feat: add MiniMax provider support with M2.7 default

README.md

@@ -193,6 +193,32 @@ interpreter.llm.model = "gpt-3.5-turbo"
 
 [Find the appropriate "model" string for your language model here.](https://docs.litellm.ai/docs/providers/)
 
+### Using MiniMax
+
+To use [MiniMax](https://platform.minimax.io/) models, set your API key and use the built-in profile:
+
+```shell
+export MINIMAX_API_KEY=your_api_key
+interpreter --profile minimax.py
+```
+
+Or configure it in Python:
+
+```python
+from interpreter import interpreter
+
+interpreter.llm.model = "openai/MiniMax-M2.7"
+interpreter.llm.api_key = "your_api_key"
+interpreter.llm.api_base = "https://api.minimax.io/v1"
+interpreter.llm.context_window = 204800
+interpreter.llm.max_tokens = 4096
+interpreter.llm.temperature = 1.0
+
+interpreter.chat()
+```
+
+Available models: `MiniMax-M2.7` (default), `MiniMax-M2.7-highspeed` (faster), `MiniMax-M2.5`, and `MiniMax-M2.5-highspeed`.
+
 ### Running Open Interpreter locally
 
 #### Terminal

interpreter/terminal_interface/profiles/defaults/minimax.py

@@ -0,0 +1,34 @@
+"""
+This is an Open Interpreter profile to use MiniMax.
+
+Please set the MINIMAX_API_KEY environment variable.
+
+MiniMax provides powerful language models with a 204,800 token context window.
+Available models:
+  - MiniMax-M2.7 (default): Latest flagship model with enhanced reasoning and coding.
+  - MiniMax-M2.7-highspeed: High-speed version of M2.7 for low-latency scenarios.
+  - MiniMax-M2.5: Peak Performance. Ultimate Value.
+  - MiniMax-M2.5-highspeed: Same performance, faster and more agile.
+
+See https://platform.minimax.io/docs/api-reference/text-openai-api for more information.
+"""
+
+from interpreter import interpreter
+import os
+
+# LLM settings
+interpreter.llm.model = "openai/MiniMax-M2.7"
+interpreter.llm.api_key = os.environ.get("MINIMAX_API_KEY")
+interpreter.llm.api_base = "https://api.minimax.io/v1"
+interpreter.llm.supports_functions = True
+interpreter.llm.supports_vision = False
+interpreter.llm.max_tokens = 4096
+interpreter.llm.context_window = 204800
+interpreter.llm.temperature = 1.0
+
+# Computer settings
+interpreter.computer.import_computer_api = True
+
+# Misc settings
+interpreter.offline = False
+interpreter.auto_run = False