LIVE TODAY

Built on withConflux.

Real products already ship on withConflux — LLM apps on the gateway (their own OpenAI key or managed credits) and a managed SEO directory. However each one is built, it runs without the busywork.

3
products live on the platform
10
models in the catalog
308
listings managed for one client
€40
free credits to start
Three live products

Three products, one platform.

Client names are held back on purpose — but every capability below is real, taken straight from how each one actually runs.

BYOK · own OpenAI key

A developer platform, billed on its own key

A SaaS product with an in-app AI assistant

Wanted spend caps, usage analytics and EU-hosted logging — without moving billing off its own OpenAI account. The gateway sits in front; the key stays theirs.

  • Kept the official OpenAI SDK — no call sites rewritten
  • A runtime Direct ↔ Gateway toggle — switch with no redeploy
  • Billed on their own key — control, not a markup
// the whole change
new OpenAI({
  baseURL: "https://withconflux.com/api/v1",
  apiKey:  process.env.CONFLUX_API_KEY,
})
Managed · prepaid credits

A content app with no OpenAI account at all

A social-content generation product

Didn’t want to own an OpenAI relationship — just working AI and one predictable bill. withConflux supplies the key behind the gateway and meters against prepaid credits.

  • No OpenAI account or key to manage — the gateway holds it
  • Prepaid credits + auto-reload — capped, predictable spend
  • Out of credits returns a clean 402 → graceful fallback
// same two options — key + base URL
new OpenAI({
  baseURL: "https://withconflux.com/api/v1",
  apiKey:  process.env.CONFLUX_API_KEY,  // managed
})
SEO · managed schema

A trades directory that writes no code at all

A regional home-services directory

Wanted rich structured data on every listing without building or maintaining a schema pipeline. withConflux manages it end to end and pushes it to their own site.

  • 308 listings across 33 service types managed for them
  • Schema pushed to their own domain — served locally, zero latency
  • Fully managed — nothing to build or run on their side
  • Same login adds AI Visibility — track how AI recommends their listings, and fix it
NO CODE
They connect their site once; we keep the structured data current.
Going live

Three steps from your first call.

The same path for the two gateway integrations above — the only fork is which billing mode you pick in step two.

1

Point the SDK at the gateway

Set the base URL and a withConflux key on your existing OpenAI client. Every model call stays exactly as written.

2

Pick a billing mode

Bring your own OpenAI key and keep that bill, or run on managed prepaid credits with auto-reload. Switch later with no code change.

3

Ship with the guardrails on

Spend caps, per-model usage analytics and EU-hosted logging are live from the first request — nothing extra to wire up.

What the gateway adds

Control you don’t get from the API directly.

The same OpenAI calls, now with the operations layer a product actually needs in front of them.

Spend caps

Hard limits per key, so a runaway loop can't run up an unbounded bill.

Usage analytics

Per-model, per-key breakdowns of tokens and spend — no scraping a provider console.

EU-hosted logging

Request logs stored in the EU — a straight answer for data-residency questions.

One bill

Managed clients get a single predictable invoice instead of a metered provider account.

Model catalog

Enable exactly the models your app may call — 10 in the catalog today, governed centrally.

Graceful fallback

A clean 402 when managed credits run out, so your app degrades instead of erroring.

Bring your key, or don’t

Pick the billing model that fits your team.

Both run on the same gateway and the same SDK. Start in one mode and move to the other without touching your code.

BYOK

Bring your own key

For teams that already own their OpenAI relationship.

  • Keep billing on your own OpenAI account
  • Gateway adds caps, analytics and logging on top
  • Flat platform plan — no markup on tokens

Best when you want control and observability, not a new billing relationship.

Managed

Managed credits

For teams that just want working AI and one invoice.

  • No OpenAI account to open or manage
  • Prepaid credits with auto-reload
  • One predictable bill, clean 402 when credits run out

Best when you’d rather not run an OpenAI account at all.

Your turn

Point your SDK at withConflux and ship.

Two lines to integrate, your choice of billing, guardrails on from the first call. The gateway guide walks through both modes end to end.

Client identities anonymized on purpose. Every claim on this page is a real capability of the two live integrations — no quotes, ratings or invented metrics.

Keep exploringOne API →How it works →Pricing →
We use a single analytics cookie to understand traffic to this site. Nothing loads until you choose. See our Privacy Policy.