feat: add openai o1 & update pricing and max_token of other models (l…

…anggenius#11780)

Signed-off-by: -LAN- <laipz8200@outlook.com>

api/core/model_runtime/model_providers/openai/llm/_position.yaml

@@ -1,4 +1,7 @@
-- gpt-4o-audio-preview
+- o1
+- o1-2024-12-17
+- o1-mini
+- o1-mini-2024-09-12
 - gpt-4
 - gpt-4o
 - gpt-4o-2024-05-13
@@ -7,10 +10,6 @@
 - chatgpt-4o-latest
 - gpt-4o-mini
 - gpt-4o-mini-2024-07-18
-- o1-preview
-- o1-preview-2024-09-12
-- o1-mini
-- o1-mini-2024-09-12
 - gpt-4-turbo
 - gpt-4-turbo-2024-04-09
 - gpt-4-turbo-preview
@@ -25,4 +24,7 @@
 - gpt-3.5-turbo-1106
 - gpt-3.5-turbo-0613
 - gpt-3.5-turbo-instruct
+- gpt-4o-audio-preview
+- o1-preview
+- o1-preview-2024-09-12
 - text-davinci-003

api/core/model_runtime/model_providers/openai/llm/chatgpt-4o-latest.yaml

@@ -22,7 +22,7 @@ parameter_rules:
     use_template: frequency_penalty
   - name: max_tokens
     use_template: max_tokens
-    default: 512
+    default: 16384
     min: 1
     max: 16384
   - name: response_format

api/core/model_runtime/model_providers/openai/llm/gpt-4o-2024-05-13.yaml

@@ -22,9 +22,9 @@ parameter_rules:
     use_template: frequency_penalty
   - name: max_tokens
     use_template: max_tokens
-    default: 512
+    default: 16384
     min: 1
-    max: 4096
+    max: 16384
   - name: response_format
     label:
       zh_Hans: 回复格式

api/core/model_runtime/model_providers/openai/llm/gpt-4o-2024-08-06.yaml

@@ -22,7 +22,7 @@ parameter_rules:
     use_template: frequency_penalty
   - name: max_tokens
     use_template: max_tokens
-    default: 512
+    default: 16384
     min: 1
     max: 16384
   - name: response_format

api/core/model_runtime/model_providers/openai/llm/gpt-4o-2024-11-20.yaml

@@ -22,7 +22,7 @@ parameter_rules:
     use_template: frequency_penalty
   - name: max_tokens
     use_template: max_tokens
-    default: 512
+    default: 16384
     min: 1
     max: 16384
   - name: response_format

api/core/model_runtime/model_providers/openai/llm/gpt-4o-audio-preview.yaml

@@ -22,9 +22,9 @@ parameter_rules:
     use_template: frequency_penalty
   - name: max_tokens
     use_template: max_tokens
-    default: 512
+    default: 16384
     min: 1
-    max: 4096
+    max: 16384
   - name: response_format
     label:
       zh_Hans: 回复格式

api/core/model_runtime/model_providers/openai/llm/gpt-4o-mini-2024-07-18.yaml

@@ -22,7 +22,7 @@ parameter_rules:
     use_template: frequency_penalty
   - name: max_tokens
     use_template: max_tokens
-    default: 512
+    default: 16384
     min: 1
     max: 16384
   - name: response_format

api/core/model_runtime/model_providers/openai/llm/gpt-4o-mini.yaml

@@ -22,7 +22,7 @@ parameter_rules:
     use_template: frequency_penalty
   - name: max_tokens
     use_template: max_tokens
-    default: 512
+    default: 16384
     min: 1
     max: 16384
   - name: response_format

api/core/model_runtime/model_providers/openai/llm/gpt-4o.yaml

@@ -22,9 +22,9 @@ parameter_rules:
     use_template: frequency_penalty
   - name: max_tokens
     use_template: max_tokens
-    default: 512
+    default: 16384
     min: 1
-    max: 4096
+    max: 16384
   - name: response_format
     label:
       zh_Hans: 回复格式
@@ -38,7 +38,7 @@ parameter_rules:
       - text
       - json_object
 pricing:
-  input: '5.00'
-  output: '15.00'
+  input: '2.50'
+  output: '10.00'
   unit: '0.000001'
   currency: USD

api/core/model_runtime/model_providers/openai/llm/o1-2024-12-17.yaml

@@ -0,0 +1,35 @@
+model: o1-2024-12-17
+label:
+  en_US: o1-2024-12-17
+model_type: llm
+features:
+  - multi-tool-call
+  - agent-thought
+  - stream-tool-call
+  - vision
+model_properties:
+  mode: chat
+  context_size: 200000
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    default: 50000
+    min: 1
+    max: 50000
+  - 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
+pricing:
+  input: '15.00'
+  output: '60.00'
+  unit: '0.000001'
+  currency: USD

api/core/model_runtime/model_providers/openai/llm/o1.yaml

@@ -0,0 +1,36 @@
+model: o1
+label:
+  zh_Hans: o1
+  en_US: o1
+model_type: llm
+features:
+  - multi-tool-call
+  - agent-thought
+  - stream-tool-call
+  - vision
+model_properties:
+  mode: chat
+  context_size: 200000
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    default: 50000
+    min: 1
+    max: 50000
+  - 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
+pricing:
+  input: '15.00'
+  output: '60.00'
+  unit: '0.000001'
+  currency: USD