feat: add MiniMax as a supported LLM provider

MiniMax provides an OpenAI-compatible API, making integration
straightforward. This adds:

- MiniMax model wrapper class (OpenAI-compatible)
- Model token mappings for MiniMax-M1, M2, and M2.5 models
- Provider routing in abstract_graph factory
- README update listing MiniMax as a supported provider

README.md

@@ -150,7 +150,7 @@ There are other pipelines that can be used to extract information from multiple
 
 For each of these graphs there is the multi version. It allows to make calls of the LLM in parallel.
 
-It is possible to use different LLM through APIs, such as **OpenAI**, **Groq**, **Azure** and **Gemini**, or local models using **Ollama**.
+It is possible to use different LLM through APIs, such as **OpenAI**, **Groq**, **Azure**, **Gemini**, **MiniMax** and more, or local models using **Ollama**.
 
 Remember to have [Ollama](https://ollama.com/) installed and download the models using the **ollama pull** command, if you want to use local models.
 

scrapegraphai/graphs/abstract_graph.py

@@ -13,7 +13,7 @@ from langchain_core.rate_limiters import InMemoryRateLimiter
 from pydantic import BaseModel
 
 from ..helpers import models_tokens
-from ..models import XAI, CLoD, DeepSeek, Nvidia, OneApi
+from ..models import XAI, CLoD, DeepSeek, MiniMax, Nvidia, OneApi
 from ..utils.logging import get_logger, set_verbosity_info, set_verbosity_warning
 
 logger = get_logger(__name__)
@@ -171,6 +171,7 @@ class AbstractGraph(ABC):
             "clod",
             "togetherai",
             "xai",
+            "minimax",
         }
 
         if "/" in llm_params["model"]:
@@ -226,6 +227,7 @@ class AbstractGraph(ABC):
                 "togetherai",
                 "clod",
                 "xai",
+                "minimax",
             }:
                 if llm_params["model_provider"] == "bedrock":
                     llm_params["model_kwargs"] = {
@@ -243,6 +245,9 @@ class AbstractGraph(ABC):
                 if model_provider == "deepseek":
                     return DeepSeek(**llm_params)
 
+                if model_provider == "minimax":
+                    return MiniMax(**llm_params)
+
                 if model_provider == "ernie":
                     from langchain_community.chat_models import ErnieBotChat
 

scrapegraphai/helpers/models_tokens.py

@@ -377,4 +377,11 @@ models_tokens = {
         "grok-3-mini": 1000000,
         "grok-beta": 128000,
     },
+    "minimax": {
+        "MiniMax-M1": 1000000,
+        "MiniMax-M1-40k": 40000,
+        "MiniMax-M2": 204000,
+        "MiniMax-M2.5": 204000,
+        "MiniMax-M2.5-highspeed": 204000,
+    },
 }

scrapegraphai/models/__init__.py

@@ -4,10 +4,11 @@ This module contains the model definitions used in the ScrapeGraphAI application
 
 from .clod import CLoD
 from .deepseek import DeepSeek
+from .minimax import MiniMax
 from .nvidia import Nvidia
 from .oneapi import OneApi
 from .openai_itt import OpenAIImageToText
 from .openai_tts import OpenAITextToSpeech
 from .xai import XAI
 
-__all__ = ["DeepSeek", "OneApi", "OpenAIImageToText", "OpenAITextToSpeech", "CLoD", "XAI", "Nvidia"]
+__all__ = ["DeepSeek", "MiniMax", "OneApi", "OpenAIImageToText", "OpenAITextToSpeech", "CLoD", "XAI", "Nvidia"]

scrapegraphai/models/minimax.py

@@ -0,0 +1,23 @@
+"""
+MiniMax Module
+"""
+
+from langchain_openai import ChatOpenAI
+
+
+class MiniMax(ChatOpenAI):
+    """
+    A wrapper for the ChatOpenAI class (MiniMax uses an OpenAI-compatible API) that
+    provides default configuration and could be extended with additional methods
+    if needed.
+
+    Args:
+        llm_config (dict): Configuration parameters for the language model.
+    """
+
+    def __init__(self, **llm_config):
+        if "api_key" in llm_config:
+            llm_config["openai_api_key"] = llm_config.pop("api_key")
+        llm_config["openai_api_base"] = "https://api.minimax.io/v1"
+
+        super().__init__(**llm_config)