diff --git a/.env.example b/.env.example
index f424cda..c68ef76 100644
--- a/.env.example
+++ b/.env.example
@@ -27,3 +27,8 @@ export AZURE_OPENAI_API_KEY=
 # ── Qwen Local Model (for qwen_chat backend) ────────────────────────
 # export QWEN_CHAT_BASE_URL=http://localhost:8000/v1
 # export QWEN_CHAT_MODEL=Qwen/Qwen3.5-4B
+
+# ── MiniMax (for minimax_chat backend) ──────────────────────────────
+# export MINIMAX_BASE_URL=https://api.minimax.chat/v1
+# export MINIMAX_API_KEY=...
+# export MINIMAX_MODEL=MiniMax/MiniMax-Text-01
diff --git a/configs/_base_/default.yaml b/configs/_base_/default.yaml
index ed8f61d..8ac5985 100644
--- a/configs/_base_/default.yaml
+++ b/configs/_base_/default.yaml
@@ -44,6 +44,18 @@ model:
   target_azure_openai_ad_scope: "https://cognitiveservices.azure.com/.default"
   target_azure_openai_managed_identity_client_id: ""
 
+  # MiniMax backend settings (minimax_chat target)
+  minimax_base_url: ""          # https://api.minimax.chat/v1 if blank
+  minimax_api_key: ""
+  minimax_model: "MiniMax/MiniMax-Text-01"
+  minimax_temperature: "0.7"
+  minimax_max_tokens: "8000"
+  minimax_enable_thinking: "false"
+  optimizer_minimax_base_url: ""    # per-role override
+  target_minimax_base_url: ""       # per-role override
+  optimizer_minimax_api_key: ""
+  target_minimax_api_key: ""
+
 train:
   num_epochs: 4
   train_size: 0          # 0 = derive from dataset split when available