AI Governance Cost Control

AI Governance Cost Control governs AI spend in two complementary ways:

• Enforcement stops a user's requests routed via AI Gateway once their spend reaches their budget.
• Reporting shows what each user and group has approximately spent in the current budget period.

AI Governance Cost Control requires:

• Coder v2.36 or later.
• AI Gateway enabled and configured with at least one provider.

These terms appear throughout this page and in the Coder dashboard:

Deployment settings

Two deployment-wide settings govern budget resolution and the reset window. Each accepts a single value today.

• Budget policy determines which budget wins when a user belongs to more than one budgeted group. highest selects the largest.
• Budget period sets the reset window. month is the UTC calendar month, so spend resets at 00:00 UTC on the first day of each month.

These settings are deployment-wide.

Budget

Every user's spend is recorded against a group. A user only has a budget when one is set on a group they belong to, or when they are given a user override.

Group budget

Setting a group budget requires the Owner, User Admin, Organization Admin, or Organization User Admin role.

A group budget applies to each member individually rather than to the group as a whole. For example, if a group has ten members and a budget of $200 USD, each member can spend $200 USD and the group has a total spend limit of $2,000 USD.

1. Go to Groups and select a group.
2. Select Settings.
3. Under AI budget, set Monthly limit per member.
4. Select Save.

Budget values behave as follows:

• An empty field means no limit. The field displays unlimited.
• $0 USD blocks every request routed via AI Gateway from members whose effective group is this group.
• The maximum is $1,000,000 USD per member per budget period.

Note: Members who belong to other groups with budgets are still governed by whichever group the budget policy selects. See Effective group resolution.

User override

Adding or removing an override requires the Owner or User Admin role. Other administrator roles can view overrides but cannot change them.

Override a group budget when one user needs a different limit from the rest of their group.

1. Go to Groups, select a group, then open the Members tab.
2. Find the member to apply the override to, open their action menu, and select Manage AI budget.
3. Enable Override group budget.
4. Set Custom monthly budget, then choose the group in Budget assigned to.
5. Select Update.

Overrides behave as follows:

• A user can have only one override at a time.
• An override supersedes every group budget the user belongs to.
• Spend is always attributed to a group, so an override must name the assigned group. This group can be different from the group selected in the Members tab. The user must belong to the assigned group.
• The $0 USD to $1,000,000 USD range applies to overrides as well.
• Disabling Override group budget removes the override and returns the user to the budget of their effective group.

Effective group resolution

A user can belong to several groups that have budgets, and can also hold an override. AI Gateway resolves a single effective group for each request, in this order:

1. The user's override takes precedence over every group budget.
2. Otherwise, the budget policy selects one of the groups the user belongs to. The default policy, highest, selects the group with the largest budget.
3. If none of those groups has a budget, the user has effectively unlimited spend and their spend is recorded against the Everyone group.

Recorded spend is immutable. Changing which budget applies to a user affects future requests only: spend that Coder has already recorded stays with the group it was attributed to, so a user's history can span several groups. The effective group is resolved at request time, so changing a group budget can change which group applies to a user on future requests.

How enforcement works

AI Gateway checks each request before forwarding it upstream. The check compares the user's spend in the current budget period with the budget that applies to the request:

• Spend below the budget: the request proceeds.
• Spend at or above the budget: AI Gateway returns 403 Forbidden with a message that describes the issue.

Users without a budget have unlimited spend, so their requests proceed without enforcement. A blocked user's access resumes when the budget period resets, when an administrator raises the budget, or when an override is added.

Notifications

The first time a user's spend crosses a threshold within a budget period, Coder notifies the user and deployment-wide Owners and User Admins, excluding the affected user:

• A single expensive request can cross both thresholds at once.
• Budgets of $0 USD and unpriced usage cross no thresholds.
• Notifications are informational. Enforcement does not depend on them.

For delivery methods, see Notifications.

How spend is estimated

Coder multiplies the token usage of each request by the published price of the model that served it. Prices come from a curated models.dev snapshot that ships with every Coder release, so no configuration is required.

Spend accumulates only from the moment v2.36 is deployed. Upgrading mid-month therefore produces a partial first period.

To see which models are priced in the release version you run, consult the price book for your Coder version:

Replace <VERSION> with your Coder minor version, for example 2.36.

Monitor coder_ai_gateway_cost_control_unpriced_token_usage_records_total, labeled by provider, provider_type, and model, to detect unpriced usage. The (provider_type, model) tuple identifies the missing price. Any non-zero value means spend is under-counted. Because the price book ships with the release, a newly launched model can remain unpriced until you upgrade Coder.

Monitor spend

Spend reporting is available in the Coder dashboard and as a CSV export. Prometheus metrics report enforcement and pricing gaps.

Dashboard

Visibility follows the viewer's role:

• The Groups page compares each group's spend with the combined limits of the members it covers.
• The Members tab of a group reports each member's spend, their budget, and its source, labeled Custom limit for an override or Group limit for a group budget. If the effective group is another group in the same organization, the row shows Budget managed by another group. If the effective group is in a different organization, the row shows a dash and explains that the group is not visible there.
• The avatar menu reports the signed-in user's own spend for the budget period as $<spend> / $<budget> USD, or $<spend> / Unlimited USD when no budget applies.

Administrators can also use the Get user AI spend API endpoint to see a user's current effective group.

CSV Export

Users who can read group-member data for the organization can export estimated spend for reporting and internal cost allocation. The export is available through the API only.

• Without parameters, the export covers the current budget period.
• To select a range, pass period_start and period_end together as RFC 3339 timestamps. A range can span at most 31 days.
• Each row breaks spend down by user, group, model, and provider, with the underlying token counts.

Prometheus Metrics

Prometheus metrics report blocked requests, users over budget, unpriced usage, and enforcement latency. For the full metric list, including types and labels, see Prometheus metrics.

Migrate from Coder Agents Cost Control

In release 2.36, native Coder Agents usage limits are no longer configurable or enforced. Existing native values remain stored, have no effect, and are not migrated to AI Gateway budgets.

Configure new AI Gateway budgets from the group settings page or use the API to get, upsert, or delete a group budget.

Expect the following differences:

• AI Gateway has no deployment-wide default budget. Each group that needs a limit requires its own budget.
• The UTC calendar month is the only budget period. Daily and weekly periods are not currently supported.
• Users in several budgeted groups receive the highest budget by default. Native Coder Agents usage limits applied the lowest group limit.
• Budgets cover priced AI Gateway traffic. Chat, IDE extensions, and CLI agents draw on the same budget when their provider and model are priced. See How spend is estimated.
• Recorded spend and native limit values do not carry over to AI Gateway budgets.

Next steps