diff --git a/llmstack/processors/providers/minimax/__init__.py b/llmstack/processors/providers/minimax/__init__.py
new file mode 100644
index 00000000000..e8f778bba8c
--- /dev/null
+++ b/llmstack/processors/providers/minimax/__init__.py
@@ -0,0 +1,25 @@
+from typing import Optional
+
+from pydantic import Field
+
+from llmstack.processors.providers.config import ProviderConfig
+
+
+class MiniMaxProviderConfig(ProviderConfig):
+    provider_slug: str = "minimax"
+    api_key: str = Field(
+        title="API Key",
+        description="Your MiniMax API Key",
+        default="",
+        json_schema_extra={"widget": "password", "advanced_parameter": False},
+    )
+    base_url: Optional[str] = Field(
+        title="Base URL",
+        description="Base URL for the MiniMax OpenAI-compatible API.",
+        default="https://api.minimax.io/v1",
+    )
+    organization: Optional[str] = Field(
+        title="Organization ID",
+        description="Organization ID to use in MiniMax API requests",
+        default=None,
+    )
diff --git a/llmstack/processors/providers/minimax/chat_completions.py b/llmstack/processors/providers/minimax/chat_completions.py
new file mode 100644
index 00000000000..89b3dccc23d
--- /dev/null
+++ b/llmstack/processors/providers/minimax/chat_completions.py
@@ -0,0 +1,167 @@
+import logging
+from typing import List, Optional
+
+from asgiref.sync import async_to_sync
+from pydantic import Field
+
+from llmstack.apps.schemas import OutputTemplate
+from llmstack.common.blocks.base.schema import StrEnum
+from llmstack.processors.providers.api_processor_interface import (
+    ApiProcessorInterface,
+    ApiProcessorSchema,
+)
+
+logger = logging.getLogger(__name__)
+
+
+class MessagesModel(StrEnum):
+    MINIMAX_M3 = "MiniMax-M3"
+
+    def model_name(self):
+        return self.value
+
+
+class Role(StrEnum):
+    USER = "user"
+    SYSTEM = "system"
+    ASSISTANT = "assistant"
+
+
+class ChatMessage(ApiProcessorSchema):
+    role: Role = Field(
+        default=Role.USER,
+        description="The role of the message. Can be 'system', 'user', or 'assistant'.",
+    )
+    message: str = Field(
+        default="",
+        description="The message text.",
+        json_schema_extra={"widget": "textarea"},
+    )
+
+
+class MessagesInput(ApiProcessorSchema):
+    messages: List[ChatMessage] = Field(
+        default=[
+            ChatMessage(),
+        ],
+        description="A list of messages, each with a role and message text.",
+    )
+
+
+class MessagesOutput(ApiProcessorSchema):
+    result: str = Field(description="The response message.")
+
+
+class MessagesConfiguration(ApiProcessorSchema):
+    system_prompt: str = Field(
+        default="",
+        description="A system prompt is a way of providing context and instructions to the model.",
+        json_schema_extra={"widget": "textarea", "advanced_parameter": False},
+    )
+
+    model: MessagesModel = Field(
+        default=MessagesModel.MINIMAX_M3,
+        description="The MiniMax model that will generate the responses.",
+        json_schema_extra={"advanced_parameter": False},
+    )
+    max_tokens: int = Field(
+        ge=1,
+        default=256,
+        description="The maximum number of tokens to generate before stopping.",
+        json_schema_extra={"advanced_parameter": False},
+    )
+    temperature: float = Field(
+        default=0.5,
+        description="Amount of randomness injected into the response.",
+        multiple_of=0.1,
+        ge=0.0,
+        le=1.0,
+        json_schema_extra={"advanced_parameter": False},
+    )
+    retain_history: Optional[bool] = Field(
+        default=False,
+        description="Retain and use the chat history. (Only works in apps)",
+    )
+    seed: Optional[int] = Field(
+        default=None,
+        description="The seed to use for random sampling. If set, different calls will generate deterministic results.",
+    )
+
+
+class MessagesProcessor(ApiProcessorInterface[MessagesInput, MessagesOutput, MessagesConfiguration]):
+    @staticmethod
+    def name() -> str:
+        return "Chat Completions"
+
+    @staticmethod
+    def slug() -> str:
+        return "chat_completions"
+
+    @staticmethod
+    def description() -> str:
+        return "MiniMax Chat Completions"
+
+    @staticmethod
+    def provider_slug() -> str:
+        return "minimax"
+
+    @classmethod
+    def get_output_template(cls) -> OutputTemplate:
+        return OutputTemplate(
+            markdown="""{{ result }}""",
+            jsonpath="$.result",
+        )
+
+    def process_session_data(self, session_data):
+        self._chat_history = session_data["chat_history"] if "chat_history" in session_data else []
+
+    def session_data_to_persist(self) -> dict:
+        if self._config.retain_history:
+            return {"chat_history": self._chat_history}
+        return {}
+
+    def process(self) -> MessagesOutput:
+        from llmstack.common.utils.sslr import LLM
+
+        minimax_provider_config = self.get_provider_config(model_slug=self._config.model.model_name())
+        client = LLM(
+            provider="openai",
+            openai_api_key=minimax_provider_config.api_key,
+            openai_base_url=minimax_provider_config.base_url,
+            organization=minimax_provider_config.organization,
+        )
+        messages = []
+
+        if self._config.system_prompt:
+            messages.append({"role": "system", "content": self._config.system_prompt})
+
+        if self._chat_history:
+            for message in self._chat_history:
+                messages.append({"role": message["role"], "content": message["message"]})
+
+        for message in self._input.messages:
+            messages.append({"role": str(message.role), "content": str(message.message)})
+
+        response = client.chat.completions.create(
+            messages=messages,
+            model=self._config.model.model_name(),
+            max_tokens=self._config.max_tokens,
+            stream=True,
+            temperature=self._config.temperature,
+            seed=self._config.seed,
+        )
+
+        for result in response:
+            choice = result.choices[0]
+            if choice.delta.content:
+                async_to_sync(self._output_stream.write)(MessagesOutput(result=choice.delta.content))
+
+        output = self._output_stream.finalize()
+
+        if self._config.retain_history:
+            for message in self._input.messages:
+                self._chat_history.append({"role": str(message.role), "message": str(message.message)})
+
+            self._chat_history.append({"role": "assistant", "message": output.message})
+
+        return output
diff --git a/llmstack/server/settings.py b/llmstack/server/settings.py
index b720d01ecf4..ef8db3c500d 100644
--- a/llmstack/server/settings.py
+++ b/llmstack/server/settings.py
@@ -574,6 +574,12 @@
         "slug": "mistral",
         "config_schema": "llmstack.processors.providers.mistral.MistralProviderConfig",
     },
+    {
+        "name": "MiniMax",
+        "processor_packages": ["llmstack.processors.providers.minimax"],
+        "slug": "minimax",
+        "config_schema": "llmstack.processors.providers.minimax.MiniMaxProviderConfig",
+    },
     {
         "name": "Meta",
         "processor_packages": ["llmstack.processors.providers.meta"],