1
Create an account and workspace
Sign up at platform.omnia-voice.com.
Your first workspace is created during onboarding; everything (keys, billing,
usage) is scoped to it.
2
Create an API key
In the dashboard, go to API keys → Create key. Copy it immediately; it’s
shown once and starts with
sk_sovereign_. See
Authentication for details.3
Choose an integration path
Choose by what your codebase already does; full detail in
Integration paths:Gateway (your app calls an OpenAI-compatible API and can use
Omnia’s catalog): point your existing client at Omnia’s base URL.Gateway inference is prepaid: top up your wallet under Usage in the
dashboard (or enable auto-reload) before routing
traffic. Every request is metered per token and deducted from the balance.Your provider key (BYOK) (you run GPT, Claude, or Gemini and intend to
keep it): same base-URL swap, but you paste your provider’s key into
Settings → Workspace → Provider keys and prefix the model
(See OTLP trace ingest.Tracing SDK (no OTel yet, and your inference stays where it
is): one package, one line, standard OpenTelemetry underneath.See the SDKs for setup per language.Faster still: paste one canonical prompt into Claude Code, Cursor, or any
coding agent with repo access, and it picks the integration path, wires
it, and verifies itself; see
Set up with your coding agent.
anthropic/claude-sonnet-4-5). Your provider keeps billing you; Omnia
bills nothing for those tokens. See
Bring your own key.OpenTelemetry (your app already emits OTel traces): no packages,
no code, just three environment variables.4
Turn on request logging
Grading needs content. In Settings → Workspace → Request logging
(owner/admin), turn on the toggle and pick a retention window. It’s
off by default because Omnia’s standing
posture is content-free; capturing prompts and responses is your explicit
choice.
5
Verify your setup
Your traffic is now captured and gradeable. Open Review in the dashboard
and grade a few real exchanges:
P pass, F fail with a critique. Those
grades are the ground truth every judge is measured against.What to explore next
How Omnia works
Why capture is step one: measurement, improvement, and ownership all
build on it.
Grade your traffic
~100 grades define your quality bar and calibrate your first judge.
Run a comparison
Test whether a cheaper model holds up on your own traffic.
Browse models
See every available model and its pricing.