Merge pull request #41870 from BerriAI/litellm_bedrock_openai_gpt_min_max_tokens

fix(bedrock): clamp maxTokens to the 16-token minimum for OpenAI GPT and xAI Grok models on Converse

litellm/llms/bedrock/chat/converse_transformation.py

@@ -108,6 +108,7 @@ BEDROCK_COMPUTER_USE_TOOLS: Final = [
     "bash_",
     "text_editor_",
 ]
+BEDROCK_OPENAI_COMPAT_MIN_MAX_TOKENS: Final = 16
 
 # Beta header patterns that are not supported by Bedrock Converse API
 # These will be filtered out to prevent errors
@@ -378,6 +379,10 @@ class AmazonConverseConfig(BaseConfig):
     def _is_openai_gpt_reasoning_model(model: str) -> bool:
         return re.search(r"openai\.gpt-\d", model) is not None
 
+    @staticmethod
+    def _requires_min_max_tokens(model: str) -> bool:
+        return re.search(r"openai\.gpt-\d|xai\.grok-", model) is not None
+
     def _is_nova_2_model(self, model: str) -> bool:
         """
         Check if the model is a Nova 2 model that supports reasoningConfig.
@@ -1000,7 +1005,11 @@ class AmazonConverseConfig(BaseConfig):
                     is_thinking_enabled=is_thinking_enabled,
                 )
             if param == "max_tokens" or param == "max_completion_tokens":
-                optional_params["maxTokens"] = value
+                optional_params["maxTokens"] = (
+                    max(value, BEDROCK_OPENAI_COMPAT_MIN_MAX_TOKENS)
+                    if isinstance(value, int) and self._requires_min_max_tokens(model)
+                    else value
+                )
             if param == "stream":
                 optional_params["stream"] = value
             if param == "stop":

tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py

@@ -458,6 +458,34 @@ def test_reasoning_with_forced_tool_choice_switches_to_auto():
     assert optional_params["tool_choice"] == {"auto": {}}
 
 
+@pytest.mark.parametrize(
+    "model, param, value, expected_max_tokens",
+    [
+        ("us.openai.gpt-6-astra", "max_tokens", 1, 16),
+        ("us.openai.gpt-6-astra", "max_completion_tokens", 1, 16),
+        ("us.openai.gpt-6-astra", "max_tokens", 64, 64),
+        ("us.xai.grok-4.6", "max_tokens", 1, 16),
+        ("global.xai.grok-4.6", "max_completion_tokens", 1, 16),
+        ("us.xai.grok-4.6", "max_tokens", 32, 32),
+        ("anthropic.claude-sonnet-4-5-20250929-v1:0", "max_tokens", 1, 1),
+        ("arn:aws:bedrock:us-east-1:123456789012:inference-profile/us.openai.gpt-6-astra", "max_tokens", 1, 16),
+        ("arn:aws:bedrock:us-east-1:123456789012:inference-profile/global.xai.grok-4.6", "max_tokens", 1, 16),
+        ("arn:aws:bedrock:us-east-1:123456789012:application-inference-profile/abc123xyz", "max_tokens", 1, 1),
+    ],
+)
+def test_map_openai_params_enforces_minimum_max_tokens_for_openai_compat_models(
+    model: str, param: str, value: int, expected_max_tokens: int
+):
+    optional_params = AmazonConverseConfig().map_openai_params(
+        non_default_params={param: value},
+        optional_params={},
+        model=model,
+        drop_params=False,
+    )
+
+    assert optional_params["maxTokens"] == expected_max_tokens
+
+
 @pytest.mark.parametrize(
     "model",
     [