Skip to main content
The Billing page, under Settings → Organization, combines credits and billing. Model requests draw on credits; everything else is invoiced monthly.
Billing page on the Pay as you go plan showing available credits, the line Model requests use credits with charges beyond included volume, Add Credits and Auto Top-up controls, Seats, Teams, Knowledge base, and Throughput add-on rows, usage tiles for Agent runs, Spans, and Storage and retention, and a Will be invoiced breakdown of agent runs, spans, storage, seats, and the Teams add-on

The Billing page on Pay as you go: credit balance, seats and add-ons, usage against the plan, and what will be invoiced beyond the included volume.

​
What credits and invoices cover

​
Usage

The Usage tiles read Agent runs, Spans, and Storage and retention against the plan allowance, and the header carries the renewal date. The breakdown below repeats each meter with what is left.
For per-request detail behind those numbers, use Analytics.

​
Available credits

The plan card carries the balance and an Add credits button. On Pay as you go it is captioned Available credits and adds the auto top-up control. The balance is shared across every project in the organization and is consumed as requests go through the AI Gateway, at each model’s token pricing.
Credits cover model requests only. Spans, storage, and agent runs beyond the plan’s included volume are metered and invoiced monthly to the card, not drawn from credits. See AI Gateway pricing for model and tracing rates.
When the balance reaches zero, AI Gateway requests are blocked until credits are added. A broader block on the workspace answers with this error.

​
Add Credits

1

Select Add Credits

Open the plan card and select Add Credits.
2

Enter an amount

The minimum purchase is $10. The sheet shows the amount, a service fee, any tax, and the total before payment.
3

Add a Tax ID (optional)

Expand Edit Tax ID, choose the country and tax ID type, and enter the number for invoices.
4

Select a payment method

Choose a saved card or add a new one.
5

Enter name and billing address

Both are required for the payment processor.
6

Confirm the purchase

Credits are added to the balance immediately.
Purchase Credits sheet showing the Edit Tax ID toggle, an amount of $10.00, a $0.80 service fee, $0.00 tax, a $10.80 total, a card ending in 4242, and Cancel and Purchase buttons

The Purchase Credits sheet: amount, service fee, tax, total, and the card to charge.

​
Payment method

The Payment Method panel lists the saved cards with their expiry and the Default badge, and + New card adds one.

​
Auto top-up

Auto top-up buys credits when the balance falls below a threshold.
  1. Enable Auto top-up.
  2. Set the Top-up threshold, for example $50.
  3. Set the Amount to add, for example $200.
  4. Select Save changes.
A common setup triggers at $50 and adds $200, which keeps peak usage from hitting an empty balance.

​
Free

Before a payment method is added, the plan card reads Free with No card on file, and the page offers Payment method and Explore plans. A Free workspace is Pay as you go without billing details: model requests are rate-limited instead of billed.
  • 50 requests a day, and 20 a minute. See Rate limits.
  • 14-day retention for traces and logs. See Data retention.
  • 3 Deployments, 3 Agents, 2 Knowledge Bases or Memory Stores, and 1 Webhook. See Quota limits.
  • Model requests run on a provider key from a workspace integration. Credits, which work with any model, start with a payment method.
Adding a payment method switches the workspace to Pay as you go: the daily cap is lifted, throughput rises to 100 requests a minute, and retention extends to 30 days.

​
Seats and add-ons

The plan card shows the seat count beside the balance. Seats cap how many members the workspace can invite on and Pay as you go. Seats are added and removed in the Manage your seats dialog, confirmed with Add N seats or Remove N seats. Changes apply immediately and land on the next invoice.
Invite a member only when a free seat exists. See Members and Teams.
The Add-ons panel beside the plan card lists the add-ons available with the plan. Teams is billed monthly.

​
Invoice history

Every charge produces a row in Invoice history: date, time in the viewer’s local time zone, description, amount, and the invoice number with a download for the PDF.
Invoice history table with Date, Time, Description, Amount, and Invoice columns, listing Subscription update, AI Router Purchase, and AI Router Auto Top-up rows with their amounts, invoice numbers, and download icons

Invoice history: one row per charge, with the invoice number and PDF download in the Invoice column.

The footer of the sidebar carries a usage widget labelled with the workspace plan. Select the widget to expand it and read each meter against its plan allowance: Explore plans in the top bar opens the pricing page and is hidden on Enterprise subscriptions.

​
Understanding Trace Storage Usage

Storage usage measures telemetry ingested during a billing cycle. It includes traces from Orq.ai requests and OpenTelemetry exporters. Each trace contains one or more spans. The trace total is the sum of each span:
A model span is billed from its token total. Cached and reasoning tokens are already inside total_tokens and are not added again.
Agent, tool, and retrieval spans do not repeat that charge. A span with no model token total, including tokenless OpenTelemetry, is billed as its serialized JSON byte length with no multiplier. An orq.storage_size attribute on the span replaces the formula. Workspace storage usage also includes ingested OpenTelemetry logs, metered separately using their recorded raw byte size.

​
Conversation history and repeated content

When a Responses API request uses previous_response_id, Orq.ai reconstructs the conversation context before calling the model. That context is included in the model span’s input tokens, so a later step bills the tokens the model processed. The same input can appear in more than one attribute on the model span and again on an Agent span. The meter uses the model span’s token total for that call. It does not bill each stored copy as extra tokens.
For OpenTelemetry spans that report no tokens, remove unnecessary payload fields before exporting. Transport compression alone does not reduce those measured JSON bytes. Model spans follow the token rate above.

​
Understanding Events

A single Deployment invoke contains multiple events, each event will incur costs reflected in your Billing and Plan Usage. To understand better the events held within your Deployments, lookup Analytics and explore the events embedded into each generation.
Logs view showing a selected DeploymentInvoke trace with its event breakdown including Retrieval, Embedding, Evaluator, Vision, Chat, and Callback spans with token counts.

Each trace and event detail will hold usage and billing information.

​
Rate Limits

Our APIs are protected through Rate Limits on a per-account basis to ensure fair and efficient use of the API. This helps maintain optimal performance and prevent server overload, while also protecting against potential abuse and limiting costs effectively. When reaching rate limit, API calls are denied with a 429 Too Many Requests response.
See Rate limits & quotas for how platform limits, budget limits, and provider limits interact.
To learn more about the Orq.ai Pricing options or to upgrade your plan, see Our Pricing Page.

​
BYOK and private models

A request routed through a provider integration key or to a private model draws no credits: the provider charges the account that owns the key for the model usage. A platform fee applies instead, as listed on Pricing: the first 1M BYOK requests each month are free, then 4%. Traces still record the call: the span carries the cost calculated at the model’s list price with Billable: No, and that cost stays out of the credit balance. Rate limits apply to every request that reaches the gateway, BYOK included: a BYOK request counts toward the plan’s per-minute limit like any other request.