diff --git a/llama_stack/apis/agents/agents.py b/llama_stack/apis/agents/agents.py
index 50bea3d55..ba383d1f7 100644
--- a/llama_stack/apis/agents/agents.py
+++ b/llama_stack/apis/agents/agents.py
@@ -165,6 +165,7 @@ class AgentConfig(AgentConfigCommon):
     instructions: str
     enable_session_persistence: bool
     response_format: Optional[ResponseFormat] = None
+    output_parser: Optional[OutputParser] = Field(default=OutputParser.auto)
 
 
 class AgentConfigOverridablePerTurn(AgentConfigCommon):
diff --git a/llama_stack/apis/inference/inference.py b/llama_stack/apis/inference/inference.py
index 6398f74e8..637b39297 100644
--- a/llama_stack/apis/inference/inference.py
+++ b/llama_stack/apis/inference/inference.py
@@ -19,6 +19,7 @@ from typing import (
 
 from llama_models.llama3.api.datatypes import (
     BuiltinTool,
+    ResponseOutputParser,
     SamplingParams,
     StopReason,
     ToolCall,
@@ -319,6 +320,7 @@ class ChatCompletionRequest(BaseModel):
     response_format: Optional[ResponseFormat] = None
     stream: Optional[bool] = False
     logprobs: Optional[LogProbConfig] = None
+    response_output_parser: Optional[ResponseOutputParser] = Field(default=ResponseOutputParser.auto)
 
 
 @json_schema_type