diff --git a/api/services/workflow/qa/node_summary.py b/api/services/workflow/qa/node_summary.py
index aaeb7d30..c474abe8 100644
--- a/api/services/workflow/qa/node_summary.py
+++ b/api/services/workflow/qa/node_summary.py
@@ -7,6 +7,7 @@ from pipecat.processors.aggregators.llm_context import LLMContext
 
 from api.db import db_client
 from api.db.models import WorkflowRunModel
+from api.services.managed_model_services import get_mps_correlation_id
 from api.services.pipecat.service_factory import create_llm_service_from_provider
 from api.services.workflow.dto import NodeType, QANodeData
 from api.services.workflow.qa.llm_config import resolve_llm_config
@@ -75,7 +76,15 @@ async def ensure_node_summaries(
         logger.warning("No API key for node summary generation, skipping")
         return existing_summaries
 
-    llm = create_llm_service_from_provider(provider, model, api_key, **service_kwargs)
+    # Reuse the run's MPS correlation id (minted at run start, persisted on
+    # initial_context) so managed-model-services calls carry billing-v2
+    # markers — orgs on billing v2 reject managed calls that lack them.
+    mps_correlation_id = get_mps_correlation_id(
+        getattr(workflow_run, "initial_context", None)
+    )
+    llm = create_llm_service_from_provider(
+        provider, model, api_key, correlation_id=mps_correlation_id, **service_kwargs
+    )
 
     updated_summaries = dict(existing_summaries)
 
diff --git a/api/services/workflow/text_chat_runner.py b/api/services/workflow/text_chat_runner.py
index 662943e6..7fa31d4a 100644
--- a/api/services/workflow/text_chat_runner.py
+++ b/api/services/workflow/text_chat_runner.py
@@ -532,6 +532,9 @@ async def execute_text_chat_pending_turn(
     embeddings_api_key = None
     embeddings_model = None
     embeddings_base_url = None
+    embeddings_provider = None
+    embeddings_endpoint = None
+    embeddings_api_version = None
     if user_config.embeddings:
         from api.services.configuration.ai_model_configuration import (
             apply_managed_embeddings_base_url,
@@ -544,6 +547,8 @@ async def execute_text_chat_pending_turn(
             provider=embeddings_provider,
             base_url=getattr(user_config.embeddings, "base_url", None),
         )
+        embeddings_endpoint = getattr(user_config.embeddings, "endpoint", None)
+        embeddings_api_version = getattr(user_config.embeddings, "api_version", None)
 
     has_recordings = await db_client.has_active_recordings(workflow.organization_id)
     context_compaction_enabled = (workflow.workflow_configurations or {}).get(
@@ -560,6 +565,9 @@ async def execute_text_chat_pending_turn(
         embeddings_api_key=embeddings_api_key,
         embeddings_model=embeddings_model,
         embeddings_base_url=embeddings_base_url,
+        embeddings_provider=embeddings_provider,
+        embeddings_endpoint=embeddings_endpoint,
+        embeddings_api_version=embeddings_api_version,
         has_recordings=has_recordings,
         context_compaction_enabled=context_compaction_enabled,
     )