Agent-native infrastructure

Autonomous agents,
on governed rails.

Refusion® provisions scoped agents, routes every task to the right model, and enforces spend & policy before any tool fires — all observed in one audit stream.

See what's new
Live agentic workflow · no signup

Watch an agentic task workflow run.

Pick a framework. A real support task flows through the pipeline live — every step routed to its own model, metered, and threaded into the next. This is the same primitive you provision in the console.

refusion · agentic workflow · swarm

Triage → Resolve → Draft.

Triage
Classify intent & urgency
01
waiting…
Resolve
Propose resolution steps
02
waiting…
Draft
Write the customer reply
03
waiting…
146/800
That’s a fixed demo workflow. Provision your own, set swarm-wide spend caps, and chain any agents.
Just shipped
Live sandbox

Run a real agent task — no signup.

ROI calculator

See your savings vs. frontier models.

One-click checkout

Rudy picks your plan, you pay in a click.

Trial nudges

Auto reminders before your trial ends.

Agent in action

Watch a run, end to end.

Provision an agent from the CLI, route the task to the right model, and observe the audit stream — every step governed and metered in real time.

rudy — interactive cli
rudy up support-bot
→ provisioning · namespace: support-bot
→ key issued · sk-rudy-•••• · cap $150
✓ agent active
rudy run support-bot triage "ticket #4821"
→ router: smart → claude_sonnet
→ cost $0.0042 · status allowed
rudy audit support-bot
→ 3 events · 0 revoked · spend $0.04
refusion · live run
ProvisionRouteAudit
Smart routingSpend meteredGoverned
Live sandbox · no signup

Run a real task. Watch it route.

Pick a use case, edit the prompt, and hit run. The router picks the model and meters the exact cost — the same path your agents use in production.

refusion · public sandbox
64/600
That's one run. Provision your own scoped agent to run thousands — governed and metered.
Routing savings · live

Every route saves. The numbers add up.

Refusion routes each task to the cheapest capable model and meters the difference vs. a frontier-class baseline. Here's what the public sandbox has saved so far.

No runs routed yet — run a task in the sandbox above to start the leaderboard.

The platform

Everything in the plane

Primitives to provision, route, and govern — plus a built-in CLI, demo, and docs.

Agent provisioning

Scoped namespace, API key, and a per-agent spend cap — issued in one command.

Model router

Per-task model selection with automatic failover and exact per-run metering.

Governance

Spend caps and lifecycle checks enforced before any tool is allowed to fire.

New

Multi-agent orchestration

Chain agents into supervisor-driven swarms with per-step routing and swarm-wide spend caps.

New

Interactive CLI

Provision, run, and govern agents from a single in-app terminal prompt.

New

Guided demo

Watch the full provision → route → audit flow play out end-to-end in 3 steps.

New

Platform docs

Primitives, the CLI command reference, and the governance model — all in-app.

New

Live sandbox

Run a real routed task right on the landing page — no signup required.

New

ROI calculator

Estimate monthly savings vs. raw frontier models in a few sliders.

New

One-click checkout

Rudy recommends the right plan from your quiz and starts checkout instantly.

How it works

Three primitives. One governed loop.

01

Provision

Scope a namespace, issue a key, set a spend cap.

02

Route

The router picks the model and meters exact cost per run.

03

Govern

Caps enforced before any tool fires — every run audited.

Scoped identity
a key per agent
4 routing strategies
smart · frontier · fast · cheap
Exact metering
cost logged per run
Agentic AI pricing

Pay for what your agents run.

Refusion is metered like infrastructure — provisioned agents, routed task runs, and frontier token pass-through. No per-seat tax. Every run is logged, governed, and capped.

Included monthly allowance
Starter: 3 agents · 10k runs
Scale: 20 agents · 250k runs
$2/ agent / mo

Scoped namespace, API key, spend cap. First 3 included on every plan.

$0.40/ 1k task runs

Smart-routed, governed, and audited — including fallback.

$0.06/ 1k frontier tokens

Pass-through cost when you pin the frontier strategy.

storage & RAG

Knowledge bases and shared-run storage, priced by GB/mo on paid plans.

Pricing

Plans that scale with your fleet

Start free. Upgrade when your agents hit production. Governance included on every tier.

Starter
$39/mo

First agents in production.

  • 3 provisioned agents
  • $250 spend cap / agent
  • Smart routing
  • Audit stream
Most popular
Scale
$149/mo

For operating agent fleets.

  • 20 provisioned agents
  • Custom spend caps
  • All 4 routing strategies
  • Failover + exact metering
  • Audit + revoke alerts
Enterprise
Custom

Governed, org-wide rollouts.

  • Unlimited agents
  • Dedicated routing
  • SSO / SCIM
  • SLA + priority support
  • Custom governance policies
Documentation

Read the manual — in the console.

The whole platform is documented in-app: primitives, the CLI command reference, the governance model, and how to author multi-agent swarms. Sign in to open it.

Core primitives

Agents, routing, audit — how the pieces fit.

CLI reference

Provision, run, and govern from the prompt.

Governance model

Spend caps, lifecycle checks, revocation.

Orchestration

Build supervisor-driven agent pipelines.

Read the blog
ROI

See what smart routing saves.

Estimate your monthly LLM spend on raw frontier models versus Refusion's per-task routing — and which plan fits.

Agents5 agents
Tasks / agent / day50 tasks
Avg tokens / task800 tokens
Raw frontier
$90
/ month
With Refusion
$43
/ month
Save $47/month · 52% less
Smart routing sends simple tasks to cheaper models.
Recommended: Scale
$149/mo · 5 agents

Provision your first agent in one command.

Sign in to unlock the console, the CLI, and the model router — governed by default.