Update LLM model examples

Author: tomek-labuk

app/_data/plugins/ai-proxy.yaml

@@ -98,21 +98,21 @@ providers:
       streaming: true
       upstream_path: '/v1/messages'
       route_type: 'llm/v1/chat'
-      model_example: 'claude-3-opus-20240229'
+      model_example: 'claude-sonnet-4-20250514'
       min_version: '3.6'
     completions:
       supported: true
       streaming: false
       upstream_path: '/v1/complete'
       route_type: 'llm/v1/completions'
-      model_example: 'claude-2.1'
+      model_example: 'claude-sonnet-4-20250514'
       min_version: '3.6'
     function_calling:
       supported: true
       streaming: false
       upstream_path: '/v1/messages'
       route_type: 'llm/v1/chat'
-      model_example: 'claude-3-opus-20240229'
+      model_example: 'claude-sonnet-4-20250514'
       min_version: '3.6'
     batches:
       supported: true
@@ -143,30 +143,30 @@ providers:
       streaming: true
       upstream_path: '/openai/deployments/{deployment_name}/chat/completions'
       route_type: 'llm/v1/chat'
-      model_example: 'gpt-4'
+      model_example: 'gpt-4o'
       min_version: '3.6'
     completions:
       supported: true
       streaming: true
       upstream_path: '/openai/deployments/{deployment_name}/completions'
       route_type: 'llm/v1/completions'
-      model_example: 'gpt-3.5-turbo-instruct'
+      model_example: 'gpt-4o-mini'
       min_version: '3.6'
     embeddings:
       supported: true
       streaming: false
       upstream_path: '/openai/deployments/{deployment_name}/embeddings'
       route_type: 'llm/v1/embeddings'
-      model_example: 'text-embedding-ada-002<sup>1</sup>'
+      model_example: 'text-embedding-3-small'
       min_version: '3.11'
       note:
-        content: 'The `text-embedding-ada-002` model requires a fixed dimension of 1536. Use `text-embedding-3-small` for dynamic dimensions.'
+        content: 'Use `text-embedding-3-small` or `text-embedding-3-large` for dynamic dimensions.'
     function_calling:
       supported: true
       streaming: false
       upstream_path: '/openai/deployments/{deployment_name}/chat/completions'
       route_type: 'llm/v1/chat'
-      model_example: 'gpt-4'
+      model_example: 'gpt-4o'
       min_version: '3.6'
     files:
       supported: true
@@ -268,7 +268,7 @@ providers:
       streaming: true
       upstream_path: '/v1/chat/completions'
       route_type: 'llm/v1/chat'
-      model_example: 'llama3.1-8b'
+      model_example: 'llama-3.3-70b'
       min_version: '3.13'
     limitations:
       provider_specific: []
@@ -283,14 +283,14 @@ providers:
       streaming: true
       upstream_path: '/v1/chat'
       route_type: 'llm/v1/chat'
-      model_example: 'command'
+      model_example: 'command-a-03-2025'
       min_version: '3.6'
     completions:
       supported: true
       streaming: true
       upstream_path: '/v1/generate'
       route_type: 'llm/v1/completions'
-      model_example: 'command'
+      model_example: 'command-r-plus-08-2024'
       min_version: '3.6'
     embeddings:
       supported: true
@@ -304,7 +304,7 @@ providers:
       streaming: false
       upstream_path: '/v1/chat'
       route_type: 'llm/v1/chat'
-      model_example: 'command-r-plus'
+      model_example: 'command-a-03-2025'
       min_version: '3.6'
     native_formats:
       - llm_format: 'cohere'
@@ -362,7 +362,7 @@ providers:
       streaming: true
       upstream_path: 'Uses <code>generateContent</code> API'
       route_type: 'llm/v1/chat'
-      model_example: 'gemini-2.0-flash'
+      model_example: 'gemini-2.5-flash'
       min_version: '3.8'
     embeddings:
       supported: true
@@ -376,7 +376,7 @@ providers:
       streaming: false
       upstream_path: 'Uses <code>generateContent</code> API with function declarations'
       route_type: 'llm/v1/chat'
-      model_example: 'gemini-2.0-flash'
+      model_example: 'gemini-2.5-flash'
       min_version: '3.8'
     files:
       supported: true
@@ -402,21 +402,21 @@ providers:
         streaming: false
         upstream_path: 'Uses <code>generateContent</code> API'
         route_type: 'image/v1/images/generations'
-        model_example: 'gemini-2.0-flash-preview-image-generation<sup>1</sup>'
+        model_example: 'gemini-2.5-flash-preview-image-generation'
         min_version: '3.11'
       edits:
         supported: true
         streaming: false
         upstream_path: 'Uses <code>generateContent</code> API'
         route_type: 'image/v1/images/edits'
-        model_example: 'gemini-2.0-flash-preview-image-generation<sup>1</sup>'
+        model_example: 'gemini-2.5-flash-preview-image-generation'
         min_version: '3.11'
     realtime:
       supported: true
       streaming: true
       upstream_path: 'Uses <code>BidiGenerateContent</code> API'
       route_type: 'realtime/v1/realtime'
-      model_example: 'gemini-live-2.5-flash-preview-native-audio-09-2025'
+      model_example: 'gemini-2.5-flash-preview-native-audio'
       min_version: '3.13'
       note:
         content: 'Realtime processing for Gemini is supported in the native format from SDK only'
@@ -452,14 +452,14 @@ providers:
       streaming: true
       upstream_path: 'Uses <code>generateContent</code> API'
       route_type: 'llm/v1/chat'
-      model_example: 'gemini-2.0-flash'
+      model_example: 'gemini-2.5-flash'
       min_version: '3.8'
     completions:
       supported: true
       streaming: false
       upstream_path: 'Uses <code>generateContent</code> API'
       route_type: 'llm/v1/completions'
-      model_example: 'gemini-2.0-flash'
+      model_example: 'gemini-2.5-flash'
       min_version: '3.8'
     embeddings:
       supported: true
@@ -473,7 +473,7 @@ providers:
       streaming: false
       upstream_path: 'Uses <code>generateContent</code> API with function declarations'
       route_type: 'llm/v1/chat'
-      model_example: 'gemini-2.0-flash'
+      model_example: 'gemini-2.5-flash'
       min_version: '3.8'
     files:
       supported: true
@@ -497,14 +497,14 @@ providers:
         streaming: false
         upstream_path: 'Uses <code>generateContent</code> API'
         route_type: 'image/v1/images/generations'
-        model_example: 'gemini-2.0-flash-preview-image-generation<sup>1</sup>'
+        model_example: 'gemini-2.5-flash-preview-image-generation'
         min_version: '3.11'
       edits:
         supported: true
         streaming: false
         upstream_path: 'Uses <code>generateContent</code> API'
         route_type: 'image/v1/images/edits'
-        model_example: 'gemini-2.0-flash-preview-image-generation<sup>1</sup>'
+        model_example: 'gemini-2.5-flash-preview-image-generation'
         min_version: '3.11'
     video:
       generations:
@@ -606,7 +606,7 @@ providers:
       streaming: true
       upstream_path: '/v1/chat/completions or user-defined'
       route_type: 'llm/v1/chat'
-      model_example: 'mistral-tiny'
+      model_example: 'mistral-large-latest'
       min_version: '3.6'
     embeddings:
       supported: true
@@ -627,7 +627,7 @@ providers:
       statistics_logging: []
 
   - name: 'OpenAI'
-    formats: 'GPT-3.5, GPT-4, GPT-4o, and Multi-Modal'
+    formats: 'GPT-4o, GPT-4.1, and Multi-Modal'
     url_patterns:
       - 'https://api.openai.com:443/{route_type_path}'
     min_version: '3.6'
@@ -636,30 +636,30 @@ providers:
       streaming: true
       upstream_path: '/v1/chat/completions'
       route_type: 'llm/v1/chat'
-      model_example: 'gpt-4'
+      model_example: 'gpt-4o'
       min_version: '3.6'
     completions:
       supported: true
       streaming: true
       upstream_path: '/v1/completions'
       route_type: 'llm/v1/completions'
-      model_example: 'gpt-3.5-turbo-instruct'
+      model_example: 'gpt-4o-mini'
       min_version: '3.6'
     embeddings:
       supported: true
       streaming: false
       upstream_path: '/v1/embeddings'
       route_type: 'llm/v1/embeddings'
-      model_example: 'text-embedding-ada-002'
+      model_example: 'text-embedding-3-small'
       min_version: '3.11'
       note:
-        content: 'The `text-embedding-ada-002` model requires a fixed dimension of 1536. Use `text-embedding-3-small` for dynamic dimensions.'
+        content: 'Use `text-embedding-3-small` or `text-embedding-3-large` for dynamic dimensions.'
     function_calling:
       supported: true
       streaming: false
       upstream_path: '/v1/chat/completions'
       route_type: 'llm/v1/chat'
-      model_example: 'gpt-4'
+      model_example: 'gpt-4o'
       min_version: '3.6'
     files:
       supported: true
@@ -680,7 +680,7 @@ providers:
       streaming: false
       upstream_path: '/v1/assistants'
       route_type: 'llm/v1/assistants'
-      model_example: 'gpt-4-1106-preview'
+      model_example: 'gpt-4o'
       min_version: '3.11'
       note:
         content: 'Requires header <code>OpenAI-Beta: assistants=v2</code>'
@@ -689,7 +689,7 @@ providers:
       streaming: false
       upstream_path: '/v1/responses'
       route_type: 'llm/v1/responses'
-      model_example: 'gpt-4-1106-preview'
+      model_example: 'gpt-4o'
       min_version: '3.11'
     audio:
       speech:
@@ -733,7 +733,7 @@ providers:
       streaming: true
       upstream_path: '/v1/realtime'
       route_type: 'realtime/v1/realtime'
-      model_example: 'gpt-4o'
+      model_example: 'gpt-4o-realtime-preview'
       min_version: '3.11'
       note:
         content: 'For requests to OpenAI realtime API, include include the header `OpenAI-Beta: realtime=v1`.'
@@ -759,7 +759,7 @@ providers:
       streaming: false
       upstream_path: '/v1/chat/completions'
       route_type: 'llm/v1/chat'
-      model_example: 'grok-4'
+      model_example: 'grok-3'
       min_version: '3.13'
     completions:
       supported: false
@@ -772,7 +772,7 @@ providers:
       streaming: false
       upstream_path: '/v1/chat/completions'
       route_type: 'llm/v1/chat'
-      model_example: 'grok-2-latest'
+      model_example: 'grok-3'
       min_version: '3.13'
     files:
       supported: false
@@ -788,7 +788,7 @@ providers:
       streaming: false
       upstream_path: '/v1/responses'
       route_type: 'llm/v1/responses'
-      model_example: 'gpt-4'
+      model_example: 'grok-3'
       min_version: '3.13'
     audio:
       speech: