feat: add MiniMax Chat node with M2.7 as default model

comfy_api_nodes/apis/minimax.py

@@ -118,3 +118,45 @@ class MinimaxVideoGenerationResponse(BaseModel):
     task_id: str = Field(
         ..., description='The task ID for the asynchronous video generation task.'
     )
+
+
+class MiniMaxChatModel(str, Enum):
+    M2_7 = 'MiniMax-M2.7'
+    M2_7_highspeed = 'MiniMax-M2.7-highspeed'
+    M2_5 = 'MiniMax-M2.5'
+    M2_5_highspeed = 'MiniMax-M2.5-highspeed'
+
+
+class MiniMaxChatMessage(BaseModel):
+    role: str = Field(..., description='The role of the message author (system, user, or assistant).')
+    content: str = Field(..., description='The content of the message.')
+
+
+class MiniMaxChatRequest(BaseModel):
+    model: str = Field(..., description='ID of the model to use.')
+    messages: list[MiniMaxChatMessage] = Field(..., description='A list of messages comprising the conversation.')
+    max_tokens: Optional[int] = Field(None, description='The maximum number of tokens to generate.')
+    temperature: Optional[float] = Field(
+        None,
+        description='Sampling temperature. Must be between 0 (exclusive) and 1 (inclusive).',
+        gt=0.0,
+        le=1.0,
+    )
+
+
+class MiniMaxChatChoice(BaseModel):
+    index: int = Field(..., description='The index of the choice.')
+    message: MiniMaxChatMessage = Field(..., description='The generated message.')
+    finish_reason: Optional[str] = Field(None, description='The reason the model stopped generating.')
+
+
+class MiniMaxChatUsage(BaseModel):
+    prompt_tokens: int = Field(0, description='Number of tokens in the prompt.')
+    completion_tokens: int = Field(0, description='Number of tokens in the generated response.')
+    total_tokens: int = Field(0, description='Total number of tokens used.')
+
+
+class MiniMaxChatResponse(BaseModel):
+    id: Optional[str] = Field(None, description='A unique identifier for the chat completion.')
+    choices: list[MiniMaxChatChoice] = Field(..., description='A list of chat completion choices.')
+    usage: Optional[MiniMaxChatUsage] = Field(None, description='Usage statistics for the request.')

comfy_api_nodes/nodes_minimax.py

@@ -5,6 +5,10 @@
 
 from comfy_api.latest import IO, ComfyExtension
 from comfy_api_nodes.apis.minimax import (
+    MiniMaxChatMessage,
+    MiniMaxChatModel,
+    MiniMaxChatRequest,
+    MiniMaxChatResponse,
     MinimaxFileRetrieveResponse,
     MiniMaxModel,
     MinimaxTaskResultResponse,
@@ -437,6 +441,118 @@ async def execute(
         return IO.NodeOutput(await download_url_to_video_output(file_url))
 
 
+class MinimaxChatNode(IO.ComfyNode):
+    """
+    Node to generate text responses using MiniMax language models.
+    """
+
+    @classmethod
+    def define_schema(cls) -> IO.Schema:
+        return IO.Schema(
+            node_id="MinimaxChatNode",
+            display_name="MiniMax Chat",
+            category="api node/text/MiniMax",
+            description="Generate text responses using MiniMax language models (MiniMax-M2.7).",
+            inputs=[
+                IO.String.Input(
+                    "prompt",
+                    default="",
+                    multiline=True,
+                    tooltip="Text prompt for the model to respond to.",
+                ),
+                IO.Combo.Input(
+                    "model",
+                    options=MiniMaxChatModel,
+                    default=MiniMaxChatModel.M2_7.value,
+                    tooltip="The MiniMax model to use for text generation.",
+                ),
+                IO.String.Input(
+                    "system_prompt",
+                    multiline=True,
+                    optional=True,
+                    tooltip="Optional system instructions to guide the model's behavior.",
+                ),
+                IO.Int.Input(
+                    "max_tokens",
+                    default=4096,
+                    min=1,
+                    max=204800,
+                    step=1,
+                    tooltip="Maximum number of tokens to generate in the response.",
+                    optional=True,
+                ),
+                IO.Float.Input(
+                    "temperature",
+                    default=0.7,
+                    min=0.01,
+                    max=1.0,
+                    step=0.01,
+                    tooltip="Controls randomness in the response. Higher values produce more creative output.",
+                    optional=True,
+                ),
+            ],
+            outputs=[
+                IO.String.Output(),
+            ],
+            hidden=[
+                IO.Hidden.auth_token_comfy_org,
+                IO.Hidden.api_key_comfy_org,
+                IO.Hidden.unique_id,
+            ],
+            is_api_node=True,
+            price_badge=IO.PriceBadge(
+                depends_on=IO.PriceBadgeDepends(widgets=["model"]),
+                expr="""
+                (
+                  $m := widgets.model;
+                  $contains($m, "highspeed") ? {
+                    "type": "list_usd",
+                    "usd": [0.00004, 0.0002],
+                    "format": { "approximate": true, "separator": "-", "suffix": " per 1K tokens" }
+                  }
+                  : {
+                    "type": "list_usd",
+                    "usd": [0.0001, 0.0006],
+                    "format": { "approximate": true, "separator": "-", "suffix": " per 1K tokens" }
+                  }
+                )
+                """,
+            ),
+        )
+
+    @classmethod
+    async def execute(
+        cls,
+        prompt: str,
+        model: str = MiniMaxChatModel.M2_7.value,
+        system_prompt: Optional[str] = None,
+        max_tokens: int = 4096,
+        temperature: float = 0.7,
+    ) -> IO.NodeOutput:
+        validate_string(prompt, field_name="prompt")
+
+        messages: list[MiniMaxChatMessage] = []
+        if system_prompt:
+            messages.append(MiniMaxChatMessage(role="system", content=system_prompt))
+        messages.append(MiniMaxChatMessage(role="user", content=prompt))
+
+        response = await sync_op(
+            cls,
+            ApiEndpoint(path="/proxy/minimax/chat/completions", method="POST"),
+            response_model=MiniMaxChatResponse,
+            data=MiniMaxChatRequest(
+                model=MiniMaxChatModel(model).value,
+                messages=messages,
+                max_tokens=max_tokens,
+                temperature=temperature,
+            ),
+        )
+
+        if response.choices:
+            return IO.NodeOutput(response.choices[0].message.content)
+        raise RuntimeError("No response generated by MiniMax model.")
+
+
 class MinimaxExtension(ComfyExtension):
     @override
     async def get_node_list(self) -> list[type[IO.ComfyNode]]:
@@ -445,6 +561,7 @@ async def get_node_list(self) -> list[type[IO.ComfyNode]]:
             MinimaxImageToVideoNode,
             # MinimaxSubjectToVideoNode,
             MinimaxHailuoVideoNode,
+            MinimaxChatNode,
         ]
 
 

tests-unit/comfy_api_test/minimax_models_test.py

@@ -0,0 +1,27 @@
+import pytest
+from comfy_api_nodes.apis.minimax import MiniMaxChatModel
+
+
+class TestMiniMaxChatModel:
+    def test_m27_in_model_list(self):
+        """MiniMax-M2.7 should be available in the chat model enum."""
+        assert MiniMaxChatModel.M2_7.value == 'MiniMax-M2.7'
+
+    def test_m27_highspeed_in_model_list(self):
+        """MiniMax-M2.7-highspeed should be available in the chat model enum."""
+        assert MiniMaxChatModel.M2_7_highspeed.value == 'MiniMax-M2.7-highspeed'
+
+    def test_m27_is_first_in_enum(self):
+        """M2.7 should appear before older models in the enum."""
+        members = list(MiniMaxChatModel)
+        assert members[0] == MiniMaxChatModel.M2_7
+        assert members[1] == MiniMaxChatModel.M2_7_highspeed
+
+    def test_legacy_models_still_available(self):
+        """Previous M2.5 models should still be available."""
+        assert MiniMaxChatModel.M2_5.value == 'MiniMax-M2.5'
+        assert MiniMaxChatModel.M2_5_highspeed.value == 'MiniMax-M2.5-highspeed'
+
+    def test_total_model_count(self):
+        """Should have 4 chat models total (M2.7, M2.7-highspeed, M2.5, M2.5-highspeed)."""
+        assert len(MiniMaxChatModel) == 4