diff --git a/inference-platforms/aigw/README.md b/inference-platforms/aigw/README.md
index dac8162..b6e27d2 100644
--- a/inference-platforms/aigw/README.md
+++ b/inference-platforms/aigw/README.md
@@ -3,8 +3,10 @@
 This shows how to use [Envoy AI Gateway][docs] to proxy Ollama, accessible via an
 OpenAI compatible API.
 
-Envoy AI Gateway [YAML configuration](ai-gateway-local.yaml) is processed and run
-by `aigw`, which launches an Envoy proxy to handle requests. OpenTelemetry support
+Envoy AI Gateway is automatically configured by OpenAI and OpenTelemetry
+environment variables read by `aigw run`, such as `OPENAI_API_KEY`.
+
+`aigw run` launches an Envoy proxy to handle requests. OpenTelemetry support
 for GenAI metrics and traces is handled directly in the `aigw` (go) binary.
 
 OpenTelemetry traces produced by Envoy AI Gateway follow the [OpenInference specification][openinference].
@@ -32,7 +34,7 @@ Once Envoy AI Gateway is running, use [uv][uv] to make an OpenAI request via
 [chat.py](../chat.py):
 
 ```bash
-uv run --exact -q --env-file env.local ../chat.py
+OPENAI_BASE_URL=http://localhost:1975/v1 uv run --exact -q --env-file env.local ../chat.py
 ```
 
 ## Notes
diff --git a/inference-platforms/aigw/ai-gateway-local.yaml b/inference-platforms/aigw/ai-gateway-local.yaml
deleted file mode 100644
index a20e1aa..0000000
--- a/inference-platforms/aigw/ai-gateway-local.yaml
+++ /dev/null
@@ -1,113 +0,0 @@
-# Copyright Envoy AI Gateway Authors
-# SPDX-License-Identifier: Apache-2.0
-# The full text of the Apache license is available in the LICENSE file at
-# the root of the repo.
-
-# Configuration for running Envoy AI Gateway with an OpenAI compatible
-# inference platform, defaulting to Ollama.
-#
-# Override with the OPENAI_HOST and OPENAI_PORT environment variables.
-# For example, to use RamaLama you would set OPENAI_PORT=8080.
-#
-# TODO: Remove after https://github.com/envoyproxy/ai-gateway/issues/1211
-apiVersion: gateway.networking.k8s.io/v1
-kind: GatewayClass
-metadata:
-  name: aigw-run
-spec:
-  controllerName: gateway.envoyproxy.io/gatewayclass-controller
----
-apiVersion: gateway.networking.k8s.io/v1
-kind: Gateway
-metadata:
-  name: aigw-run
-  namespace: default
-spec:
-  gatewayClassName: aigw-run
-  listeners:
-    - name: http
-      protocol: HTTP
-      port: 1975
-  infrastructure:
-    parametersRef:
-      group: gateway.envoyproxy.io
-      kind: EnvoyProxy
-      name: envoy-ai-gateway
----
-apiVersion: gateway.envoyproxy.io/v1alpha1
-kind: EnvoyProxy
-metadata:
-  name: envoy-ai-gateway
-  namespace: default
-spec:
-  logging:
-    level:
-      default: error
----
-apiVersion: aigateway.envoyproxy.io/v1alpha1
-kind: AIGatewayRoute
-metadata:
-  name: aigw-run
-  namespace: default
-spec:
-  parentRefs:
-    - name: aigw-run
-      kind: Gateway
-      group: gateway.networking.k8s.io
-  # Simple rule: route everything to Ollama
-  rules:
-    - matches:
-        - headers:
-            - type: RegularExpression
-              name: x-ai-eg-model
-              value: .*
-      backendRefs:
-        - name: ollama
-          namespace: default
-      timeouts:
-        request: 120s
----
-apiVersion: gateway.envoyproxy.io/v1alpha1
-kind: Backend
-metadata:
-  name: ollama
-  namespace: default
-spec:
-  endpoints:
-    # Use fqdn, not ip, to allow changing to host.docker.internal
-    - fqdn:
-        hostname: ${OPENAI_HOST:=127.0.0.1.nip.io}  # Resolves to 127.0.0.1
-        port: ${OPENAI_PORT:=11434}  # Default to Ollama's port
----
-apiVersion: aigateway.envoyproxy.io/v1alpha1
-kind: AIServiceBackend
-metadata:
-  name: ollama
-  namespace: default
-spec:
-  timeouts:
-    request: 3m
-  schema:
-    name: OpenAI
-  backendRef:
-    name: ollama
-    kind: Backend
-    group: gateway.envoyproxy.io
-    namespace: default
----
-# By default, Envoy Gateway sets the buffer limit to 32kiB which is not
-# sufficient for AI workloads. This ClientTrafficPolicy sets the buffer limit
-# to 50MiB as an example.
-# TODO: Remove ofter https://github.com/envoyproxy/ai-gateway/issues/1212
-apiVersion: gateway.envoyproxy.io/v1alpha1
-kind: ClientTrafficPolicy
-metadata:
-  name: client-buffer-limit
-  namespace: default
-spec:
-  targetRefs:
-    - group: gateway.networking.k8s.io
-      kind: Gateway
-      name: aigw-run
-  connection:
-    bufferLimit: 50Mi
diff --git a/inference-platforms/aigw/docker-compose.yml b/inference-platforms/aigw/docker-compose.yml
index 82131d9..250781c 100644
--- a/inference-platforms/aigw/docker-compose.yml
+++ b/inference-platforms/aigw/docker-compose.yml
@@ -21,12 +21,10 @@ services:
     env_file:
       - env.local
     environment:
-      - OPENAI_HOST=host.docker.internal
+      - OPENAI_BASE_URL=http://host.docker.internal:11434/v1
       - OTEL_EXPORTER_OTLP_ENDPOINT=http://host.docker.internal:4318
     ports:
       - "1975:1975"  # OpenAI compatible endpoint at /v1
     extra_hosts:  # localhost:host-gateway trick doesn't work with aigw
       - "host.docker.internal:host-gateway"
-    volumes:
-      - ./ai-gateway-local.yaml:/config.yaml:ro
     command: ["run", "/config.yaml"]
diff --git a/inference-platforms/aigw/env.local b/inference-platforms/aigw/env.local
index 933b0c6..699753e 100644
--- a/inference-platforms/aigw/env.local
+++ b/inference-platforms/aigw/env.local
@@ -1,4 +1,5 @@
-OPENAI_BASE_URL=http://localhost:1975/v1
+# Override default ENV variables for Ollama
+OPENAI_BASE_URL=http://localhost:11434/v1
 OPENAI_API_KEY=unused
 CHAT_MODEL=qwen3:0.6B