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

# Usage information and limits

> Understand pricing, plan allowances, pay-as-you-go billing, spending caps, and usage limits for Serverless Inference


This page describes the pricing, billing, and usage limits that apply to Serverless Inference. Use this information to plan your usage and avoid unexpected charges or interruptions. Review it before you send production traffic, especially if you manage billing or operate at higher concurrency.

> [!NOTE]
>
> If you have questions about pricing, limits, or your account that this page doesn't answer, contact [Support](mailto:forge-support@coreweave.com) to discuss your requirements.

## View billing and usage information

Serverless Inference usage is billed to your Forge organization. Organization admins and [billing admins](https://docs.coreweave.com/products/wandb/platform/app/settings-page/billing-settings.md#billing-admin) can review the organization's plan, Inference allowance, and usage history from the Billing page in Forge. To open it:

1. In the upper-right corner, click the account selector.
2. In the **Account** section, click **Billing**.

The organization page opens with the **Billing** tab selected. The **Plan summary** section shows your plan, and the **Current usage** section shows your Inference allowance and whether pay-as-you-go is active.

To see Inference usage over time and configure usage and spending alerts:

1. In the tab bar, click **Usage & Alerts**.
2. In the sidebar, click **Inference**.

The Billing page is available at `https://forge.coreweave.com/account-settings/[ORG-NAME]/billing`. For details about each section of the page, see [Manage billing settings](https://docs.coreweave.com/products/wandb/platform/app/settings-page/billing-settings.md).

## Pricing

Serverless Inference is priced per token, and the rate depends on the model. For model pricing, see [Serverless Inference pricing](https://coreweave.com/forge-pricing/inference-agents).

## Inference allowances and billing by plan

Each Forge plan includes an Inference *allowance*, also called Inference credits on the [pricing page](https://coreweave.com/forge-pricing). Your Billing page shows the allowance available to your organization. Your allowance is used first. Each month, you're billed for the previous month's usage beyond the allowance, based on [model pricing](https://coreweave.com/forge-pricing/inference-agents).

| Plan | When you use up the allowance | How paid usage is billed |
| - | - | - |
| Free | Inference stops until you [activate pay-as-you-go](#activate-pay-as-you-go) for Inference or upgrade your plan. | Monthly, after you activate pay-as-you-go. |
| Academic | Inference stops until you [activate pay-as-you-go](#activate-pay-as-you-go) for Inference or upgrade your plan. | Monthly, after you activate pay-as-you-go. |
| Pro | Inference continues. | Monthly, as overage on your Pro invoice (pay-as-you-go already activated). |
| Enterprise | Depends on your contract. Contact your account executive. | Per your contract. |

To upgrade your plan, open the Billing page and, in the **Plan summary** section, click **Explore plans** or **Talk to sales**.

> [!NOTE]
>
> The **Pay-as-you-go** panel on the Billing page is shown only to organization admins and billing admins. Enterprise organizations and some custom plans don't have a **Pay-as-you-go** panel, because their Inference usage is billed under their contract. If you expect to see pay-as-you-go controls and don't, contact [Support](mailto:forge-support@coreweave.com).

### Activate pay-as-you-go

On Free and Academic plans, activate pay-as-you-go for Inference to keep using Serverless Inference after you use up the included allowance. You activate pay-as-you-go per product, so activating it for Inference doesn't affect other products such as [Sandboxes](https://docs.coreweave.com/products/sandboxes.md).

To activate pay-as-you-go for Inference:

1. Open the Billing page, as described in [View billing and usage information](#view-billing-and-usage-information).
2. In the **Current usage** section, find the **Pay-as-you-go** panel. It lists each product you can activate, with its included allowance.
3. In the **Inference** row, click **Activate**. The **Activate pay-as-you-go for Inference** dialog opens.
4. Complete activation as prompted.

Activation doesn't charge your card. After activation, the **Pay-as-you-go** panel shows Inference as active, and Inference requests resume. You can cancel pay-as-you-go at any time from the **Pay-as-you-go** panel.

## Default spending caps

Each plan has a default spending cap on Serverless Inference usage beyond the included allowance. The cap helps you manage costs and prevent unexpected charges. When your organization reaches its cap, Inference requests return a `402` error. See [API error code 402](https://docs.coreweave.com/support/inference/articles/api-error-code-402-you-exceeded-your-cur).

| Plan | Default cap | How to change it |
| - | - | - |
| Free | \$100/month | Upgrade to Pro or Enterprise |
| Academic | \$100/month | Contact [Support](mailto:forge-support@coreweave.com) for manual review |
| Pro | \$6,000/month | Contact your account executive or [Support](mailto:forge-support@coreweave.com) for manual review |
| Enterprise | \$700,000/year | Contact your account executive or [Support](mailto:forge-support@coreweave.com) for manual review |

## Concurrency limits

Concurrency limits protect service quality by capping how many requests a project or user can have in flight at once. If you exceed the concurrency limit, the API returns a `429 Concurrency limit reached for requests` response. To fix this error, reduce the number of concurrent requests.

CoreWeave applies concurrency limits per Weights & Biases project and per user. For example, if you have three projects in a team, each project has its own concurrency limit quota.

If your use case requires increased limits, contact [Support](mailto:forge-support@coreweave.com) to discuss your requirements.

## Geographic restrictions

Serverless Inference is available only from supported geographic locations, due to compliance and regulatory requirements, including U.S. trade controls. Serverless Inference determines your location from your IP address at the time of each request, and returns a `403` error for requests from other locations.

CoreWeave doesn't publish the full list of locations that Serverless Inference blocks, because the list changes as regulatory requirements change. To confirm whether your location is supported, email [Support](mailto:forge-support@coreweave.com). For the trade sanctions terms that apply, see the [CoreWeave Terms of Service](https://docs.coreweave.com/policies/terms-of-service.md). For help with the error, see [API error code 403 - Country, region, or territory not supported](https://docs.coreweave.com/support/inference/articles/api-error-code-403-country-region-or-ter).

## Next steps

* See [available models](https://docs.coreweave.com/products/inference/serverless/models.md) and their specific pricing.
* Configure usage and spending alerts in [Manage billing settings](https://docs.coreweave.com/products/wandb/platform/app/settings-page/billing-settings.md#usage-alerts).
