diff --git a/config/config2.yaml.example b/config/config2.yaml.example
index 8f4a33fc1..ff9429917 100644
--- a/config/config2.yaml.example
+++ b/config/config2.yaml.example
@@ -3,6 +3,13 @@ llm:
   base_url: "YOUR_BASE_URL"
   api_key: "YOUR_API_KEY"
   model: "gpt-4-turbo-preview"  # or gpt-3.5-turbo-1106 / gpt-4-1106-preview
+  # Azure-exclusive pricing plan mappings：
+  # - gpt-3.5-turbo 4k: "gpt-3.5-turbo"
+  # - gpt-4-turbo: "gpt-4-1106-preview"
+  # - gpt-4-turbo-vision: "gpt-4-1106-preview"
+  # - gpt-4 8k: "gpt-4"
+  # See for more: https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/
+  # pricing_plan: "gpt-4-turbo-preview"
 
 proxy: "YOUR_PROXY"
 
diff --git a/metagpt/utils/token_counter.py b/metagpt/utils/token_counter.py
index 6fddf2964..44024248b 100644
--- a/metagpt/utils/token_counter.py
+++ b/metagpt/utils/token_counter.py
@@ -35,10 +35,6 @@ TOKEN_COSTS = {
     "glm-3-turbo": {"prompt": 0.0, "completion": 0.0007},  # 128k version, prompt + completion tokens=0.005￥/k-tokens
     "glm-4": {"prompt": 0.0, "completion": 0.014},  # 128k version, prompt + completion tokens=0.1￥/k-tokens
     "gemini-pro": {"prompt": 0.00025, "completion": 0.0005},
-    "gpt-3.5-turbo-4k": {"prompt": 0.0015, "completion": 0.002},
-    "gpt-4-turbo": {"prompt": 0.01, "completion": 0.03},
-    "gpt-4-turbo-vision": {"prompt": 0.01, "completion": 0.03},
-    "gpt-4-8k": {"prompt": 0.03, "completion": 0.06},
 }
 
 TOKEN_MAX = {