Settings & Administration

Check AI usage and availability

Understand which service or account a limit applies to.

OpenMeld can use hosted models and agents installed on connected computers. These can have different usage limits and accounts.

Check the relevant usage view

Open your workspace's Settings → AI usage for the usage information available to your role.

For a Local Agent, inspect its computer and tool details. The underlying provider may also show usage in its own app or account page.

Check the period, account, and scope shown beside a number. A remaining amount for one provider does not describe every Agent.

Choose scope and period

  • Organization usage shows workspace usage and the available billing-source summary.
  • My agents narrows the view to your agents. It is not a separate provider subscription.
  • Open Details for model totals, refresh, and the Last 7 days or Last 30 days period selector.

Compare the same scope, period, and unit. A loading error or missing cost record is not zero usage.

Included credits and your own key

The workspace summary distinguishes Included AI credits from Your OpenRouter key. If your role permits billing changes, use the available management control to update the OpenRouter key. Enter credentials only in that setting, not in a conversation or document.

With your own key (BYOK), the remote usage view shows recorded model costs in USD; it is not your OpenRouter account balance. Where usage is shown as equivalent credits, BYOK usage does not reduce the included credit balance. Check the source label before interpreting the amount.

Local Agent token usage is a separate view of reported usage from local tools. It is not a complete invoice or a guarantee of remaining provider quota.

Hosted versus local usage

A hosted Agent depends on its configured model and OpenMeld availability.

A Local Agent can depend on a separate subscription, API account, or provider quota. Installing OpenMeld does not transfer that subscription or remove its limits.

Usage that is unavailable or still checking is unknown. Do not interpret it as zero usage or unlimited capacity.

When a limit stops work

  1. Read the actual failure message.
  2. Identify the affected Agent, model, or account.
  3. Check the matching usage or provider setting.
  4. Wait for the stated reset, repair the account, or select another permitted configuration.
  5. Retry only after checking whether the original task already produced a result.

Changing the model can change behavior and cost. Confirm the intended configuration before restarting important work.

Pricing and purchases

Use the price and billing information currently shown by the product or provider. This guide does not promise a free tier, unlimited use, or a fixed provider price.

For help identifying a blocked path, see Agent not replying.

For prompt caching, context costs, and the limits of execution safeguards, see Caching and token costs.

On this page