diff --git a/litellm/llms/fireworks_ai/responses/transformation.py b/litellm/llms/fireworks_ai/responses/transformation.py index 463b9cbfc9a..d599f0b65f7 100644 --- a/litellm/llms/fireworks_ai/responses/transformation.py +++ b/litellm/llms/fireworks_ai/responses/transformation.py @@ -29,6 +29,7 @@ from litellm.utils import ( declared_mid_conversation_system_support, deployment_declared_mid_conversation_system_support, deployment_model_info, + get_bundled_model_cost_map, ) if TYPE_CHECKING: @@ -54,6 +55,15 @@ 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() + 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): @property def custom_llm_provider(self) -> LlmProviders: @@ -90,9 +100,13 @@ class FireworksAIResponsesAPIConfig(OpenAIResponsesAPIConfig): validated_input: Final = self._validate_input_param(input) model_info: Final = deployment_model_info(litellm_params) declared: Final = declared_mid_conversation_system_support(model, self.custom_llm_provider.value, model_info) + keeps_developer_items_in_place: Final = declared is True and ( + deployment_declared_mid_conversation_system_support(model_info) is True + or _bundled_cost_map_declares_mid_conversation_system(model) + ) folded: Final = ( None - if deployment_declared_mid_conversation_system_support(model_info) is True + if keeps_developer_items_in_place else instruction_items_folded( validated_input, response_api_optional_request_params, "user" if declared is False else "system" ) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 703621b60cf..1d0d87d8643 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -64026,6 +64026,7 @@ "output_cost_per_token_priority": 1.5e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -64045,6 +64046,7 @@ "output_cost_per_token_priority": 2.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -64087,6 +64089,7 @@ ], "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -64124,6 +64127,7 @@ "output_cost_per_token_priority": 1.5e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -64143,6 +64147,7 @@ "output_cost_per_token_priority": 2.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -64217,6 +64222,7 @@ ], "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -64237,6 +64243,7 @@ ], "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -64260,6 +64267,7 @@ ], "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -64335,6 +64343,7 @@ "output_cost_per_token_priority": 3e-06, "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, @@ -64371,6 +64380,7 @@ "output_cost_per_token_priority": 6.375e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_vision": true }, @@ -64407,6 +64417,7 @@ "output_cost_per_token_priority": 3e-06, "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, @@ -64477,6 +64488,7 @@ ], "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -64500,6 +64512,7 @@ ], "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -67293,6 +67306,7 @@ "output_cost_per_token_priority": 5.5e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -67311,6 +67325,7 @@ "output_cost_per_token_priority": 8.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -67329,6 +67344,7 @@ "output_cost_per_token_priority": 5.5e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -67347,6 +67363,7 @@ "output_cost_per_token_priority": 8.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -67362,6 +67379,7 @@ "output_cost_per_token": 6.6e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -67404,6 +67422,7 @@ "output_cost_per_token": 6.6e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -67422,6 +67441,7 @@ "output_cost_per_token_priority": 6.25e-07, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true @@ -67440,6 +67460,7 @@ "output_cost_per_token_priority": 9.375e-07, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true @@ -67457,6 +67478,7 @@ "output_cost_per_token_priority": 6.25e-07, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true @@ -67475,6 +67497,7 @@ "output_cost_per_token_priority": 9.375e-07, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true @@ -67493,6 +67516,7 @@ "output_cost_per_token_priority": 4.05e-06, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true @@ -73728,6 +73752,7 @@ "output_cost_per_token_priority": 1.875e-05, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -77228,6 +77253,7 @@ "output_cost_per_token_priority": 1.5e-06, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -77386,6 +77412,7 @@ "output_cost_per_token_priority": 9e-07, "source": "https://platform.minimax.io/docs/guides/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -81161,6 +81188,7 @@ ], "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -81177,6 +81205,7 @@ "output_cost_per_token": 3.08e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -81193,6 +81222,7 @@ "output_cost_per_token": 8.4e-07, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -81209,6 +81239,7 @@ "output_cost_per_token": 8.4e-07, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 703621b60cf..1d0d87d8643 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -64026,6 +64026,7 @@ "output_cost_per_token_priority": 1.5e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -64045,6 +64046,7 @@ "output_cost_per_token_priority": 2.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -64087,6 +64089,7 @@ ], "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -64124,6 +64127,7 @@ "output_cost_per_token_priority": 1.5e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -64143,6 +64147,7 @@ "output_cost_per_token_priority": 2.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -64217,6 +64222,7 @@ ], "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -64237,6 +64243,7 @@ ], "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -64260,6 +64267,7 @@ ], "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -64335,6 +64343,7 @@ "output_cost_per_token_priority": 3e-06, "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, @@ -64371,6 +64380,7 @@ "output_cost_per_token_priority": 6.375e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_vision": true }, @@ -64407,6 +64417,7 @@ "output_cost_per_token_priority": 3e-06, "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, @@ -64477,6 +64488,7 @@ ], "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -64500,6 +64512,7 @@ ], "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -67293,6 +67306,7 @@ "output_cost_per_token_priority": 5.5e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -67311,6 +67325,7 @@ "output_cost_per_token_priority": 8.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -67329,6 +67344,7 @@ "output_cost_per_token_priority": 5.5e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -67347,6 +67363,7 @@ "output_cost_per_token_priority": 8.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -67362,6 +67379,7 @@ "output_cost_per_token": 6.6e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -67404,6 +67422,7 @@ "output_cost_per_token": 6.6e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -67422,6 +67441,7 @@ "output_cost_per_token_priority": 6.25e-07, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true @@ -67440,6 +67460,7 @@ "output_cost_per_token_priority": 9.375e-07, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true @@ -67457,6 +67478,7 @@ "output_cost_per_token_priority": 6.25e-07, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true @@ -67475,6 +67497,7 @@ "output_cost_per_token_priority": 9.375e-07, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true @@ -67493,6 +67516,7 @@ "output_cost_per_token_priority": 4.05e-06, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true @@ -73728,6 +73752,7 @@ "output_cost_per_token_priority": 1.875e-05, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -77228,6 +77253,7 @@ "output_cost_per_token_priority": 1.5e-06, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -77386,6 +77412,7 @@ "output_cost_per_token_priority": 9e-07, "source": "https://platform.minimax.io/docs/guides/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -81161,6 +81188,7 @@ ], "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -81177,6 +81205,7 @@ "output_cost_per_token": 3.08e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -81193,6 +81222,7 @@ "output_cost_per_token": 8.4e-07, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -81209,6 +81239,7 @@ "output_cost_per_token": 8.4e-07, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": 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 7fc6ac2c436..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 @@ -172,10 +172,10 @@ def test_responses_call_forwards_previous_response_id_and_store() -> None: def test_responses_call_folds_developer_items_into_instructions() -> None: - client: Final = _mock_http_client(_fireworks_response("accounts/fireworks/models/kimi-k3")) + client: Final = _mock_http_client(_fireworks_response("accounts/fireworks/models/qwen3p8-2p4t-a95b")) with patch(HTTPX_CLIENT_FACTORY, return_value=client): litellm.responses( - model="fireworks_ai/accounts/fireworks/models/kimi-k3", + model="fireworks_ai/accounts/fireworks/models/qwen3p8-2p4t-a95b", input=[ {"role": "user", "content": "Hi there"}, {"role": "developer", "content": "Answer with exactly one word."}, @@ -214,6 +214,68 @@ def test_responses_call_keeps_developer_items_in_place_for_a_deployment_that_acc ) +@respx.mock +@pytest.mark.parametrize( + "model", + [ + "fireworks_ai/accounts/fireworks/models/kimi-k3", + "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( + model: str, +) -> None: + route: Final = _fireworks_responses_route(model.removeprefix("fireworks_ai/")) + litellm.responses( + model=model, + instructions="You are Codex", + input=[ + {"role": "user", "content": "Hi there"}, + {"role": "developer", "content": "Answer with exactly one word."}, + {"role": "user", "content": "What is the capital of France?"}, + ], + api_key="fw-test-key", + ) + body: Final = _routed_body(route) + assert body["instructions"] == "You are Codex" + assert tuple(body["input"]) == ( + {"role": "user", "content": "Hi there"}, + {"role": "system", "content": "Answer with exactly one word.", "type": "message"}, + {"role": "user", "content": "What is the capital of France?"}, + ) + + +@respx.mock +def test_responses_call_folds_developer_items_when_the_loaded_cost_map_turns_the_flag_off( + declare_mid_conversation_system: Callable[[str, bool], None], +) -> None: + declare_mid_conversation_system("fireworks_ai/accounts/fireworks/models/kimi-k3", False) + route: Final = _fireworks_responses_route("accounts/fireworks/models/kimi-k3") + litellm.responses( + model="fireworks_ai/accounts/fireworks/models/kimi-k3", + input=[ + {"role": "user", "content": "Hi there"}, + {"role": "developer", "content": "Answer with exactly one word."}, + {"role": "user", "content": "What is the capital of France?"}, + {"type": "message", "role": "assistant", "content": "Paris"}, + {"role": "developer", "content": "Reply with PONG."}, + ], + api_key="fw-test-key", + ) + body: Final = _routed_body(route) + assert body["instructions"] == "Answer with exactly one word." + assert tuple(body["input"]) == ( + {"role": "user", "content": "Hi there"}, + {"role": "user", "content": "What is the capital of France?"}, + {"type": "message", "role": "assistant", "content": "Paris"}, + {"role": "user", "content": "Reply with PONG.", "type": "message"}, + ) + + @respx.mock @pytest.mark.parametrize( ("model_info", "closing_role"), @@ -222,9 +284,9 @@ def test_responses_call_keeps_developer_items_in_place_for_a_deployment_that_acc def test_responses_call_sends_the_closing_developer_item_as_a_user_turn_only_for_a_declared_system_first_deployment( model_info: Mapping[str, object] | None, closing_role: str ) -> None: - route: Final = _fireworks_responses_route("accounts/fireworks/models/kimi-k3") + route: Final = _fireworks_responses_route("accounts/fireworks/models/qwen3p8-2p4t-a95b") litellm.responses( - model="fireworks_ai/accounts/fireworks/models/kimi-k3", + model="fireworks_ai/accounts/fireworks/models/qwen3p8-2p4t-a95b", input=[ {"role": "user", "content": "Hi there"}, {"role": "developer", "content": "Answer with exactly one word."}, @@ -402,7 +464,7 @@ def test_transform_request_forwards_non_string_instructions_and_input_untouched( developer_item: Final = {"role": "developer", "content": "Answer with exactly one word."} user_item: Final = {"role": "user", "content": "What is the capital of France?"} request: Final = FireworksAIResponsesAPIConfig().transform_responses_api_request( - model="accounts/fireworks/models/kimi-k3", + model="accounts/fireworks/models/qwen3p8-2p4t-a95b", input=cast(ResponseInputParam, [developer_item, user_item]), response_api_optional_request_params={"instructions": ["not", "a", "string"]}, litellm_params=GenericLiteLLMParams(), @@ -416,7 +478,7 @@ def test_transform_request_forwards_non_string_instructions_and_input_untouched( def test_responses_call_maps_pydantic_developer_items_and_replays_pydantic_output_items() -> None: - client: Final = _mock_http_client(_fireworks_response("accounts/fireworks/models/kimi-k3")) + client: Final = _mock_http_client(_fireworks_response("accounts/fireworks/models/qwen3p8-2p4t-a95b")) pydantic_input: Final = cast( ResponseInputParam, [ @@ -435,7 +497,9 @@ def test_responses_call_maps_pydantic_developer_items_and_replays_pydantic_outpu ) with patch(HTTPX_CLIENT_FACTORY, return_value=client): litellm.responses( - model="fireworks_ai/accounts/fireworks/models/kimi-k3", input=pydantic_input, api_key="fw-test-key" + model="fireworks_ai/accounts/fireworks/models/qwen3p8-2p4t-a95b", + input=pydantic_input, + api_key="fw-test-key", ) _, _, body = _sent_request(client) assert body["instructions"] == "Answer with exactly one word."