diff --git a/.env.example b/.env.example
index d93ee34e..019d9e98 100644
--- a/.env.example
+++ b/.env.example
@@ -5,7 +5,7 @@
 # Supported providers: openai, groq, ollama, gemini, anthropic, lmstudio, vertexai
 HINDSIGHT_API_LLM_PROVIDER=openai
 HINDSIGHT_API_LLM_API_KEY=your-api-key-here
-HINDSIGHT_API_LLM_MODEL=o3-mini
+HINDSIGHT_API_LLM_MODEL=gpt-4o-mini
 HINDSIGHT_API_LLM_BASE_URL=https://api.openai.com/v1
 
 # Example: Anthropic Claude configuration
diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
index 4ad0160c..f00efac1 100644
--- a/.github/workflows/test.yml
+++ b/.github/workflows/test.yml
@@ -171,10 +171,9 @@ jobs:
   test-rust-cli:
     runs-on: ubuntu-latest
     env:
-      HINDSIGHT_API_LLM_PROVIDER: groq
-      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
-      HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
-      HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
+      HINDSIGHT_API_LLM_PROVIDER: openai
+      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
       HINDSIGHT_API_URL: http://localhost:8888
       GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       UV_INDEX: pytorch=https://download.pytorch.org/whl/cpu
@@ -234,7 +233,6 @@ jobs:
         HINDSIGHT_API_LLM_PROVIDER=${{ env.HINDSIGHT_API_LLM_PROVIDER }}
         HINDSIGHT_API_LLM_API_KEY=${{ env.HINDSIGHT_API_LLM_API_KEY }}
         HINDSIGHT_API_LLM_MODEL=${{ env.HINDSIGHT_API_LLM_MODEL }}
-        HINDSIGHT_API_LLM_GROQ_SERVICE_TIER=${{ env.HINDSIGHT_API_LLM_GROQ_SERVICE_TIER }}
         EOF
 
     - name: Start API server
@@ -345,7 +343,9 @@ jobs:
     - name: Smoke test - verify container starts
       if: matrix.variant == 'slim'
       env:
-        GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
+        HINDSIGHT_API_LLM_PROVIDER: openai
+        HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+        HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
         HINDSIGHT_API_EMBEDDINGS_PROVIDER: openai
         HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
         HINDSIGHT_API_RERANKER_PROVIDER: cohere
@@ -355,15 +355,13 @@ jobs:
   test-api:
     runs-on: ubuntu-latest
     env:
-      HINDSIGHT_API_LLM_PROVIDER: groq
-      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
-      GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
+      HINDSIGHT_API_LLM_PROVIDER: openai
+      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
       GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
       OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
       COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
       HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-      HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
-      HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
+      HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
       GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       # Prefer CPU-only PyTorch in CI (but keep PyPI for everything else)
       UV_INDEX: pytorch=https://download.pytorch.org/whl/cpu
@@ -417,10 +415,9 @@ jobs:
   test-python-client:
     runs-on: ubuntu-latest
     env:
-      HINDSIGHT_API_LLM_PROVIDER: groq
-      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
-      HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
-      HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
+      HINDSIGHT_API_LLM_PROVIDER: openai
+      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
       HINDSIGHT_API_URL: http://localhost:8888
       GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       # Prefer CPU-only PyTorch in CI (but keep PyPI for everything else)
@@ -462,7 +459,6 @@ jobs:
         HINDSIGHT_API_LLM_PROVIDER=${{ env.HINDSIGHT_API_LLM_PROVIDER }}
         HINDSIGHT_API_LLM_API_KEY=${{ env.HINDSIGHT_API_LLM_API_KEY }}
         HINDSIGHT_API_LLM_MODEL=${{ env.HINDSIGHT_API_LLM_MODEL }}
-        HINDSIGHT_API_LLM_GROQ_SERVICE_TIER=${{ env.HINDSIGHT_API_LLM_GROQ_SERVICE_TIER }}
         EOF
 
     - name: Start API server
@@ -495,10 +491,9 @@ jobs:
   test-typescript-client:
     runs-on: ubuntu-latest
     env:
-      HINDSIGHT_API_LLM_PROVIDER: groq
-      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
-      HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
-      HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
+      HINDSIGHT_API_LLM_PROVIDER: openai
+      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
       HINDSIGHT_API_URL: http://localhost:8888
       GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       # Prefer CPU-only PyTorch in CI (but keep PyPI for everything else)
@@ -545,7 +540,6 @@ jobs:
         HINDSIGHT_API_LLM_PROVIDER=${{ env.HINDSIGHT_API_LLM_PROVIDER }}
         HINDSIGHT_API_LLM_API_KEY=${{ env.HINDSIGHT_API_LLM_API_KEY }}
         HINDSIGHT_API_LLM_MODEL=${{ env.HINDSIGHT_API_LLM_MODEL }}
-        HINDSIGHT_API_LLM_GROQ_SERVICE_TIER=${{ env.HINDSIGHT_API_LLM_GROQ_SERVICE_TIER }}
         EOF
 
     - name: Start API server
@@ -578,10 +572,9 @@ jobs:
   test-rust-client:
     runs-on: ubuntu-latest
     env:
-      HINDSIGHT_API_LLM_PROVIDER: groq
-      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
-      HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
-      HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
+      HINDSIGHT_API_LLM_PROVIDER: openai
+      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
       HINDSIGHT_API_URL: http://localhost:8888
       GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       # Prefer CPU-only PyTorch in CI (but keep PyPI for everything else)
@@ -627,7 +620,6 @@ jobs:
         HINDSIGHT_API_LLM_PROVIDER=${{ env.HINDSIGHT_API_LLM_PROVIDER }}
         HINDSIGHT_API_LLM_API_KEY=${{ env.HINDSIGHT_API_LLM_API_KEY }}
         HINDSIGHT_API_LLM_MODEL=${{ env.HINDSIGHT_API_LLM_MODEL }}
-        HINDSIGHT_API_LLM_GROQ_SERVICE_TIER=${{ env.HINDSIGHT_API_LLM_GROQ_SERVICE_TIER }}
         EOF
 
     - name: Start API server
@@ -660,10 +652,9 @@ jobs:
   test-go-client:
     runs-on: ubuntu-latest
     env:
-      HINDSIGHT_API_LLM_PROVIDER: groq
-      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
-      HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
-      HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
+      HINDSIGHT_API_LLM_PROVIDER: openai
+      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
       HINDSIGHT_API_URL: http://localhost:8888
       GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       # Prefer CPU-only PyTorch in CI (but keep PyPI for everything else)
@@ -703,7 +694,6 @@ jobs:
         HINDSIGHT_API_LLM_PROVIDER=${{ env.HINDSIGHT_API_LLM_PROVIDER }}
         HINDSIGHT_API_LLM_API_KEY=${{ env.HINDSIGHT_API_LLM_API_KEY }}
         HINDSIGHT_API_LLM_MODEL=${{ env.HINDSIGHT_API_LLM_MODEL }}
-        HINDSIGHT_API_LLM_GROQ_SERVICE_TIER=${{ env.HINDSIGHT_API_LLM_GROQ_SERVICE_TIER }}
         EOF
 
     - name: Start API server
@@ -740,10 +730,9 @@ jobs:
   test-openclaw-integration:
     runs-on: ubuntu-latest
     env:
-      HINDSIGHT_API_LLM_PROVIDER: groq
-      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
-      HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
-      HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
+      HINDSIGHT_API_LLM_PROVIDER: openai
+      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
       HINDSIGHT_API_URL: http://localhost:8888
       HINDSIGHT_EMBED_PACKAGE_PATH: ${{ github.workspace }}/hindsight-embed
       GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@@ -810,7 +799,6 @@ jobs:
         HINDSIGHT_API_LLM_PROVIDER=${{ env.HINDSIGHT_API_LLM_PROVIDER }}
         HINDSIGHT_API_LLM_API_KEY=${{ env.HINDSIGHT_API_LLM_API_KEY }}
         HINDSIGHT_API_LLM_MODEL=${{ env.HINDSIGHT_API_LLM_MODEL }}
-        HINDSIGHT_API_LLM_GROQ_SERVICE_TIER=${{ env.HINDSIGHT_API_LLM_GROQ_SERVICE_TIER }}
         EOF
 
     - name: Start API server
@@ -843,10 +831,9 @@ jobs:
   test-integration:
     runs-on: ubuntu-latest
     env:
-      HINDSIGHT_API_LLM_PROVIDER: groq
-      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
-      HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
-      HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
+      HINDSIGHT_API_LLM_PROVIDER: openai
+      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
       HINDSIGHT_API_URL: http://localhost:8888
       GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       UV_INDEX: pytorch=https://download.pytorch.org/whl/cpu
@@ -903,7 +890,6 @@ jobs:
         HINDSIGHT_API_LLM_PROVIDER=${{ env.HINDSIGHT_API_LLM_PROVIDER }}
         HINDSIGHT_API_LLM_API_KEY=${{ env.HINDSIGHT_API_LLM_API_KEY }}
         HINDSIGHT_API_LLM_MODEL=${{ env.HINDSIGHT_API_LLM_MODEL }}
-        HINDSIGHT_API_LLM_GROQ_SERVICE_TIER=${{ env.HINDSIGHT_API_LLM_GROQ_SERVICE_TIER }}
         EOF
 
     - name: Start API server
@@ -994,10 +980,9 @@ jobs:
   test-embed:
     runs-on: ubuntu-latest
     env:
-      HINDSIGHT_API_LLM_PROVIDER: groq
-      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
-      HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
-      HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
+      HINDSIGHT_API_LLM_PROVIDER: openai
+      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
       # Prefer CPU-only PyTorch in CI
       UV_INDEX: pytorch=https://download.pytorch.org/whl/cpu
 
@@ -1039,14 +1024,13 @@ jobs:
   test-hindsight-all:
     runs-on: ubuntu-latest
     env:
-      HINDSIGHT_API_LLM_PROVIDER: groq
-      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
-      HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
-      HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
+      HINDSIGHT_API_LLM_PROVIDER: openai
+      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
       # For test_server_integration.py compatibility
-      HINDSIGHT_LLM_PROVIDER: groq
-      HINDSIGHT_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
-      HINDSIGHT_LLM_MODEL: openai/gpt-oss-20b
+      HINDSIGHT_LLM_PROVIDER: openai
+      HINDSIGHT_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      HINDSIGHT_LLM_MODEL: gpt-4o-mini
       # Prefer CPU-only PyTorch in CI
       UV_INDEX: pytorch=https://download.pytorch.org/whl/cpu
 
@@ -1089,10 +1073,9 @@ jobs:
     runs-on: ubuntu-latest
     needs: test-rust-cli
     env:
-      HINDSIGHT_API_LLM_PROVIDER: groq
-      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
-      HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
-      HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
+      HINDSIGHT_API_LLM_PROVIDER: openai
+      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
       HINDSIGHT_API_URL: http://localhost:8888
       GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       UV_INDEX: pytorch=https://download.pytorch.org/whl/cpu
@@ -1148,7 +1131,6 @@ jobs:
         HINDSIGHT_API_LLM_PROVIDER=${{ env.HINDSIGHT_API_LLM_PROVIDER }}
         HINDSIGHT_API_LLM_API_KEY=${{ env.HINDSIGHT_API_LLM_API_KEY }}
         HINDSIGHT_API_LLM_MODEL=${{ env.HINDSIGHT_API_LLM_MODEL }}
-        HINDSIGHT_API_LLM_GROQ_SERVICE_TIER=${{ env.HINDSIGHT_API_LLM_GROQ_SERVICE_TIER }}
         EOF
 
     - name: Start API server
@@ -1183,10 +1165,9 @@ jobs:
   test-upgrade:
     runs-on: ubuntu-latest
     env:
-      HINDSIGHT_API_LLM_PROVIDER: groq
-      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
-      HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
-      HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
+      HINDSIGHT_API_LLM_PROVIDER: openai
+      HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
       GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       UV_INDEX: pytorch=https://download.pytorch.org/whl/cpu
 
diff --git a/CLAUDE.md b/CLAUDE.md
index cc8340e5..46813775 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -317,7 +317,7 @@ npm install
 Required env vars:
 - `HINDSIGHT_API_LLM_PROVIDER`: openai, anthropic, gemini, groq, ollama, lmstudio
 - `HINDSIGHT_API_LLM_API_KEY`: Your API key
-- `HINDSIGHT_API_LLM_MODEL`: Model name (e.g., o3-mini, claude-sonnet-4-20250514)
+- `HINDSIGHT_API_LLM_MODEL`: Model name (e.g., gpt-4o-mini, claude-sonnet-4-20250514)
 
 Optional (uses local models by default):
 - `HINDSIGHT_API_EMBEDDINGS_PROVIDER`: local (default) or tei
diff --git a/docker/test-image.sh b/docker/test-image.sh
index 10cc55f6..e4fe4592 100755
--- a/docker/test-image.sh
+++ b/docker/test-image.sh
@@ -13,9 +13,9 @@
 #   target  - Optional: 'cp-only' for control plane, otherwise assumes API image (default: api)
 #
 # Environment variables:
-#   GROQ_API_KEY                                - Required for API/standalone images (LLM verification)
-#   HINDSIGHT_API_LLM_PROVIDER                  - LLM provider (default: groq)
-#   HINDSIGHT_API_LLM_MODEL                     - LLM model (default: llama-3.3-70b-versatile)
+#   HINDSIGHT_API_LLM_API_KEY                   - Required for API/standalone images (LLM verification)
+#   HINDSIGHT_API_LLM_PROVIDER                  - LLM provider (default: openai)
+#   HINDSIGHT_API_LLM_MODEL                     - LLM model (default: gpt-4o-mini)
 #   HINDSIGHT_API_EMBEDDINGS_PROVIDER           - Embeddings provider (optional, for slim images: openai, cohere, tei)
 #   HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY     - OpenAI API key for embeddings (optional)
 #   HINDSIGHT_API_RERANKER_PROVIDER             - Reranker provider (optional, for slim images: cohere, tei)
@@ -34,7 +34,7 @@
 #   ./docker/test-image.sh hindsight-control-plane:test cp-only
 #
 #   # Test slim image with external providers
-#   export GROQ_API_KEY=gsk_xxx
+#   export HINDSIGHT_API_LLM_API_KEY=sk_xxx
 #   export HINDSIGHT_API_EMBEDDINGS_PROVIDER=openai
 #   export HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY=sk-xxx
 #   export HINDSIGHT_API_RERANKER_PROVIDER=cohere
@@ -60,8 +60,8 @@ IMAGE="${1:-}"
 TARGET="${2:-api}"
 TIMEOUT="${SMOKE_TEST_TIMEOUT:-120}"
 CONTAINER_NAME="${SMOKE_TEST_CONTAINER_NAME:-hindsight-smoke-test}"
-LLM_PROVIDER="${HINDSIGHT_API_LLM_PROVIDER:-groq}"
-LLM_MODEL="${HINDSIGHT_API_LLM_MODEL:-llama-3.3-70b-versatile}"
+LLM_PROVIDER="${HINDSIGHT_API_LLM_PROVIDER:-openai}"
+LLM_MODEL="${HINDSIGHT_API_LLM_MODEL:-gpt-4o-mini}"
 
 # Validate arguments
 if [ -z "$IMAGE" ]; then
@@ -88,9 +88,9 @@ else
 fi
 
 # Check for required environment variables
-if [ "$NEEDS_LLM" = true ] && [ -z "${GROQ_API_KEY:-}" ]; then
-    echo -e "${RED}Error: GROQ_API_KEY environment variable is required for API/standalone images${NC}"
-    echo "Set it with: export GROQ_API_KEY=your-api-key"
+if [ "$NEEDS_LLM" = true ] && [ -z "${HINDSIGHT_API_LLM_API_KEY:-}" ]; then
+    echo -e "${RED}Error: HINDSIGHT_API_LLM_API_KEY environment variable is required for API/standalone images${NC}"
+    echo "Set it with: export HINDSIGHT_API_LLM_API_KEY=your-api-key"
     exit 2
 fi
 
@@ -123,7 +123,7 @@ else
     # Build docker run command with required and optional env vars
     DOCKER_CMD="docker run -d --name $CONTAINER_NAME"
     DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_LLM_PROVIDER=$LLM_PROVIDER"
-    DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_LLM_API_KEY=${GROQ_API_KEY}"
+    DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_LLM_API_KEY=${HINDSIGHT_API_LLM_API_KEY}"
     DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_LLM_MODEL=$LLM_MODEL"
 
     # Add optional embeddings provider config
diff --git a/docker/test-slim-local.sh b/docker/test-slim-local.sh
index 08dabbb1..5830a079 100755
--- a/docker/test-slim-local.sh
+++ b/docker/test-slim-local.sh
@@ -6,24 +6,17 @@
 # It expects API keys to be set in environment variables.
 #
 # Usage:
-#   export GROQ_API_KEY=gsk_xxx
 #   export OPENAI_API_KEY=sk-xxx
 #   export COHERE_API_KEY=xxx
 #   ./docker/test-slim-local.sh
 #
 # Or inline:
-#   GROQ_API_KEY=gsk_xxx OPENAI_API_KEY=sk_xxx COHERE_API_KEY=xxx ./docker/test-slim-local.sh
+#   OPENAI_API_KEY=sk_xxx COHERE_API_KEY=xxx ./docker/test-slim-local.sh
 #
 
 set -euo pipefail
 
 # Check for required API keys
-if [ -z "${GROQ_API_KEY:-}" ]; then
-    echo "❌ Error: GROQ_API_KEY environment variable is required"
-    echo "Set it with: export GROQ_API_KEY=gsk_xxx"
-    exit 1
-fi
-
 if [ -z "${OPENAI_API_KEY:-}" ]; then
     echo "❌ Error: OPENAI_API_KEY environment variable is required"
     echo "Set it with: export OPENAI_API_KEY=sk-xxx"
@@ -41,7 +34,10 @@ IMAGE="${1:-hindsight-slim:test}"
 echo "Testing image: $IMAGE"
 echo ""
 
-# Set up external providers
+# Set up LLM and external providers
+export HINDSIGHT_API_LLM_PROVIDER=openai
+export HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY
+export HINDSIGHT_API_LLM_MODEL=gpt-4o-mini
 export HINDSIGHT_API_EMBEDDINGS_PROVIDER=openai
 export HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY=$OPENAI_API_KEY
 export HINDSIGHT_API_RERANKER_PROVIDER=cohere
diff --git a/hindsight-api/hindsight_api/config.py b/hindsight-api/hindsight_api/config.py
index a87330f5..99ce6e54 100644
--- a/hindsight-api/hindsight_api/config.py
+++ b/hindsight-api/hindsight_api/config.py
@@ -314,7 +314,7 @@ DEFAULT_LLM_PROVIDER = "openai"
 
 # Provider-specific default models
 PROVIDER_DEFAULT_MODELS = {
-    "openai": "o3-mini",
+    "openai": "gpt-4o-mini",
     "anthropic": "claude-haiku-4-5-20251001",
     "gemini": "gemini-2.5-flash",
     "groq": "openai/gpt-oss-120b",
@@ -325,7 +325,7 @@ PROVIDER_DEFAULT_MODELS = {
     "claude-code": "claude-sonnet-4-5-20250929",
     "mock": "mock-model",
 }
-DEFAULT_LLM_MODEL = "o3-mini"  # Fallback if provider not in table
+DEFAULT_LLM_MODEL = "gpt-4o-mini"  # Fallback if provider not in table
 DEFAULT_LLM_MAX_CONCURRENT = 32
 DEFAULT_LLM_MAX_RETRIES = 10  # Max retry attempts for LLM API calls
 DEFAULT_LLM_INITIAL_BACKOFF = 1.0  # Initial backoff in seconds for retry exponential backoff
diff --git a/hindsight-api/tests/test_provider_default_models.py b/hindsight-api/tests/test_provider_default_models.py
index 433d8b94..cc424111 100644
--- a/hindsight-api/tests/test_provider_default_models.py
+++ b/hindsight-api/tests/test_provider_default_models.py
@@ -93,7 +93,7 @@ def test_per_operation_provider_default_model():
         config = HindsightConfig.from_env()
 
         # Global LLM should use OpenAI default
-        assert config.llm_model == "o3-mini", f"Expected o3-mini, got {config.llm_model}"
+        assert config.llm_model == "gpt-4o-mini", f"Expected gpt-4o-mini, got {config.llm_model}"
 
         # Retain should use Anthropic default
         assert (
diff --git a/hindsight-docs/docs/cookbook/applications/go-memory-service.md b/hindsight-docs/docs/cookbook/applications/go-memory-service.md
index 2cc8db82..ef0728fc 100644
--- a/hindsight-docs/docs/cookbook/applications/go-memory-service.md
+++ b/hindsight-docs/docs/cookbook/applications/go-memory-service.md
@@ -29,7 +29,7 @@ export OPENAI_API_KEY=your-key
 
 docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
   -e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-  -e HINDSIGHT_API_LLM_MODEL=o3-mini \
+  -e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
   -v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
   ghcr.io/vectorize-io/hindsight:latest
 ```
diff --git a/hindsight-docs/docs/cookbook/recipes/litellm-memory-demo.md b/hindsight-docs/docs/cookbook/recipes/litellm-memory-demo.md
index 3e7594b4..d633f706 100644
--- a/hindsight-docs/docs/cookbook/recipes/litellm-memory-demo.md
+++ b/hindsight-docs/docs/cookbook/recipes/litellm-memory-demo.md
@@ -31,7 +31,7 @@ export OPENAI_API_KEY=your-key
 
 docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
   -e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-  -e HINDSIGHT_API_LLM_MODEL=o3-mini \
+  -e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
   -v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
   ghcr.io/vectorize-io/hindsight:latest
 ```
diff --git a/hindsight-docs/docs/cookbook/recipes/quickstart.md b/hindsight-docs/docs/cookbook/recipes/quickstart.md
index b219fe9a..cea1cd77 100644
--- a/hindsight-docs/docs/cookbook/recipes/quickstart.md
+++ b/hindsight-docs/docs/cookbook/recipes/quickstart.md
@@ -25,7 +25,7 @@ export OPENAI_API_KEY=your-key
 
 docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
   -e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-  -e HINDSIGHT_API_LLM_MODEL=o3-mini \
+  -e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
   -v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
   ghcr.io/vectorize-io/hindsight:latest
 ```
diff --git a/hindsight-docs/docs/cookbook/recipes/tool-learning-demo.md b/hindsight-docs/docs/cookbook/recipes/tool-learning-demo.md
index 927eec91..c2e3b870 100644
--- a/hindsight-docs/docs/cookbook/recipes/tool-learning-demo.md
+++ b/hindsight-docs/docs/cookbook/recipes/tool-learning-demo.md
@@ -35,7 +35,7 @@ export OPENAI_API_KEY=your-key
 
 docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
   -e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-  -e HINDSIGHT_API_LLM_MODEL=o3-mini \
+  -e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
   -v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
   ghcr.io/vectorize-io/hindsight:latest
 ```
diff --git a/hindsight-docs/docs/developer/models.md b/hindsight-docs/docs/developer/models.md
index 5afd4eb4..f45f8ade 100644
--- a/hindsight-docs/docs/developer/models.md
+++ b/hindsight-docs/docs/developer/models.md
@@ -53,7 +53,7 @@ Each provider has a recommended default model that's used when `HINDSIGHT_API_LL
 
 | Provider | Default Model |
 |----------|--------------|
-| `openai` | `o3-mini` |
+| `openai` | `gpt-4o-mini` |
 | `anthropic` | `claude-haiku-4-5-20251001` |
 | `gemini` | `gemini-2.5-flash` |
 | `groq` | `openai/gpt-oss-120b` |
@@ -80,7 +80,7 @@ export HINDSIGHT_API_LLM_MODEL=claude-sonnet-4-5-20250929
 
 This also applies to per-operation overrides:
 ```bash
-# Global: OpenAI o3-mini (default)
+# Global: OpenAI gpt-4o-mini (default)
 export HINDSIGHT_API_LLM_PROVIDER=openai
 
 # Retain: Anthropic claude-haiku-4-5-20251001 (default)
diff --git a/hindsight-docs/docs/sdks/integrations/openclaw.md b/hindsight-docs/docs/sdks/integrations/openclaw.md
index bcd1567e..86a4f0b9 100644
--- a/hindsight-docs/docs/sdks/integrations/openclaw.md
+++ b/hindsight-docs/docs/sdks/integrations/openclaw.md
@@ -30,7 +30,7 @@ export GROQ_API_KEY="your-key"
 # Option E: Claude Code (uses claude-sonnet-4-20250514, no API key needed)
 export HINDSIGHT_API_LLM_PROVIDER=claude-code
 
-# Option F: OpenAI Codex (uses o3-mini, no API key needed)
+# Option F: OpenAI Codex (uses gpt-4o-mini, no API key needed)
 export HINDSIGHT_API_LLM_PROVIDER=openai-codex
 ```
 
@@ -103,7 +103,7 @@ The plugin auto-detects your LLM provider from these environment variables:
 | Gemini | `GEMINI_API_KEY` | `gemini-2.5-flash` | |
 | Groq | `GROQ_API_KEY` | `openai/gpt-oss-20b` | |
 | Claude Code | `HINDSIGHT_API_LLM_PROVIDER=claude-code` | `claude-sonnet-4-20250514` | No API key needed |
-| OpenAI Codex | `HINDSIGHT_API_LLM_PROVIDER=openai-codex` | `o3-mini` | No API key needed |
+| OpenAI Codex | `HINDSIGHT_API_LLM_PROVIDER=openai-codex` | `gpt-4o-mini` | No API key needed |
 
 **Override with explicit config:**
 
diff --git a/hindsight-docs/versioned_docs/version-0.3/cookbook/recipes/litellm-memory-demo.md b/hindsight-docs/versioned_docs/version-0.3/cookbook/recipes/litellm-memory-demo.md
index 3e7594b4..d633f706 100644
--- a/hindsight-docs/versioned_docs/version-0.3/cookbook/recipes/litellm-memory-demo.md
+++ b/hindsight-docs/versioned_docs/version-0.3/cookbook/recipes/litellm-memory-demo.md
@@ -31,7 +31,7 @@ export OPENAI_API_KEY=your-key
 
 docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
   -e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-  -e HINDSIGHT_API_LLM_MODEL=o3-mini \
+  -e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
   -v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
   ghcr.io/vectorize-io/hindsight:latest
 ```
diff --git a/hindsight-docs/versioned_docs/version-0.3/cookbook/recipes/quickstart.md b/hindsight-docs/versioned_docs/version-0.3/cookbook/recipes/quickstart.md
index b219fe9a..cea1cd77 100644
--- a/hindsight-docs/versioned_docs/version-0.3/cookbook/recipes/quickstart.md
+++ b/hindsight-docs/versioned_docs/version-0.3/cookbook/recipes/quickstart.md
@@ -25,7 +25,7 @@ export OPENAI_API_KEY=your-key
 
 docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
   -e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-  -e HINDSIGHT_API_LLM_MODEL=o3-mini \
+  -e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
   -v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
   ghcr.io/vectorize-io/hindsight:latest
 ```
diff --git a/hindsight-docs/versioned_docs/version-0.3/cookbook/recipes/tool-learning-demo.md b/hindsight-docs/versioned_docs/version-0.3/cookbook/recipes/tool-learning-demo.md
index 927eec91..c2e3b870 100644
--- a/hindsight-docs/versioned_docs/version-0.3/cookbook/recipes/tool-learning-demo.md
+++ b/hindsight-docs/versioned_docs/version-0.3/cookbook/recipes/tool-learning-demo.md
@@ -35,7 +35,7 @@ export OPENAI_API_KEY=your-key
 
 docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
   -e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-  -e HINDSIGHT_API_LLM_MODEL=o3-mini \
+  -e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
   -v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
   ghcr.io/vectorize-io/hindsight:latest
 ```
diff --git a/hindsight-docs/versioned_docs/version-0.4/cookbook/applications/go-memory-service.md b/hindsight-docs/versioned_docs/version-0.4/cookbook/applications/go-memory-service.md
index 2cc8db82..ef0728fc 100644
--- a/hindsight-docs/versioned_docs/version-0.4/cookbook/applications/go-memory-service.md
+++ b/hindsight-docs/versioned_docs/version-0.4/cookbook/applications/go-memory-service.md
@@ -29,7 +29,7 @@ export OPENAI_API_KEY=your-key
 
 docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
   -e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-  -e HINDSIGHT_API_LLM_MODEL=o3-mini \
+  -e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
   -v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
   ghcr.io/vectorize-io/hindsight:latest
 ```
diff --git a/hindsight-docs/versioned_docs/version-0.4/cookbook/recipes/litellm-memory-demo.md b/hindsight-docs/versioned_docs/version-0.4/cookbook/recipes/litellm-memory-demo.md
index 3e7594b4..d633f706 100644
--- a/hindsight-docs/versioned_docs/version-0.4/cookbook/recipes/litellm-memory-demo.md
+++ b/hindsight-docs/versioned_docs/version-0.4/cookbook/recipes/litellm-memory-demo.md
@@ -31,7 +31,7 @@ export OPENAI_API_KEY=your-key
 
 docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
   -e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-  -e HINDSIGHT_API_LLM_MODEL=o3-mini \
+  -e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
   -v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
   ghcr.io/vectorize-io/hindsight:latest
 ```
diff --git a/hindsight-docs/versioned_docs/version-0.4/cookbook/recipes/quickstart.md b/hindsight-docs/versioned_docs/version-0.4/cookbook/recipes/quickstart.md
index b219fe9a..cea1cd77 100644
--- a/hindsight-docs/versioned_docs/version-0.4/cookbook/recipes/quickstart.md
+++ b/hindsight-docs/versioned_docs/version-0.4/cookbook/recipes/quickstart.md
@@ -25,7 +25,7 @@ export OPENAI_API_KEY=your-key
 
 docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
   -e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-  -e HINDSIGHT_API_LLM_MODEL=o3-mini \
+  -e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
   -v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
   ghcr.io/vectorize-io/hindsight:latest
 ```
diff --git a/hindsight-docs/versioned_docs/version-0.4/cookbook/recipes/tool-learning-demo.md b/hindsight-docs/versioned_docs/version-0.4/cookbook/recipes/tool-learning-demo.md
index 927eec91..c2e3b870 100644
--- a/hindsight-docs/versioned_docs/version-0.4/cookbook/recipes/tool-learning-demo.md
+++ b/hindsight-docs/versioned_docs/version-0.4/cookbook/recipes/tool-learning-demo.md
@@ -35,7 +35,7 @@ export OPENAI_API_KEY=your-key
 
 docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
   -e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-  -e HINDSIGHT_API_LLM_MODEL=o3-mini \
+  -e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
   -v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
   ghcr.io/vectorize-io/hindsight:latest
 ```
diff --git a/hindsight-docs/versioned_docs/version-0.4/developer/models.md b/hindsight-docs/versioned_docs/version-0.4/developer/models.md
index 5afd4eb4..f45f8ade 100644
--- a/hindsight-docs/versioned_docs/version-0.4/developer/models.md
+++ b/hindsight-docs/versioned_docs/version-0.4/developer/models.md
@@ -53,7 +53,7 @@ Each provider has a recommended default model that's used when `HINDSIGHT_API_LL
 
 | Provider | Default Model |
 |----------|--------------|
-| `openai` | `o3-mini` |
+| `openai` | `gpt-4o-mini` |
 | `anthropic` | `claude-haiku-4-5-20251001` |
 | `gemini` | `gemini-2.5-flash` |
 | `groq` | `openai/gpt-oss-120b` |
@@ -80,7 +80,7 @@ export HINDSIGHT_API_LLM_MODEL=claude-sonnet-4-5-20250929
 
 This also applies to per-operation overrides:
 ```bash
-# Global: OpenAI o3-mini (default)
+# Global: OpenAI gpt-4o-mini (default)
 export HINDSIGHT_API_LLM_PROVIDER=openai
 
 # Retain: Anthropic claude-haiku-4-5-20251001 (default)
diff --git a/hindsight-docs/versioned_docs/version-0.4/sdks/integrations/openclaw.md b/hindsight-docs/versioned_docs/version-0.4/sdks/integrations/openclaw.md
index bcd1567e..86a4f0b9 100644
--- a/hindsight-docs/versioned_docs/version-0.4/sdks/integrations/openclaw.md
+++ b/hindsight-docs/versioned_docs/version-0.4/sdks/integrations/openclaw.md
@@ -30,7 +30,7 @@ export GROQ_API_KEY="your-key"
 # Option E: Claude Code (uses claude-sonnet-4-20250514, no API key needed)
 export HINDSIGHT_API_LLM_PROVIDER=claude-code
 
-# Option F: OpenAI Codex (uses o3-mini, no API key needed)
+# Option F: OpenAI Codex (uses gpt-4o-mini, no API key needed)
 export HINDSIGHT_API_LLM_PROVIDER=openai-codex
 ```
 
@@ -103,7 +103,7 @@ The plugin auto-detects your LLM provider from these environment variables:
 | Gemini | `GEMINI_API_KEY` | `gemini-2.5-flash` | |
 | Groq | `GROQ_API_KEY` | `openai/gpt-oss-20b` | |
 | Claude Code | `HINDSIGHT_API_LLM_PROVIDER=claude-code` | `claude-sonnet-4-20250514` | No API key needed |
-| OpenAI Codex | `HINDSIGHT_API_LLM_PROVIDER=openai-codex` | `o3-mini` | No API key needed |
+| OpenAI Codex | `HINDSIGHT_API_LLM_PROVIDER=openai-codex` | `gpt-4o-mini` | No API key needed |
 
 **Override with explicit config:**
 
diff --git a/skills/hindsight-docs/references/cookbook/applications/go-memory-service.md b/skills/hindsight-docs/references/cookbook/applications/go-memory-service.md
index 2cc8db82..ef0728fc 100644
--- a/skills/hindsight-docs/references/cookbook/applications/go-memory-service.md
+++ b/skills/hindsight-docs/references/cookbook/applications/go-memory-service.md
@@ -29,7 +29,7 @@ export OPENAI_API_KEY=your-key
 
 docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
   -e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-  -e HINDSIGHT_API_LLM_MODEL=o3-mini \
+  -e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
   -v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
   ghcr.io/vectorize-io/hindsight:latest
 ```
diff --git a/skills/hindsight-docs/references/cookbook/recipes/litellm-memory-demo.md b/skills/hindsight-docs/references/cookbook/recipes/litellm-memory-demo.md
index 3e7594b4..d633f706 100644
--- a/skills/hindsight-docs/references/cookbook/recipes/litellm-memory-demo.md
+++ b/skills/hindsight-docs/references/cookbook/recipes/litellm-memory-demo.md
@@ -31,7 +31,7 @@ export OPENAI_API_KEY=your-key
 
 docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
   -e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-  -e HINDSIGHT_API_LLM_MODEL=o3-mini \
+  -e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
   -v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
   ghcr.io/vectorize-io/hindsight:latest
 ```
diff --git a/skills/hindsight-docs/references/cookbook/recipes/quickstart.md b/skills/hindsight-docs/references/cookbook/recipes/quickstart.md
index b219fe9a..cea1cd77 100644
--- a/skills/hindsight-docs/references/cookbook/recipes/quickstart.md
+++ b/skills/hindsight-docs/references/cookbook/recipes/quickstart.md
@@ -25,7 +25,7 @@ export OPENAI_API_KEY=your-key
 
 docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
   -e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-  -e HINDSIGHT_API_LLM_MODEL=o3-mini \
+  -e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
   -v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
   ghcr.io/vectorize-io/hindsight:latest
 ```
diff --git a/skills/hindsight-docs/references/cookbook/recipes/tool-learning-demo.md b/skills/hindsight-docs/references/cookbook/recipes/tool-learning-demo.md
index 927eec91..c2e3b870 100644
--- a/skills/hindsight-docs/references/cookbook/recipes/tool-learning-demo.md
+++ b/skills/hindsight-docs/references/cookbook/recipes/tool-learning-demo.md
@@ -35,7 +35,7 @@ export OPENAI_API_KEY=your-key
 
 docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
   -e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-  -e HINDSIGHT_API_LLM_MODEL=o3-mini \
+  -e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
   -v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
   ghcr.io/vectorize-io/hindsight:latest
 ```
diff --git a/skills/hindsight-docs/references/developer/models.md b/skills/hindsight-docs/references/developer/models.md
index 5afd4eb4..f45f8ade 100644
--- a/skills/hindsight-docs/references/developer/models.md
+++ b/skills/hindsight-docs/references/developer/models.md
@@ -53,7 +53,7 @@ Each provider has a recommended default model that's used when `HINDSIGHT_API_LL
 
 | Provider | Default Model |
 |----------|--------------|
-| `openai` | `o3-mini` |
+| `openai` | `gpt-4o-mini` |
 | `anthropic` | `claude-haiku-4-5-20251001` |
 | `gemini` | `gemini-2.5-flash` |
 | `groq` | `openai/gpt-oss-120b` |
@@ -80,7 +80,7 @@ export HINDSIGHT_API_LLM_MODEL=claude-sonnet-4-5-20250929
 
 This also applies to per-operation overrides:
 ```bash
-# Global: OpenAI o3-mini (default)
+# Global: OpenAI gpt-4o-mini (default)
 export HINDSIGHT_API_LLM_PROVIDER=openai
 
 # Retain: Anthropic claude-haiku-4-5-20251001 (default)
diff --git a/skills/hindsight-docs/references/sdks/integrations/openclaw.md b/skills/hindsight-docs/references/sdks/integrations/openclaw.md
index bcd1567e..86a4f0b9 100644
--- a/skills/hindsight-docs/references/sdks/integrations/openclaw.md
+++ b/skills/hindsight-docs/references/sdks/integrations/openclaw.md
@@ -30,7 +30,7 @@ export GROQ_API_KEY="your-key"
 # Option E: Claude Code (uses claude-sonnet-4-20250514, no API key needed)
 export HINDSIGHT_API_LLM_PROVIDER=claude-code
 
-# Option F: OpenAI Codex (uses o3-mini, no API key needed)
+# Option F: OpenAI Codex (uses gpt-4o-mini, no API key needed)
 export HINDSIGHT_API_LLM_PROVIDER=openai-codex
 ```
 
@@ -103,7 +103,7 @@ The plugin auto-detects your LLM provider from these environment variables:
 | Gemini | `GEMINI_API_KEY` | `gemini-2.5-flash` | |
 | Groq | `GROQ_API_KEY` | `openai/gpt-oss-20b` | |
 | Claude Code | `HINDSIGHT_API_LLM_PROVIDER=claude-code` | `claude-sonnet-4-20250514` | No API key needed |
-| OpenAI Codex | `HINDSIGHT_API_LLM_PROVIDER=openai-codex` | `o3-mini` | No API key needed |
+| OpenAI Codex | `HINDSIGHT_API_LLM_PROVIDER=openai-codex` | `gpt-4o-mini` | No API key needed |
 
 **Override with explicit config:**