Fully Managed OmniRoute
as a Service

Deploy OmniRoute as a fully managed service starting at €9/mo. Get automated backups, SSL, updates, support and monitoring included.

OmniRoute is a self-hosted AI gateway. It puts one OpenAI-compatible endpoint in front of every model provider you already pay for, routes each request by the policy you set, and fails over to the next provider when a quota trips.

✓Free 7-day trial  ✓99.9% Uptime SLA  ✓No credit card  ✓Cancel anytime

✓Free 7-day trial  ✓99.9% Uptime SLA
✓No credit card  ✓Cancel anytime

OmniRoute

OmniRoute

STARTING AT

€9/month
Automated Backups
Monitoring
Automated Updates
Auto SSL

USAGE

Unlimited
Human Support
Custom Domains
Terminal Access
File Manager Access
Deploy in your region — 21 locations worldwide
GermanyFinlandNetherlandsUKSwedenUnited StatesCanadaSingaporeJapanAustraliaBrazilSouth Africa+9 more →
OmniRoute Preview Image

ABOUT THE SOFTWARE

What is OmniRoute

OmniRoute is an open-source AI gateway you host yourself. It exposes a single OpenAI-compatible endpoint, holds your provider credentials encrypted on your own instance, and decides per request which upstream model provider should answer and what happens when that provider says no.

The project is MIT-licensed and maintained in the open by an independent developer, with no contributor licence agreement and no trademark policy restricting commercial hosting. That matters more than it sounds: several tools in this category have moved to source-available terms that forbid exactly this kind of managed offering. We check the licence on every major release before a version reaches your instance.

Technically it is a TypeScript application on Next.js that keeps its state in SQLite through a compiled native module, with an optional Redis backend for rate limiting. It ships a web dashboard, a command-line client, and a desktop build. The runtime is pinned to a narrow band of Node versions, which is the source of its most common self-hosting failure and one of the things a managed instance takes off your desk.

FEATURES

What OmniRoute does

OmniRoute sits between your tools and your model providers. It normalises the request format, chooses an upstream by policy, retries elsewhere on failure, meters what each key spends, and keeps the record of what was asked on hardware you control rather than a vendor dashboard.

One OpenAI-compatible endpoint

Anything that speaks the chat-completions API points at a single base URL. No client-side SDK swap and no per-tool credential sprawl.

Multi-provider routing

Requests are matched to an upstream by model name, cost band or explicit rule, so cheap work never lands on your most expensive provider.

Automatic failover

When an upstream returns a quota, rate-limit or availability error, the request cascades to the next provider in the chain instead of failing.

Per-key rate limits and budgets

Every issued key carries its own daily, weekly and monthly ceiling, which makes a runaway agent loop a capped incident rather than an invoice.

Call logging with retention control

Each request is recorded with model, tokens and outcome, and the retention window is a setting rather than a vendor policy.

Encrypted credential storage

Provider keys are encrypted before they touch disk, and whole-database encryption is available on top of that.

Input sanitising and response filtering

Optional guards inspect prompts for injection patterns and strip identifying strings out of requests before they leave your instance.

Dashboard and command line

Routing rules, keys and spend are managed from a browser or scripted from a CLI, so the same policy can live in your own repository.

WHAT'S ALWAYS INCLUDED

Every app. Fully managed.
Nothing extra to pay for.

Every app on DANIAN ships with the same operational baseline. You do not choose a backup add-on or a monitoring tier. Hosting, patching, backups, SSL, and support are part of the €9, and they apply to OmniRoute the same way they apply to everything else in the catalog.

Automatic updates and patches

Apps run the latest stable version. Security patches applied silently, with rollback if needed.

Daily off-site backups

Multiple daily backups in redundant off-site locations. One-click restore if anything goes wrong.

24/7 uptime monitoring

Continuous monitoring with instant alerting. We respond before you notice.

SSL, firewall, DDoS protection

Auto-renewing SSL, hardened firewall rules, DDoS mitigation on every deployment.

Performance and scaling

We monitor resource usage continuously. When your app needs more headroom, we flag it and upgrade with your explicit approval.

Dedicated engineering support

Real engineers by email and ticket. DNS, SMTP & migration help. All included in €9.

WHY MANAGED

Why teams pick managed OmniRoute

The trigger is the move from flat monthly seats to metered usage across the coding-assistant vendors. Teams that budgeted a fixed line item now face a meter, and a gateway that routes by policy and fails over on a quota trip becomes the cheapest control they can put in front of it.

Running the gateway itself is the easy part. What follows it is not. The application keeps every route, key, policy and call log in a SQLite file reached through a compiled native module, and that module is built against one specific Node runtime. Upgrade the runtime underneath an existing install and the binary no longer loads: the process exits, the service crash-loops, and every client pointed at the endpoint starts failing at once. The recovery is a rebuild of the native module in place, which is fine if you know that is the failure and expensive if you do not.

The same module has a second edge. The shipped prebuilt binaries are compiled for x86_64, so an install on an ARM host throws an architecture mismatch on load and cannot be rebuilt against the vendored copy. Logins fail, settings reads fail, and proxy logging stops. We run these instances on x86_64 hosts for that reason, and we rebuild the native module against the target runtime in staging before any release is promoted to your instance.

REVIEWS

Hear from customers ​like you​​​​​​​

Successful businesses and professionals around the world rely on DANIAN every day

USE CASES

Three teams who run OmniRoute on DANIAN

The pattern is consistent across team sizes: several tools, several provider accounts, one endpoint in the middle, and a ceiling on what any single key can spend. What changes is which policy matters most and how the request record gets used afterwards.

8-PERSON PRODUCT STUDIO

One key per client, so the model bill splits itself

Each client engagement gets its own issued key with a daily ceiling and its own routing rule. The monthly call log exports straight into the cost line on that client's invoice, and a runaway agent on one project cannot spend another project's budget.

4-PERSON DATA CONSULTANCY

Two providers behind one endpoint, so a quota trip is not a stopped day

Two provider accounts sit in the fallback chain with a local model at the end. When the primary returns a rate-limit error mid-afternoon, the request lands on the second account instead of failing, and the switch shows up in the log rather than in a support ticket.

12-PERSON SAAS ENGINEERING TEAM

Separate keys for staging and production, with different ceilings

Staging keys route to the cheap tier with a low daily cap. Production keys route to the high-quality tier with alerting on the weekly ceiling. Both sets are issued from the same instance in the region their build system already runs in.

COMPARISON

Four ways to run OmniRoute

The gateway market prices three different ways: a flat platform subscription, a percentage skim on every request, or your own time. The table below puts the four realistic paths side by side at one, five and ten people, with the ongoing work each one leaves on your desk.

Path1 seat5 seats10 seatsOngoing work
Portkey (hosted AI gateway)USD 49/moUSD 49/moUSD 49/moNone, but the plan meters recorded logs and adds USD 9 per extra 100k requests. Prompts and keys live in the vendor account.
Self-host on a VPSUSD 24/moUSD 24/moUSD 24/moPatching, certificate renewal, backups, and the native module rebuild every time the Node runtime moves. Budget a few hours a month.
Home serverUSD 900 once, plus powerUSD 900 once, plus powerUSD 900 once, plus powerEverything above, plus hardware failure, a residential connection in front of a production endpoint, and no second site for backups.
DANIAN managed OmniRouteEUR 9/moEUR 9/moEUR 9/moNone. Updates, backups, certificates, monitoring, the runtime pin and the hardened defaults are ours. You set routing policy.

Percentage-fee routers price differently again: the common marketplace model takes roughly five percent on top of the provider bill, which is invisible at small volume and the largest line on the page once a team runs agents all day.

BY INDUSTRY

OmniRoute for specific industries

An AI gateway inherits whatever rules already govern the work passing through it. These four sectors put different demands on the same software: one cares about prompt handling, one about interface stability, one about record keeping, and one about knowing which model produced which answer.

Client code goes through the gateway, which makes prompt handling a delivery question rather than a preference. The OWASP Top 10 for LLM Applications names prompt injection and sensitive information disclosure as the first two risks in this category, and both are decided by settings on this app. We enable the input sanitiser in blocking mode and set response filtering on instances that carry client work. In practice a studio issues one key per engagement, sets a per-key ceiling, and pulls the monthly call log as the evidence line for that client's cost report. The default fallback ceiling of 1,000 requests per key per day is usually the first number a studio changes, upward for agent workloads and downward for keys handed to contractors.

For a product team the gateway is an interface contract, not a tool. The chat-completions API shape is the de-facto integration standard across the model vendors, and OmniRoute presenting it means a provider change is a routing rule rather than a code change and a release. We keep the endpoint hostname stable across upgrades and pin the runtime so a native module rebuild never changes the URL your service calls. A typical setup routes summarisation traffic to a cheap tier and customer-facing generation to a premium one, with the same base URL for both. Teams commonly run two issued keys per environment, one for the application and one for internal tooling, so a spend spike is attributable within minutes rather than at the end of the billing period.

Funder data management plans require that research outputs and the processing that produced them stay retrievable for a defined period, commonly ten years after project end. A gateway that logs model, prompt reference, token count and outcome turns that into a record you already hold rather than a reconstruction. We extend call-log retention well past the stock seven days on research instances and size the database volume for it. A lab typically issues one key per doctoral project, routes free-tier and local models first to keep grant spend flat, and exports the log at the end of each term as the processing record attached to the dataset.

Supervisory model-risk guidance such as SR 11-7 expects a firm to know which models are in use, who authorised them, and what they were used for. Teams that add language models to internal tooling inherit that expectation, and a gateway is the cheapest place to satisfy it because every request already passes through one point. We turn on identifying-string redaction before requests leave the instance and set retention to the window the firm's own record rule specifies. The working pattern is an allow-list of approved models in the routing policy, so an engineer calling an unapproved model gets a rejection rather than a result, and the monthly export becomes the model inventory line.

FAQ

Frequently asked questions

Three groups below. The first covers how this gateway behaves and what we change from the stock configuration. The second covers moving an existing instance across and getting started. The third covers billing, support and how the platform works for any app you run with us.

01

Technical and configuration

No. The stock configuration ships a literal placeholder as the initial admin password. We replace it with a generated credential during provisioning and hand it over through the dashboard, so the instance is never reachable with the published default.
Not on our instances. The application ships with the API key requirement switched off, which is reasonable on a laptop and wrong on a host with a public address. We turn it on, so every call to the gateway carries an issued key.
On your instance, encrypted before they touch disk. Nobody needs to send us a provider key to get set up.
The request cascades. You order your providers into a chain, and a quota, rate-limit or availability error moves that request to the next one instead of returning a failure to the client. The switch is recorded in the call log.
Anything that speaks the OpenAI chat-completions API and lets you set a base URL. That covers the common coding agents, editor extensions, notebooks and your own services. You change one setting per tool and keep everything else.
We rebuild it in staging first. The application reaches SQLite through a module compiled against one specific Node version, so a runtime move breaks the binary. We rebuild against the target runtime and verify the app starts before promoting anything.
We run these instances on x86_64. The project ships prebuilt database binaries compiled for x86_64 only, and on ARM they fail to load with an architecture mismatch that cannot be rebuilt against the vendored copy.
You choose. The stock retention window is seven days for both call logs and application logs. We set it to the window you ask for and size the storage volume to match, whether that is shorter for sensitive work or years for research.
Yes. Every issued key carries daily, weekly and monthly request ceilings, and the fallback default is 1,000 requests a day. We set your ceilings during setup, which is what turns a runaway agent loop into a capped incident.

02

Migration and onboarding

21 datacenter locations across six continents. You choose the region at provisioning. Application data sits in the region you choose; pick whichever is closest to your users or matches your data-residency preference.
Yes. Request a region migration from the dashboard and we run the move in the background. The system emails you when the migration completes; total transfer time depends on data volume but typical instances finish in a few hours. There is no extra charge for a region change.
Yes. Full data export is available at any time, in a portable format you can bring to any infrastructure.
Yes, and you add them yourself through the dashboard once the instance is live. We do not need to see them. Existing keys keep their provider-side history and billing, so nothing changes upstream.
Only the base URL. Each tool that currently points at a local gateway address gets pointed at your instance hostname instead. Issued keys carry over if you restore from your existing database.
Yes. Point a subdomain at the instance and we issue and renew the certificate for it. Custom domains are included at no extra cost, and using one keeps your tool configuration stable if you ever move the app.

03

Billing, support, and platform

€9 covers everything we do for that app: hardware in the region you choose, daily off-site backups with one-click restore, automatic security patches and version upgrades, 24/7 monitoring, SSL and firewall, and engineering support on email and the ticket section in the client portal. There are no setup fees or hidden line items. For more info see our Pricing page.
If you decide to continue, we charge €9/app/month from day 8. If you don't, the trial ends and you can export your data. No card is required for the trial, and we never auto-charge you without explicit consent.
No. The €9/month is flat regardless of how many users log into your app. Add 5 users or 50; the price doesn't change.
24/7 email and ticket support, both staffed by engineers who run the systems. We handle DNS configuration, SMTP setup, app integrations, performance tuning, troubleshooting, and migration help. Response time is typically under an hour. There is no tier system — every customer gets the same support.
Yes. Cancel from the dashboard. We don't charge a cancellation fee, we don't lock data, and we will export your data to you on request before deletion. data to you on request before deletion.
Every customer instance is backed up daily to a separate region from the primary. We test restores. You can request a restore at any backup point within the retention window — usually 7 days for daily backups.
Your application data sits in the region you choose at provisioning — 21 datacenter locations across six continents. Account-level data (billing, account email, support ticket history) is processed centrally. Application data region is picked by you, per app.
99.9% uptime SLA on every app, every tenant. Service credits are documented at danian.co/service-level-agreement. The status page is located at status.danian.co.
When your tenant approaches the resource ceiling — the base tier holds 1 vCPU/RAM, 30 GB storage — we notify you. Resource upgrades happen with your explicit consent; we will not upgrade your tenant or charge you without it.
We wait. We don't suspend the app or delete your data on the first failed charge. We email you, you fix the card on file, and we continue.
Invoices can be downloaded from the billing dashboard in PDF the day each charge succeeds. EU VAT is added where applicable and the VAT-reverse-charge regime applies for VAT-registered businesses with a valid number.
150+ open-source apps across automation, team chat, file sync, analytics, AI, password management, email marketing, dev tools, project management, smart home, CMS, and federated social. See the full catalog →
Yes. Every instance comes with a web-based terminal and a file manager in your DANIAN management dashboard. Useful for managing your data and customizations.
Resources scale with your usage. If your app needs more vCPU, RAM, or storage, we add it — and we ask first before any change to your plan. €9 is the floor; resource-heavy workloads may price higher, but you'll always know in advance.
Yes. We have both a Partner program and an Affiliate program available. Anybody can sign up.
No contract. No minimum commitment. Cancel anytime from the dashboard with one click. The 7-day free trial requires no credit card. After the trial converts to paid, you can still cancel at any month without notice or penalty.

DEPLOY IN YOUR REGION

21 datacenter locations on six continents

Pick the region closest to your users.

United States, Germany, Finland, Singapore, Australia, Brazil, Canada, Netherlands, UK, Spain, Italy, France, Sweden, Malaysia, India, Japan, Mexico, Poland, South Korea, Chile, South Africa and more coming soon

Global Reach Map

Try managed OmniRoute for 7 days

No card. Cancel from the dashboard.