Files
2026-05-12 19:51:31 +00:00

30 lines
822 B
YAML

---
apiVersion: aigateway.envoyproxy.io/v1beta1
kind: AIGatewayRoute
metadata:
name: envoy-ai-gateway-gpt-oss
spec:
parentRefs:
- name: ai-gateway
kind: Gateway
group: gateway.networking.k8s.io
rules:
- matches:
- headers:
- type: Exact
name: x-ai-eg-model
value: RedHatAI/gpt-oss-20b
backendRefs:
- group: inference.networking.k8s.io
kind: InferencePool
name: gpt-oss-20b-inference-pool
timeouts:
request: 60s
llmRequestCosts:
- metadataKey: llm_input_token
type: InputToken # Counts tokens in the request
- metadataKey: llm_output_token
type: OutputToken # Counts tokens in the response
- metadataKey: llm_total_token
type: TotalToken # Tracks combined usage