> ## Documentation Index
> Fetch the complete documentation index at: https://docs.orq.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Billing and credits

> Read the plan, credits, usage, add-ons, and invoices for an Orq.ai workspace from the Billing page.

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](https://mintcdn.com/orqai/JL0Rp5V4_0CT9sUj/images/billing-417.png?fit=max\&auto=format\&n=JL0Rp5V4_0CT9sUj\&q=85\&s=862b860b11c0a7ac4a3622b36e59ee37)

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

| Charge | Paid from |
| - | - |
| Model requests | Credits, with charges beyond the included volume |
| Agent runs, Spans, Storage and retention | The monthly invoice, charged to the card beyond the included volume |
| Seats | The monthly invoice |
| Teams add-on | The monthly invoice |

## 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.

> [!TIP]
>
> For per-request detail behind those numbers, use [Analytics](https://docs.orq.ai/ai-studio/observability/quickstart.md).

## 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.

> [!NOTE]
>
> 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](https://orq.ai/pricing) for model and tracing rates.

> [!WARNING]
>
> When the balance reaches zero, **AI Gateway** requests are blocked until credits are added. A broader block on the workspace answers with [this error](https://docs.orq.ai/reference/errors.md#workspace_blocked).

### Add Credits

**1. Select Add Credits**

Open the plan card and select <kbd>Add Credits</kbd>.

**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](https://mintcdn.com/orqai/JLQ-v7RG_lcCif-N/images/billing-purchase-credits-417.png?fit=max\&auto=format\&n=JLQ-v7RG_lcCif-N\&q=85\&s=10d6ffdf9a5861f12ed41baba5434615)

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**.

> [!TIP]
>
> 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](#rate-limits).
* 14-day retention for traces and logs. See [Data retention](https://docs.orq.ai/ai-studio/organization/data-retention.md).
* 3 Deployments, 3 Agents, 2 Knowledge Bases or Memory Stores, and 1 Webhook. See [Quota limits](https://docs.orq.ai/reference/errors.md#quota_exceeded).
* 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 Free (Pay as you go without a payment method on file) 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.

> [!NOTE]
>
> Invite a member only when a free seat exists. See [Members and Teams](https://docs.orq.ai/ai-studio/organization/members-teams.md).

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](https://mintcdn.com/orqai/JL0Rp5V4_0CT9sUj/images/billing-invoices-417.png?fit=max\&auto=format\&n=JL0Rp5V4_0CT9sUj\&q=85\&s=c319318709540c8b0e2199eb0f1637ce)

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

## Sidebar plan usage

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:

| Meter | Measures |
| - | - |
| **Logs** | Trace logs counted against the plan, shown as a count and a limit. |
| **Storage** | Telemetry storage used against the plan, shown in GB, calculated as described in [Volume Ingestion](#volume-ingestion). |

**Explore plans** in the top bar opens the pricing page and is hidden on **Enterprise** subscriptions.

## Volume Ingestion

Volume ingestion is the telemetry data **Orq.ai** receives during a billing cycle, measured in GB. It covers [**traces**](https://docs.orq.ai/ai-studio/observability/traces.md) from **Orq.ai** requests and OpenTelemetry exporters, and ingested OpenTelemetry logs. It is metered separately from the **Spans** count.

Each step of a trace is sized on its own, and the trace's volume is the total of its steps:

| Data | Ingested volume |
| - | - |
| Model call with a token count | `total_tokens * 8` bytes |
| Any other step, including OpenTelemetry data with no token count | Serialized JSON size in bytes |
| OpenTelemetry logs | Recorded raw size in bytes |

Cached and reasoning tokens are already inside `total_tokens` and are not added again. An `orq.storage_size` attribute replaces the calculated size.

**Example Calculations**

A trace with two model calls of 8,000 and 2,000 tokens ingests 80 KB: 64 KB plus 16 KB. The **Agent** step around them adds only its own JSON size, not those tokens again.

An OpenTelemetry trace with no token counts, made of a 3 KB tool step and a 1 KB retrieval step, ingests 4 KB. Exporting one 2 KB log alongside it brings the total to 6 KB.

### 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 part of the model call's input tokens, so a later step counts the tokens the model processed.

The same input can be stored more than once in a trace, for example on the model call and again on the **Agent** step. Volume uses the model call's token total once. Each stored copy is not counted as extra tokens.

> [!TIP]
>
> For OpenTelemetry data with no token count, remove unnecessary payload fields before exporting. Transport compression does not reduce the measured JSON size.

## Understanding Events

A single [Deployment](https://docs.orq.ai/ai-studio/ai-engineering/deployments.md) 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](https://docs.orq.ai/ai-studio/observability/quickstart.md) 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.](https://mintcdn.com/orqai/aSZBQyfYrbyA2UeJ/images/docs/c890b94a621b3f17b772728b28f46b25415164e7915d7e8e3dde41050387cc66-image.png?fit=max\&auto=format\&n=aSZBQyfYrbyA2UeJ\&q=85\&s=53d6b1d38093d0d8d21b69f429a0e1fb)

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.

| Subscription | Rate Limit |
| - | - |
| Free (Pay as you go without a payment method on file) | 20 requests per minute, and 50 per day |
| Pay as you go | 100 requests per minute |
| Enterprise | 1500 requests per minute, higher by arrangement |

> [!NOTE]
>
> See [Rate limits & quotas](https://docs.orq.ai/ai-gateway/features/rate-limits.md) for how platform limits, budget limits, and provider limits interact.

> [!NOTE]
>
> To learn more about the Orq.ai Pricing options or to upgrade your plan, see [Our Pricing Page](https://orq.ai/pricing).

## BYOK and private models

A request routed through a [provider integration](https://docs.orq.ai/ai-gateway/providers-overview.md) key or to a [private model](https://docs.orq.ai/ai-gateway/private-models.md) 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](https://orq.ai/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](https://docs.orq.ai/ai-gateway/features/rate-limits.md) 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.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.