diff --git a/.env.example b/.env.example
index be9bf13e..ade505f0 100644
--- a/.env.example
+++ b/.env.example
@@ -7,3 +7,4 @@ DEEPSEEK_API_KEY=
 DASHSCOPE_API_KEY=
 ZHIPU_API_KEY=
 OPENROUTER_API_KEY=
+MINIMAX_API_KEY=
diff --git a/cli/utils.py b/cli/utils.py
index 85c282ed..76421c6c 100644
--- a/cli/utils.py
+++ b/cli/utils.py
@@ -239,6 +239,7 @@ def select_llm_provider() -> tuple[str, str | None]:
         ("DeepSeek", "deepseek", "https://api.deepseek.com"),
         ("Qwen", "qwen", "https://dashscope.aliyuncs.com/compatible-mode/v1"),
         ("GLM", "glm", "https://open.bigmodel.cn/api/paas/v4/"),
+        ("MiniMax", "minimax", "https://api.minimaxi.chat/v1"),
         ("OpenRouter", "openrouter", "https://openrouter.ai/api/v1"),
         ("Azure OpenAI", "azure", None),
         ("Ollama", "ollama", "http://localhost:11434/v1"),
diff --git a/tradingagents/llm_clients/factory.py b/tradingagents/llm_clients/factory.py
index a9a7e83d..c8ec2084 100644
--- a/tradingagents/llm_clients/factory.py
+++ b/tradingagents/llm_clients/factory.py
@@ -8,7 +8,7 @@ from .azure_client import AzureOpenAIClient
 
 # Providers that use the OpenAI-compatible chat completions API
 _OPENAI_COMPATIBLE = (
-    "openai", "xai", "deepseek", "qwen", "glm", "ollama", "openrouter",
+    "openai", "xai", "deepseek", "qwen", "glm", "ollama", "openrouter", "minimax",
 )
 
 
diff --git a/tradingagents/llm_clients/model_catalog.py b/tradingagents/llm_clients/model_catalog.py
index a2c57ed8..a86e1b02 100644
--- a/tradingagents/llm_clients/model_catalog.py
+++ b/tradingagents/llm_clients/model_catalog.py
@@ -99,6 +99,20 @@ MODEL_OPTIONS: ProviderModeOptions = {
             ("Custom model ID", "custom"),
         ],
     },
+    "minimax": {
+        "quick": [
+            ("MiniMax-M2.7", "MiniMax-M2.7"),
+            ("MiniMax-M2.7-highspeed", "MiniMax-M2.7-highspeed"),
+            ("MiniMax-M2.5", "MiniMax-M2.5"),
+            ("MiniMax-M2.5-highspeed", "MiniMax-M2.5-highspeed"),
+        ],
+        "deep": [
+            ("MiniMax-M2.7", "MiniMax-M2.7"),
+            ("MiniMax-M2.7-highspeed", "MiniMax-M2.7-highspeed"),
+            ("MiniMax-M2.5", "MiniMax-M2.5"),
+            ("MiniMax-M2.5-highspeed", "MiniMax-M2.5-highspeed"),
+        ],
+    },
     # OpenRouter: fetched dynamically. Azure: any deployed model name.
     "ollama": {
         "quick": [
diff --git a/tradingagents/llm_clients/openai_client.py b/tradingagents/llm_clients/openai_client.py
index f943124a..f793be65 100644
--- a/tradingagents/llm_clients/openai_client.py
+++ b/tradingagents/llm_clients/openai_client.py
@@ -1,4 +1,6 @@
 import os
+import time
+import logging
 from typing import Any, Optional
 
 from langchain_openai import ChatOpenAI
@@ -6,6 +8,11 @@ from langchain_openai import ChatOpenAI
 from .base_client import BaseLLMClient, normalize_content
 from .validators import validate_model
 
+logger = logging.getLogger(__name__)
+
+_NULL_CHOICES_RETRIES = 3
+_NULL_CHOICES_DELAY = 2  # seconds
+
 
 class NormalizedChatOpenAI(ChatOpenAI):
     """ChatOpenAI with normalized content output.
@@ -16,7 +23,28 @@ class NormalizedChatOpenAI(ChatOpenAI):
     """
 
     def invoke(self, input, config=None, **kwargs):
-        return normalize_content(super().invoke(input, config, **kwargs))
+        for attempt in range(1, _NULL_CHOICES_RETRIES + 1):
+            try:
+                return normalize_content(super().invoke(input, config, **kwargs))
+            except TypeError as e:
+                if "null value for 'choices'" in str(e):
+                    if attempt < _NULL_CHOICES_RETRIES:
+                        logger.warning(
+                            "Received null choices from API (content filter or transient error). "
+                            "Retrying in %ds (attempt %d/%d)...",
+                            _NULL_CHOICES_DELAY,
+                            attempt,
+                            _NULL_CHOICES_RETRIES,
+                        )
+                        time.sleep(_NULL_CHOICES_DELAY)
+                    else:
+                        raise RuntimeError(
+                            "API returned null choices after retries. "
+                            "The request may have been blocked by content moderation. "
+                            "Try rephrasing the prompt or check the provider's content policy."
+                        ) from e
+                else:
+                    raise
 
 # Kwargs forwarded from user config to ChatOpenAI
 _PASSTHROUGH_KWARGS = (
@@ -32,6 +60,7 @@ _PROVIDER_CONFIG = {
     "glm": ("https://api.z.ai/api/paas/v4/", "ZHIPU_API_KEY"),
     "openrouter": ("https://openrouter.ai/api/v1", "OPENROUTER_API_KEY"),
     "ollama": ("http://localhost:11434/v1", None),
+    "minimax": ("https://api.minimaxi.chat/v1", "MINIMAX_API_KEY"),
 }