Pay in dollars for what you actually use. Top up an Oriora wallet, and every call is itemized in your Activity feed — which model ran and what we charged. Oriora doesn't resell AI: when a call uses AI, the fee is priced off our published catalogue rate for that model, plus a transparent layered fee.
For each call that uses AI, the fee is calculated from our published catalogue rate for the model that ran — the price you see — plus the layers below. The fee depends on how the call is made and how it's paid:
| Surface | Payment mode | Effective fee |
|---|---|---|
| Managed API BYOK — server-side | BYOK | 4% of equivalent AI cost |
| Managed API BYOK — client-side | BYOK | $0.001 per recommendation |
| Catalog app | Wallet | AI cost + 6% |
| Catalog app | BYOK | 6% of equivalent AI cost |
The AI price is the published catalogue rate for whichever model runs — that's the price you see. On top of it, each layer a call touches adds 2%, charged on that catalogue AI cost. You only pay for the layers you use:
So Managed API BYOK server-side = platform & orchestration 2% + model routing 2% = 4%(no app layer — it's the raw API, not a catalog App). A catalog App adds the third layer, for 6%. When you bring your own key the vendor bills you for the AI directly, so you pay only the layer fees; on Managed AI the catalogue AI price is added on top.
Managed API BYOK client-side is different. We only return a model recommendation and never see the call, so none of the per-call % layers apply — it's a flat $0.001 per recommendation, the same Oriora API key, just routed on your side.
Say a call runs a model whose catalogue rate is $2.00 / 1M tokens, and it uses 250K tokens. The AI cost for that call is 250K × $2.00/1M = $0.50. That $0.50 — your tokens, priced at our catalogue rate for the model that ran — is the base every fee applies to. On BYOK you've already paid your vendor for those tokens directly; we still compute our percentage from this same $0.50, which the table above calls “equivalent AI cost.”
| Lane | What you pay on this call |
|---|---|
| Managed AI catalog app · wallet | $0.50 + 6% = $0.53 we sourced the AI: catalogue AI cost + platform 2% + routing 2% + app 2% |
| Managed BYOK catalog app · your key | 6% of $0.50 = $0.03 your vendor bills you for the tokens; Oriora charges platform 2% + routing 2% + app 2% |
| Managed API BYOK server-side (c1) | 4% of $0.50 = $0.02 your vendor bills you for the tokens; Oriora charges platform 2% + routing 2% (no app layer — raw API) |
| Managed API BYOK client-side (c2) | $0.001 flat no AI runs through us — you get a model recommendation and execute the call yourself |
Per-model catalogue rates are on the models page. Every call is itemized in your Activity feed — which model ran, the tokens used, and what we charged.
You don't hand-pick a model for every call — Oriora does that for you, choosing the best fit for each task within the vendors and priorities you've set. A few things it handles automatically:
Per-task quality scoring
Models are pre-scored against benchmarks per task category. A coding request never gets routed to a model that underperforms on code.
Transparent pricing, under the hood
No opaque token credits — you see which model actually ran and our catalogue rate for it, the basis for every layered fee. Oriora doesn't sell or resell AI; you pay for the work and the orchestration.
Prompt cache pass-through
Where the underlying vendor supports prompt caching, requests are structured so the cache fires on repeated content. When it hits, the AI cost line drops automatically.
Circuit breakers
If a provider rate-limits or goes down, the next best model picks up automatically. No error surface to your app.
Weighted fallback
Configurable fallback chains per task type. Define how aggressively to escalate to premium models when the top tier is unavailable.
Vendors we route to
Vendor names referenced on this page identify integrations Oriora supports. Oriora has no formal partnership, sponsorship, or endorsement arrangement with these vendors unless explicitly disclosed.
Supported task types
Pay-as-you-go. Free-form amount, $10 minimum.
Add any amount above $10 to the wallet. Funds expire 365 days after they're added.
Same wallet model on a recurring schedule. Same per-call fees, same expiry. The benefit is a lower payment-processing fee as a percentage — Stripe's flat $0.30 per transaction is amortised over fewer, larger top-ups.
The wallet page shows the full checkout breakdown — ecosystem dollars you receive, processing fee, applicable VAT, and total — before payment.
Unused balance is refundable within 24 hours of purchase; service fees are non-refundable. See the refund policy. VAT is collected by the payment processor on top-up at the customer's local rate.
Approximate — exact cost depends on inputs, how much AI the call uses, and whether vendor prompt caches were warm. The same call can cost different amounts run to run. Full per-call breakdown shown in the Activity feed after each call.
Add your own vendor API keys to your Oriora account, and AI calls go through your keys. The vendor bills you directly for AI cost; Oriora charges only the orchestration fee. Available across both BYOK lanes (Managed BYOK in catalog Apps and Managed API BYOK when you integrate Oriora into your own product) — no separate tier required.