diff --git a/llama_stack/providers/remote/inference/openai/models.py b/llama_stack/providers/remote/inference/openai/models.py
index 37bee57de..28d0c4b41 100644
--- a/llama_stack/providers/remote/inference/openai/models.py
+++ b/llama_stack/providers/remote/inference/openai/models.py
@@ -12,11 +12,6 @@ from llama_stack.providers.utils.inference.model_registry import (
 )
 
 LLM_MODEL_IDS = [
-    # the models w/ "openai/" prefix are the litellm specific model names.
-    # they should be deprecated in favor of the canonical openai model names.
-    "openai/gpt-4o",
-    "openai/gpt-4o-mini",
-    "openai/chatgpt-4o-latest",
     "gpt-3.5-turbo-0125",
     "gpt-3.5-turbo",
     "gpt-3.5-turbo-instruct",
@@ -43,8 +38,6 @@ class EmbeddingModelInfo:
 
 
 EMBEDDING_MODEL_IDS: dict[str, EmbeddingModelInfo] = {
-    "openai/text-embedding-3-small": EmbeddingModelInfo(1536, 8192),
-    "openai/text-embedding-3-large": EmbeddingModelInfo(3072, 8192),
     "text-embedding-3-small": EmbeddingModelInfo(1536, 8192),
     "text-embedding-3-large": EmbeddingModelInfo(3072, 8192),
 }
diff --git a/llama_stack/templates/ci-tests/run.yaml b/llama_stack/templates/ci-tests/run.yaml
index 3555c2d5e..1396d54a8 100644
--- a/llama_stack/templates/ci-tests/run.yaml
+++ b/llama_stack/templates/ci-tests/run.yaml
@@ -785,21 +785,6 @@ models:
   provider_id: ${env.ENABLE_RUNPOD:=__disabled__}
   provider_model_id: Llama3.2-3B
   model_type: llm
-- metadata: {}
-  model_id: ${env.ENABLE_OPENAI:=__disabled__}/openai/gpt-4o
-  provider_id: ${env.ENABLE_OPENAI:=__disabled__}
-  provider_model_id: openai/gpt-4o
-  model_type: llm
-- metadata: {}
-  model_id: ${env.ENABLE_OPENAI:=__disabled__}/openai/gpt-4o-mini
-  provider_id: ${env.ENABLE_OPENAI:=__disabled__}
-  provider_model_id: openai/gpt-4o-mini
-  model_type: llm
-- metadata: {}
-  model_id: ${env.ENABLE_OPENAI:=__disabled__}/openai/chatgpt-4o-latest
-  provider_id: ${env.ENABLE_OPENAI:=__disabled__}
-  provider_model_id: openai/chatgpt-4o-latest
-  model_type: llm
 - metadata: {}
   model_id: ${env.ENABLE_OPENAI:=__disabled__}/gpt-3.5-turbo-0125
   provider_id: ${env.ENABLE_OPENAI:=__disabled__}
@@ -870,20 +855,6 @@ models:
   provider_id: ${env.ENABLE_OPENAI:=__disabled__}
   provider_model_id: o4-mini
   model_type: llm
-- metadata:
-    embedding_dimension: 1536
-    context_length: 8192
-  model_id: ${env.ENABLE_OPENAI:=__disabled__}/openai/text-embedding-3-small
-  provider_id: ${env.ENABLE_OPENAI:=__disabled__}
-  provider_model_id: openai/text-embedding-3-small
-  model_type: embedding
-- metadata:
-    embedding_dimension: 3072
-    context_length: 8192
-  model_id: ${env.ENABLE_OPENAI:=__disabled__}/openai/text-embedding-3-large
-  provider_id: ${env.ENABLE_OPENAI:=__disabled__}
-  provider_model_id: openai/text-embedding-3-large
-  model_type: embedding
 - metadata:
     embedding_dimension: 1536
     context_length: 8192
diff --git a/llama_stack/templates/starter/run.yaml b/llama_stack/templates/starter/run.yaml
index 32ee0ea21..c38933f98 100644
--- a/llama_stack/templates/starter/run.yaml
+++ b/llama_stack/templates/starter/run.yaml
@@ -785,21 +785,6 @@ models:
   provider_id: ${env.ENABLE_RUNPOD:=__disabled__}
   provider_model_id: Llama3.2-3B
   model_type: llm
-- metadata: {}
-  model_id: ${env.ENABLE_OPENAI:=__disabled__}/openai/gpt-4o
-  provider_id: ${env.ENABLE_OPENAI:=__disabled__}
-  provider_model_id: openai/gpt-4o
-  model_type: llm
-- metadata: {}
-  model_id: ${env.ENABLE_OPENAI:=__disabled__}/openai/gpt-4o-mini
-  provider_id: ${env.ENABLE_OPENAI:=__disabled__}
-  provider_model_id: openai/gpt-4o-mini
-  model_type: llm
-- metadata: {}
-  model_id: ${env.ENABLE_OPENAI:=__disabled__}/openai/chatgpt-4o-latest
-  provider_id: ${env.ENABLE_OPENAI:=__disabled__}
-  provider_model_id: openai/chatgpt-4o-latest
-  model_type: llm
 - metadata: {}
   model_id: ${env.ENABLE_OPENAI:=__disabled__}/gpt-3.5-turbo-0125
   provider_id: ${env.ENABLE_OPENAI:=__disabled__}
@@ -870,20 +855,6 @@ models:
   provider_id: ${env.ENABLE_OPENAI:=__disabled__}
   provider_model_id: o4-mini
   model_type: llm
-- metadata:
-    embedding_dimension: 1536
-    context_length: 8192
-  model_id: ${env.ENABLE_OPENAI:=__disabled__}/openai/text-embedding-3-small
-  provider_id: ${env.ENABLE_OPENAI:=__disabled__}
-  provider_model_id: openai/text-embedding-3-small
-  model_type: embedding
-- metadata:
-    embedding_dimension: 3072
-    context_length: 8192
-  model_id: ${env.ENABLE_OPENAI:=__disabled__}/openai/text-embedding-3-large
-  provider_id: ${env.ENABLE_OPENAI:=__disabled__}
-  provider_model_id: openai/text-embedding-3-large
-  model_type: embedding
 - metadata:
     embedding_dimension: 1536
     context_length: 8192