Add MiniMax-M2 model to NVIDIA provider

- Created minimax-m2.toml with proper configuration
- 128K context window, 16K output tokens
- Supports reasoning, tool calling, and temperature control
- Open weights model with MIT license
- Based on NVIDIA NIM documentation

Author: shariqriazz

providers/nvidia/models/minimaxai/minimax-m2.toml

@@ -0,0 +1,21 @@
+name = "MiniMax-M2"
+release_date = "2025-10-27"
+last_updated = "2025-10-31"
+attachment = false
+reasoning = true
+temperature = true
+knowledge = "2024-07"
+tool_call = true
+open_weights = true
+
+[cost]
+input = 0.0
+output = 0.0
+
+[limit]
+context = 128_000
+output = 16_384
+
+[modalities]
+input = ["text"]
+output = ["text"]