diff --git a/api/core/model_runtime/model_providers/openai/llm/_position.yaml b/api/core/model_runtime/model_providers/openai/llm/_position.yaml
index 0d3143c2ae..688d4dbd09 100644
--- a/api/core/model_runtime/model_providers/openai/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/openai/llm/_position.yaml
@@ -1,3 +1,4 @@
+- gpt-4.1
 - o1
 - o1-2024-12-17
 - o1-mini
diff --git a/api/core/model_runtime/model_providers/openai/llm/gpt-4-1.yaml b/api/core/model_runtime/model_providers/openai/llm/gpt-4-1.yaml
new file mode 100644
index 0000000000..f9f6edb4e6
--- /dev/null
+++ b/api/core/model_runtime/model_providers/openai/llm/gpt-4-1.yaml
@@ -0,0 +1,60 @@
+model: gpt-4.1
+label:
+  zh_Hans: gpt-4.1
+  en_US: gpt-4.1
+model_type: llm
+features:
+  - multi-tool-call
+  - agent-thought
+  - stream-tool-call
+  - vision
+model_properties:
+  mode: chat
+  context_size: 1047576
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: presence_penalty
+    use_template: presence_penalty
+  - name: frequency_penalty
+    use_template: frequency_penalty
+  - name: max_tokens
+    use_template: max_tokens
+    default: 512
+    min: 1
+    max: 32768
+  - name: reasoning_effort
+    label:
+      zh_Hans: 推理工作
+      en_US: Reasoning Effort
+    type: string
+    help:
+      zh_Hans: 限制推理模型的推理工作
+      en_US: Constrains effort on reasoning for reasoning models
+    required: false
+    options:
+      - low
+      - medium
+      - high
+  - name: response_format
+    label:
+      zh_Hans: 回复格式
+      en_US: Response Format
+    type: string
+    help:
+      zh_Hans: 指定模型必须输出的格式
+      en_US: specifying the format that the model must output
+    required: false
+    options:
+      - text
+      - json_object
+      - json_schema
+  - name: json_schema
+    use_template: json_schema
+pricing:
+  input: '2.00'
+  output: '8.00'
+  unit: '0.000001'
+  currency: USD
\ No newline at end of file
diff --git a/api/core/model_runtime/model_providers/openai/llm/llm.py b/api/core/model_runtime/model_providers/openai/llm/llm.py
index 37f7b33514..ab2580eb02 100644
--- a/api/core/model_runtime/model_providers/openai/llm/llm.py
+++ b/api/core/model_runtime/model_providers/openai/llm/llm.py
@@ -1049,6 +1049,9 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):
         """Calculate num tokens for gpt-3.5-turbo and gpt-4 with tiktoken package.
 
         Official documentation: https://github.com/openai/openai-cookbook/blob/main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb"""
+        if not messages and not tools:
+            return 0
+
         if model.startswith("ft:"):
             model = model.split(":")[1]
 
@@ -1058,17 +1061,17 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):
 
         try:
             encoding = tiktoken.get_encoding(model)
-        except KeyError:
+        except (KeyError, ValueError) as e:
             logger.warning("Warning: model not found. Using cl100k_base encoding.")
-            model = "cl100k_base"
-            encoding = tiktoken.get_encoding(model)
+            encoding_name = "cl100k_base"
+            encoding = tiktoken.get_encoding(encoding_name)
 
         if model.startswith("gpt-3.5-turbo-0301"):
             # every message follows <im_start>{role/name}\n{content}<im_end>\n
             tokens_per_message = 4
             # if there's a name, the role is omitted
             tokens_per_name = -1
-        elif model.startswith("gpt-3.5-turbo") or model.startswith("gpt-4") or model.startswith(("o1", "o3")):
+        elif model.startswith("gpt-3.5-turbo") or model.startswith("gpt-4") or model.startswith(("o1", "o3", "o4")):
             tokens_per_message = 3
             tokens_per_name = 1
         else: