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

# Solo.io agentgateway

> What CostGraph scrapes from agentgateway and how its token metrics are priced

agentgateway reports GenAI token usage from its data plane. See the upstream
[LLM observability reference](https://agentgateway.dev/docs/kubernetes/main/llm/observability/).

## What CostGraph scrapes

|               |                                       |
| ------------- | ------------------------------------- |
| Namespace     | none, you supply it                   |
| Pod selector  | none, you supply it                   |
| Port and path | `15020` `/metrics`                    |
| Metrics       | names starting `agentgateway_gen_ai_` |

<Warning>
  Token metrics come from the per-Gateway data plane, not the control plane, and
  those pods live in whichever namespace you created the Gateway in. An
  agentgateway connection must name the namespace and the pod label selector, or
  nothing can ever be scraped.
</Warning>

Read the labels off the running data plane pods and narrow the selector until it
matches them and nothing else:

```bash theme={null}
kubectl -n my-namespace get pods --show-labels
```

## How the metric maps

`agentgateway_gen_ai_client_token_usage` becomes
[`costgraph_gen_ai_usage_total`](/costgraph/integrations/ai-gateways#send-from-anything-else):

| agentgateway label      | CostGraph label         |
| ----------------------- | ----------------------- |
| `gen_ai_response_model` | `costgraph_model`       |
| `gen_ai_token_type`     | `costgraph_usage_kind`  |
| `gen_ai_system`         | `costgraph_host`        |
| `customer`              | `costgraph_sub_account` |

The unit is always `tokens`.

## Attribute usage to your customers

Add a metric attribute computed from the request. On Kubernetes this goes in an
AgentgatewayPolicy. The value is a CEL expression, so the identifier can come
from a header, a JWT claim, or anything else in the request.

```yaml theme={null}
apiVersion: agentgateway.dev/v1alpha1
kind: AgentgatewayPolicy
metadata:
  name: costgraph-customer-attribution
  namespace: my-gateway-namespace
spec:
  targetRefs:
    - group: gateway.networking.k8s.io
      kind: Gateway
      name: my-gateway
  frontend:
    metrics:
      attributes:
        add:
          - name: customer
            expression: request.headers["x-customer-id"]
```

<Note>
  A policy applies only where it is targeted, so it needs `targetRefs` or
  `targetSelectors` naming your Gateway. It must also live in that Gateway's
  namespace, because a policy cannot reach across namespaces. If a policy
  already targets the Gateway, add the `attributes` block to that one instead
  of creating a second.
</Note>

<Card title="AI gateways" icon="chart-line" href="/costgraph/integrations/ai-gateways">
  Connecting, pricing, and sending usage yourself.
</Card>