feat: add MiniMax as LLM provider

Add MiniMax (MiniMax-M2.5 and MiniMax-M2.5-highspeed) as a supported
LLM provider. MiniMax offers an OpenAI-compatible API with 204K context
window support.

Changes:
- Add MiniMax provider routing in factory (via OpenAI-compatible client)
- Add MiniMax API endpoint and key handling in OpenAIClient
- Add MiniMax model validation in validators
- Add MiniMax models to CLI quick/deep thinking selection
- Add MiniMax to provider selection in CLI
- Update .env.example with MINIMAX_API_KEY
- Update README with MiniMax documentation

.env.example

@@ -3,4 +3,5 @@ OPENAI_API_KEY=
 GOOGLE_API_KEY=
 ANTHROPIC_API_KEY=
 XAI_API_KEY=
+MINIMAX_API_KEY=
 OPENROUTER_API_KEY=

README.md

@@ -28,7 +28,7 @@
 # TradingAgents: Multi-Agents LLM Financial Trading Framework
 
 ## News
-- [2026-02] **TradingAgents v0.2.0** released with multi-provider LLM support (GPT-5.x, Gemini 3.x, Claude 4.x, Grok 4.x) and improved system architecture.
+- [2026-02] **TradingAgents v0.2.0** released with multi-provider LLM support (GPT-5.x, Gemini 3.x, Claude 4.x, Grok 4.x, MiniMax-M2.5) and improved system architecture.
 - [2026-01] **Trading-R1** [Technical Report](https://arxiv.org/abs/2509.11420) released, with [Terminal](https://github.com/TauricResearch/Trading-R1) expected to land soon.
 
 <div align="center">
@@ -125,6 +125,7 @@ export OPENAI_API_KEY=...          # OpenAI (GPT)
 export GOOGLE_API_KEY=...          # Google (Gemini)
 export ANTHROPIC_API_KEY=...       # Anthropic (Claude)
 export XAI_API_KEY=...             # xAI (Grok)
+export MINIMAX_API_KEY=...         # MiniMax
 export OPENROUTER_API_KEY=...      # OpenRouter
 export ALPHA_VANTAGE_API_KEY=...   # Alpha Vantage
 ```
@@ -162,7 +163,7 @@ An interface will appear showing results as they load, letting you track the age
 
 ### Implementation Details
 
-We built TradingAgents with LangGraph to ensure flexibility and modularity. The framework supports multiple LLM providers: OpenAI, Google, Anthropic, xAI, OpenRouter, and Ollama.
+We built TradingAgents with LangGraph to ensure flexibility and modularity. The framework supports multiple LLM providers: OpenAI, Google, Anthropic, xAI, MiniMax, OpenRouter, and Ollama.
 
 ### Python Usage
 
@@ -186,7 +187,7 @@ from tradingagents.graph.trading_graph import TradingAgentsGraph
 from tradingagents.default_config import DEFAULT_CONFIG
 
 config = DEFAULT_CONFIG.copy()
-config["llm_provider"] = "openai"        # openai, google, anthropic, xai, openrouter, ollama
+config["llm_provider"] = "openai"        # openai, google, anthropic, xai, minimax, openrouter, ollama
 config["deep_think_llm"] = "gpt-5.2"     # Model for complex reasoning
 config["quick_think_llm"] = "gpt-5-mini" # Model for quick tasks
 config["max_debate_rounds"] = 2

cli/utils.py

@@ -151,6 +151,10 @@ def select_shallow_thinking_agent(provider) -> str:
             ("Grok 4.1 Fast (Reasoning) - High-performance, 2M ctx", "grok-4-1-fast-reasoning"),
             ("Grok 4 Fast (Reasoning) - High-performance", "grok-4-fast-reasoning"),
         ],
+        "minimax": [
+            ("MiniMax-M2.5-highspeed - Ultra-fast, 204K context", "MiniMax-M2.5-highspeed"),
+            ("MiniMax-M2.5 - Flagship, 204K context", "MiniMax-M2.5"),
+        ],
         "openrouter": [
             ("NVIDIA Nemotron 3 Nano 30B (free)", "nvidia/nemotron-3-nano-30b-a3b:free"),
             ("Z.AI GLM 4.5 Air (free)", "z-ai/glm-4.5-air:free"),
@@ -219,6 +223,10 @@ def select_deep_thinking_agent(provider) -> str:
             ("Grok 4.1 Fast (Non-Reasoning) - Speed optimized, 2M ctx", "grok-4-1-fast-non-reasoning"),
             ("Grok 4 Fast (Non-Reasoning) - Speed optimized", "grok-4-fast-non-reasoning"),
         ],
+        "minimax": [
+            ("MiniMax-M2.5 - Flagship, 204K context", "MiniMax-M2.5"),
+            ("MiniMax-M2.5-highspeed - Ultra-fast, 204K context", "MiniMax-M2.5-highspeed"),
+        ],
         "openrouter": [
             ("Z.AI GLM 4.5 Air (free)", "z-ai/glm-4.5-air:free"),
             ("NVIDIA Nemotron 3 Nano 30B (free)", "nvidia/nemotron-3-nano-30b-a3b:free"),
@@ -260,6 +268,7 @@ def select_llm_provider() -> tuple[str, str]:
         ("Google", "https://generativelanguage.googleapis.com/v1"),
         ("Anthropic", "https://api.anthropic.com/"),
         ("xAI", "https://api.x.ai/v1"),
+        ("MiniMax", "https://api.minimax.io/v1"),
         ("Openrouter", "https://openrouter.ai/api/v1"),
         ("Ollama", "http://localhost:11434/v1"),
     ]

tradingagents/llm_clients/factory.py

@@ -15,7 +15,7 @@ def create_llm_client(
     """Create an LLM client for the specified provider.
 
     Args:
-        provider: LLM provider (openai, anthropic, google, xai, ollama, openrouter)
+        provider: LLM provider (openai, anthropic, google, xai, minimax, ollama, openrouter)
         model: Model name/identifier
         base_url: Optional base URL for API endpoint
         **kwargs: Additional provider-specific arguments
@@ -34,6 +34,9 @@ def create_llm_client(
     if provider_lower == "xai":
         return OpenAIClient(model, base_url, provider="xai", **kwargs)
 
+    if provider_lower == "minimax":
+        return OpenAIClient(model, base_url, provider="minimax", **kwargs)
+
     if provider_lower == "anthropic":
         return AnthropicClient(model, base_url, **kwargs)
 

tradingagents/llm_clients/openai_client.py

@@ -29,7 +29,7 @@ class UnifiedChatOpenAI(ChatOpenAI):
 
 
 class OpenAIClient(BaseLLMClient):
-    """Client for OpenAI, Ollama, OpenRouter, and xAI providers."""
+    """Client for OpenAI, Ollama, OpenRouter, xAI, and MiniMax providers."""
 
     def __init__(
         self,
@@ -55,6 +55,11 @@ class OpenAIClient(BaseLLMClient):
             api_key = os.environ.get("OPENROUTER_API_KEY")
             if api_key:
                 llm_kwargs["api_key"] = api_key
+        elif self.provider == "minimax":
+            llm_kwargs["base_url"] = "https://api.minimax.io/v1"
+            api_key = os.environ.get("MINIMAX_API_KEY")
+            if api_key:
+                llm_kwargs["api_key"] = api_key
         elif self.provider == "ollama":
             llm_kwargs["base_url"] = "http://localhost:11434/v1"
             llm_kwargs["api_key"] = "ollama"  # Ollama doesn't require auth

tradingagents/llm_clients/validators.py

@@ -63,6 +63,11 @@ VALID_MODELS = {
         "grok-4-fast-reasoning",
         "grok-4-fast-non-reasoning",
     ],
+    "minimax": [
+        # MiniMax M2.5 series (204K context, OpenAI-compatible)
+        "MiniMax-M2.5",
+        "MiniMax-M2.5-highspeed",
+    ],
 }