diff --git a/litellm/llms/openai/decisions/transformation.py b/litellm/llms/openai/decisions/transformation.py
index fcae4bcc49c..003fccb7a8d 100644
--- a/litellm/llms/openai/decisions/transformation.py
+++ b/litellm/llms/openai/decisions/transformation.py
@@ -45,10 +45,14 @@ from litellm.types.decisions import (
     OpenAIScoreAnswer,
     OpenAIScoreProbability,
     OpenAIScoreQuestion,
+    UnsupportedDecisionsRequest,
     systemone_choice_key,
 )
 
 _OPENAI_RESPONSE_ADAPTER: Final[TypeAdapter[OpenAIDecisionResponse]] = TypeAdapter(OpenAIDecisionResponse)
+_SINGLE_OPTION: Final = UnsupportedDecisionsRequest(
+    reason="OpenAI needs at least 2 choices or levels on every choice or score question"
+)
 
 
 def _ir_input(decision_input: OpenAIDecisionInput) -> DecisionsIRState | DecisionsIRMessages:
@@ -94,6 +98,10 @@ def _text_field(key: str, value: DecisionsJSON | None) -> Mapping[str, str]:
     return {} if value is None else {key: decisions_text(value)}
 
 
+def _instructions(value: DecisionsJSON | None, default: str) -> str:
+    return default if value is None else decisions_text(value)
+
+
 def _predicate_instructions(question: DecisionsIRPredicateQuestion) -> str:
     instructions: Final = () if question.instructions is None else (decisions_text(question.instructions),)
     criteria: Final = tuple(
@@ -110,13 +118,13 @@ def _openai_question(question: DecisionsIRQuestion) -> Mapping[str, object]:
             return {
                 "type": "predicate",
                 **_text_field("name", question.name),
-                "instructions": _predicate_instructions(question),
+                "instructions": _predicate_instructions(question) or "Is this true of the input?",
             }
         case DecisionsIRChoiceQuestion():
             return {
                 "type": "choice",
                 **_text_field("name", question.name),
-                **_text_field("instructions", question.instructions),
+                "instructions": _instructions(question.instructions, "Which choice best fits the input?"),
                 "choices": [
                     {"value": option.value, **_text_field("description", option.description)}
                     for option in question.choices
@@ -126,7 +134,7 @@ def _openai_question(question: DecisionsIRQuestion) -> Mapping[str, object]:
             return {
                 "type": "score",
                 **_text_field("name", question.name),
-                **_text_field("instructions", question.instructions),
+                "instructions": _instructions(question.instructions, "Which level best fits the input?"),
                 "levels": [
                     {"label": decisions_text(level.label), **_text_field("description", level.description)}
                     for level in question.levels
@@ -146,7 +154,19 @@ def _openai_input(decision_input: DecisionsIRState | DecisionsIRMessages) -> str
             assert_never(decision_input)
 
 
-def ir_to_openai_request(model: str, request: DecisionsIRRequest) -> Mapping[str, object]:
+def _has_one_option(question: DecisionsIRQuestion) -> bool:
+    match question:
+        case DecisionsIRChoiceQuestion():
+            return len(question.choices) < 2
+        case DecisionsIRScoreQuestion():
+            return len(question.levels) < 2
+        case _:
+            return False
+
+
+def ir_to_openai_request(model: str, request: DecisionsIRRequest) -> Mapping[str, object] | UnsupportedDecisionsRequest:
+    if any(_has_one_option(question) for question in request.questions):
+        return _SINGLE_OPTION
     return {
         "model": model,
         "input": _openai_input(request.input),
@@ -298,7 +318,9 @@ class OpenAIDecisionsEndpoint:
     def endpoint_url(self, api_base: str, model: str) -> str:
         return f"{api_base.rstrip('/').removesuffix('/v1')}/v1/decisions"
 
-    def request_body(self, model: str, request: DecisionsIRRequest) -> Mapping[str, object]:
+    def request_body(
+        self, model: str, request: DecisionsIRRequest
+    ) -> Mapping[str, object] | UnsupportedDecisionsRequest:
         return ir_to_openai_request(model, request)
 
     def parse_response(self, payload: object, request: DecisionsIRRequest) -> DecisionsIRResponse:
diff --git a/tests/unit/llms/openai/decisions/test_openai_decisions_transformation.py b/tests/unit/llms/openai/decisions/test_openai_decisions_transformation.py
index 942fad1db6d..249a1a7640a 100644
--- a/tests/unit/llms/openai/decisions/test_openai_decisions_transformation.py
+++ b/tests/unit/llms/openai/decisions/test_openai_decisions_transformation.py
@@ -1,6 +1,7 @@
 from collections.abc import Mapping
 from typing import Final
 
+import pytest
 from pydantic import TypeAdapter
 
 from litellm.llms.base_llm.decisions.transformation import ir_to_systemone_response, systemone_request_to_ir
@@ -10,7 +11,12 @@ from litellm.llms.openai.decisions.transformation import (
     ir_to_openai_response,
     openai_request_to_ir,
 )
-from litellm.types.decisions import DecisionsIRRequest, DecisionsRequestBody, OpenAIDecisionRequestBody
+from litellm.types.decisions import (
+    DecisionsIRRequest,
+    DecisionsRequestBody,
+    OpenAIDecisionRequestBody,
+    UnsupportedDecisionsRequest,
+)
 
 _SYSTEMONE_BODY: Final[TypeAdapter[DecisionsRequestBody]] = TypeAdapter(DecisionsRequestBody)
 _OPENAI_BODY: Final[TypeAdapter[OpenAIDecisionRequestBody]] = TypeAdapter(OpenAIDecisionRequestBody)
@@ -148,11 +154,49 @@ def test_a_systemone_request_becomes_an_openai_request_with_questions_named_by_t
                 "instructions": '{"policy": "refund-v2"}',
                 "choices": [{"value": "refund", "description": "Within 30 days"}, {"value": "escalate"}],
             },
-            {"type": "score", "name": "severity", "levels": [{"label": "minor"}, {"label": '{"label": "major"}'}]},
+            {
+                "type": "score",
+                "name": "severity",
+                "instructions": "Which level best fits the input?",
+                "levels": [{"label": "minor"}, {"label": '{"label": "major"}'}],
+            },
         ],
     }
 
 
+def test_systemone_questions_without_instructions_become_valid_openai_questions() -> None:
+    request: Final = _SYSTEMONE_BODY.validate_python(
+        {
+            "state": "Screen cracked",
+            "questions": {
+                "damaged": {"type": "noul", "criteria": {"false": None}},
+                "action": {"type": "choice", "criteria": {"refund": None, "escalate": None}},
+                "severity": {"type": "score", "criteria": ["minor", "major"]},
+            },
+        }
+    )
+
+    body: Final = ir_to_openai_request("gpt-6-luna", systemone_request_to_ir(request))
+
+    assert all(question.instructions for question in _OPENAI_BODY.validate_python(body).questions)
+
+
+@pytest.mark.parametrize(
+    "question",
+    ({"type": "choice", "criteria": {"refund": None}}, {"type": "score", "criteria": ["minor"]}),
+    ids=("choice", "score"),
+)
+def test_a_systemone_question_with_one_option_is_unsupported_by_openai(question: Mapping[str, object]) -> None:
+    request: Final = _SYSTEMONE_BODY.validate_python(
+        {
+            "state": "Screen cracked",
+            "questions": {"damaged": {"type": "noul", "instructions": "Damaged?"}, "q": question},
+        }
+    )
+
+    assert isinstance(ir_to_openai_request("gpt-6-luna", systemone_request_to_ir(request)), UnsupportedDecisionsRequest)
+
+
 def test_an_openai_response_becomes_systemone_answers_with_the_callers_score_labels() -> None:
     ir: Final = systemone_request_to_ir(
         _SYSTEMONE_BODY.validate_python(