diff --git a/litellm/llms/fireworks_ai/responses/transformation.py b/litellm/llms/fireworks_ai/responses/transformation.py index 0c2c83c2978..636075e18b2 100644 --- a/litellm/llms/fireworks_ai/responses/transformation.py +++ b/litellm/llms/fireworks_ai/responses/transformation.py @@ -53,8 +53,11 @@ def _forwarded_user_params(litellm_params: GenericLiteLLMParams) -> Mapping[str, def _bundled_cost_map_declares_mid_conversation_system(model: str) -> bool: bundled_cost_map: Final[Mapping[str, object]] = get_bundled_model_cost_map() - entry: Final = bundled_cost_map.get(f"fireworks_ai/{model.removeprefix('fireworks_ai/')}") - return deployment_declared_mid_conversation_system_support(entry) is True + names: Final = (model.removeprefix("fireworks_ai/"), resolve_fireworks_resource_name(model)) + return any( + deployment_declared_mid_conversation_system_support(bundled_cost_map.get(f"fireworks_ai/{name}")) is True + for name in names + ) class FireworksAIResponsesAPIConfig(OpenAIResponsesAPIConfig): diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 300d62faeed..480dfc542bd 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -27839,7 +27839,6 @@ "output_cost_per_token_priority": 7.2e-07, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, - "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -28214,7 +28213,6 @@ "output_cost_per_token_priority": 7.2e-07, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, - "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 300d62faeed..480dfc542bd 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -27839,7 +27839,6 @@ "output_cost_per_token_priority": 7.2e-07, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, - "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -28214,7 +28213,6 @@ "output_cost_per_token_priority": 7.2e-07, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, - "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, diff --git a/tests/unit/llms/fireworks_ai/responses/test_fireworks_ai_responses_transformation.py b/tests/unit/llms/fireworks_ai/responses/test_fireworks_ai_responses_transformation.py index aa231c978f8..6538ccf1cac 100644 --- a/tests/unit/llms/fireworks_ai/responses/test_fireworks_ai_responses_transformation.py +++ b/tests/unit/llms/fireworks_ai/responses/test_fireworks_ai_responses_transformation.py @@ -222,6 +222,8 @@ def test_responses_call_keeps_developer_items_in_place_for_a_deployment_that_acc "fireworks_ai/accounts/fireworks/models/glm-5p3", "fireworks_ai/accounts/fireworks/routers/kimi-k3-fast", "fireworks_ai/glm-5p3-us", + "fireworks_ai/models/kimi-k3", + "fireworks_ai/routers/kimi-k3-fast", ], ) def test_responses_call_keeps_developer_items_in_place_for_a_model_the_cost_map_declares_accepts_them(