Flux Cloud, Flux Intel

Cost layer for Mercury Core · standalone capable

AI spend that flows to the right model.

Mercury Flux is the cost-effective update to Mercury Core. It routes every AI task to the cheapest model that can do it well — premium, budget, or your own GPUs — and proves quality with real tests before anything ships. Run it on Core, or as its own service.

Cost-effective Core updateStandalone serviceQuality gated

60–75% typical cost reduction · zero vendor lock-in · open-source core

FLUX ROUTER — LIVE
TASKS0 inFLUXtriage · routelocal · self-hosted$0cheap · haiku-class$mid · deepseek-class$$premium · opus-class$$$
Tasks routed
0
Premium share
0%
Saved this run
$0.00
all-premium baseline $0.00flux-routed $0.00
Definition

What Mercury Flux is

Mercury Flux is the AI cost optimization layer from Mercury Technology Solutions. It is the cost-effective update to Mercury Core: a multi-model router that sends every task to the cheapest capable tier (local, cheap, mid, premium), verifies quality with deterministic tests, and ledgers every token. Install it as a Booster Pack on Mercury Core, or run it as a standalone service with no Core license.

Key takeaways

What executives should remember

  • Flux is the cost-effective update to Mercury Core — same family, cheaper path.
  • It also runs standalone. No Core license is required to route, ledger, or verify.
  • Typical savings are 60–75% versus an all-premium baseline on mixed-difficulty work.
  • Quality is gated by real tests. Cheap models cannot silently degrade output.
  • Herdr Core is open source. Flux Cloud and Flux Intel are optional commercial layers.
01 / The problem

You're overpaying for intelligence you don't use.

$$$ → $

Premium prices for junior work

Renaming config keys doesn't need a $15/M-token model. Neither does 70% of your workload — but that's what you're paying for it.

1 vendor

Locked to one provider

Every switch means rewrites, retesting, renegotiation. So you never switch — and your provider's pricing team knows it.

???

A black-box bill

AI spend lands on the credit card with no breakdown by feature, project, or client. Good luck defending it at budget review.

02 / How it works

One layer between you and every model.

Flux sits above the providers. Swap any model by editing one config line — adopt next quarter's cheaper model this afternoon, not next sprint.

1

Triage

A lightweight classifier scores each task's difficulty — trivial to expert — for fractions of a cent.

2

Route

Tasks flow to the cheapest capable tier: local → cheap → mid → premium. Speculative execution tries cheaper first.

3

Verify

Deterministic tests run in a sandbox before any model reviews anything. Shaky approvals get a second opinion.

4

Learn

Outcomes feed back into routing. The engine gets sharper — and cheaper — every week it runs.

router.config.yamlyour entire integration
# Four lines of config. No rewrites.
stages:
  executor:
    tier: mid              # Flux speculatively tries cheaper first
    fallback_tier: premium
budget:
  projects:
    client_a: 500000    # hard cap, enforced before every call

Works with the providers you already pay — Claude, GPT, DeepSeek, Qwen, or your own vLLM/Ollama GPUs.

03 / The numbers

Measured on your workload, not our slide deck.

60–75%
typical cost reduction vs. all-premium baseline
$0
marginal cost on the self-hosted local tier
<1 day
to adopt a newly launched model
100%
of tokens ledgered, per project, auditable

Savings depend on workload mix — the Flux dashboard shows yours exactly, from your own runs. Figures are versus an all-premium baseline on mixed-difficulty work.

04 / Why teams choose Flux

An asset that compounds, not a bill that grows.

It learns your codebase

The learning router tracks which tier succeeds at which task type in your repos and adjusts automatically. Your routing intelligence never leaves your infrastructure.

Quality is enforced, not hoped for

Real test suites gate every change; low-confidence approvals trigger an automatic second opinion. Cheap models can't quietly degrade output.

It never goes down

Per-provider circuit breakers with automatic failover up the tier ladder. One provider's outage is your non-event.

Built for agencies

Hard per-project budgets mean Client A can never burn Client B's tokens. Every dollar attributed, every run ledgered.

Self-host friendly

Route routine work to your own GPUs at zero marginal cost. Rent what's spiky, own what's predictable.

CFO-ready

Spend per project, per stage, per feature — with savings vs. baseline on one dashboard. AI goes from black-box expense to managed portfolio.

05 / Open core

Open at the core. Yours at the edges.

The routing engine is open source — audit it, fork it, self-host it, never pay us a cent. Commercial layers add hosted intelligence.

Open source

Herdr Core

Free · forever

  • Full routing engine + 4-tier ladder
  • Learning router + outcome tracking
  • Local ledger and cost dashboard
  • Circuit breakers and failover
Cloud

Flux Cloud

Per project · pays for itself in one saved premium day

  • Everything in Herdr Core
  • Hosted dashboards and alerting
  • Team budgets and roles
  • Slack / webhook cost alerts
Enterprise

Flux Intel

Custom

  • Everything in Flux Cloud
  • Cross-fleet routing benchmarks from opt-in anonymized data
  • SSO, audit export, SLA
  • Booster Pack install on Mercury Core
FAQ

Frequently asked questions

Mercury Flux is an AI cost optimization layer. It routes every task to the cheapest model that can do it well, verifies quality with real tests, and ledgers every token. It is the cost-effective update to Mercury Core and can also run as a standalone service.
Ready when you are

Stop paying senior prices for junior work.

five minutes to your first routed run · MIT-licensed core