chore: replace old models

api-reference/authentication.mdx

@@ -34,7 +34,7 @@ will also fail.
   -H 'Authorization: Bearer <token>' \
   -H 'Content-Type: application/json' \
   -d '{
-    "model": "openai/gpt-4o",
+    "model": "openai/gpt-5.2",
     "messages": [{"role": "user", "content": "Hello"}]
   }'
   ```
@@ -44,7 +44,7 @@ will also fail.
   -u '<token>:' \
   -H 'Content-Type: application/json' \
   -d '{
-    "model": "openai/gpt-4o",
+    "model": "openai/gpt-5.2",
     "messages": [{"role": "user", "content": "Hello"}]
   }'
   # The colon prevents curl from asking for a password.

api-reference/errors.mdx

@@ -83,7 +83,7 @@ Below is a summary of the HTTP status codes that Edgee API uses.
 {
   "error": {
     "code": "provider_not_supported",
-    "message": "Provider 'anthropic' is not supported for model 'openai/gpt-4o'"
+    "message": "Provider 'anthropic' is not supported for model 'openai/gpt-5.2'"
   }
 }
 ```
@@ -162,7 +162,7 @@ Below is a summary of the HTTP status codes that Edgee API uses.
 {
   "error": {
     "code": "forbidden",
-    "message": "Model 'openai/gpt-4o' is not allowed for this API key"
+    "message": "Model 'openai/gpt-5.2' is not allowed for this API key"
   }
 }
 ```

api-reference/messages.mdx

@@ -49,7 +49,7 @@ See the [Authentication](/api-reference/authentication) page for more details.
 <ParamField body="model" type="string" required>
   The model ID to use. Use Anthropic model names without provider prefix.
 
-  Examples: `claude-sonnet-4.5`, `claude-opus-4`, `claude-haiku-4`
+  Examples: `claude-sonnet-4-6`, `claude-opus-4-6`, `claude-haiku-4-5`
 </ParamField>
 
 <ParamField body="max_tokens" type="integer" required>

api-reference/openapi.json

@@ -76,7 +76,7 @@
                   "id": "chatcmpl-123",
                   "object": "chat.completion",
                   "created": 1677652288,
-                  "model": "openai/gpt-4o",
+                  "model": "openai/gpt-5.2",
                   "choices": [
                     {
                       "index": 0,
@@ -114,13 +114,13 @@
                 },
                 "examples": {
                   "contentChunk": {
-                    "value": "data: {\"id\":\"chatcmpl-123\",\"object\":\"chat.completion.chunk\",\"created\":1677652288,\"model\":\"openai/gpt-4o\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"Hello\"},\"finish_reason\":null}]}\n\n"
+                    "value": "data: {\"id\":\"chatcmpl-123\",\"object\":\"chat.completion.chunk\",\"created\":1677652288,\"model\":\"openai/gpt-5.2\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"Hello\"},\"finish_reason\":null}]}\n\n"
                   },
                   "roleChunk": {
-                    "value": "data: {\"id\":\"chatcmpl-123\",\"object\":\"chat.completion.chunk\",\"created\":1677652288,\"model\":\"openai/gpt-4o\",\"choices\":[{\"index\":0,\"delta\":{\"role\":\"assistant\"},\"finish_reason\":null}]}\n\n"
+                    "value": "data: {\"id\":\"chatcmpl-123\",\"object\":\"chat.completion.chunk\",\"created\":1677652288,\"model\":\"openai/gpt-5.2\",\"choices\":[{\"index\":0,\"delta\":{\"role\":\"assistant\"},\"finish_reason\":null}]}\n\n"
                   },
                   "finalChunk": {
-                    "value": "data: {\"id\":\"chatcmpl-123\",\"object\":\"chat.completion.chunk\",\"created\":1677652288,\"model\":\"openai/gpt-4o\",\"choices\":[{\"index\":0,\"delta\":{},\"finish_reason\":\"stop\"}],\"usage\":{\"prompt_tokens\":10,\"completion_tokens\":10,\"total_tokens\":20,\"input_tokens_details\":{\"cached_tokens\":0},\"output_tokens_details\":{\"reasoning_tokens\":0}}}\n\n"
+                    "value": "data: {\"id\":\"chatcmpl-123\",\"object\":\"chat.completion.chunk\",\"created\":1677652288,\"model\":\"openai/gpt-5.2\",\"choices\":[{\"index\":0,\"delta\":{},\"finish_reason\":\"stop\"}],\"usage\":{\"prompt_tokens\":10,\"completion_tokens\":10,\"total_tokens\":20,\"input_tokens_details\":{\"cached_tokens\":0},\"output_tokens_details\":{\"reasoning_tokens\":0}}}\n\n"
                   }
                 }
               }
@@ -154,7 +154,7 @@
                     "value": {
                       "error": {
                         "code": "provider_not_supported",
-                        "message": "Provider 'anthropic' is not supported for model 'openai/gpt-4o'"
+                        "message": "Provider 'anthropic' is not supported for model 'openai/gpt-5.2'"
                       }
                     }
                   }
@@ -206,7 +206,7 @@
                     "value": {
                       "error": {
                         "code": "forbidden",
-                        "message": "Model 'openai/gpt-4o' is not allowed for this API key"
+                        "message": "Model 'openai/gpt-5.2' is not allowed for this API key"
                       }
                     }
                   }
@@ -351,13 +351,13 @@
                   "object": "list",
                   "data": [
                     {
-                      "id": "openai/gpt-4o",
+                      "id": "openai/gpt-5.2",
                       "object": "model",
                       "created": 1677610602,
                       "owned_by": "openai"
                     },
                     {
-                      "id": "anthropic/claude-3-opus",
+                      "id": "anthropic/claude-opus-4-6",
                       "object": "model",
                       "created": 1677610602,
                       "owned_by": "anthropic"
@@ -492,7 +492,7 @@
           "model": {
             "type": "string",
             "description": "Optional model hint to improve tokenizer selection. When provided, the gateway uses this to choose the most appropriate tokenizer for the target model.",
-            "example": "openai/gpt-4o"
+            "example": "openai/gpt-5.2"
           }
         }
       },
@@ -519,8 +519,8 @@
         "properties": {
           "model": {
             "type": "string",
-            "description": "ID of the model to use. Format: `{author_id}/{model_id}` (e.g. `openai/gpt-4o`)",
-            "example": "openai/gpt-4o"
+            "description": "ID of the model to use. Format: `{author_id}/{model_id}` (e.g. `openai/gpt-5.2`)",
+            "example": "openai/gpt-5.2"
           },
           "messages": {
             "type": "array",
@@ -782,7 +782,7 @@
           "model": {
             "type": "string",
             "description": "The model used for the chat completion.",
-            "example": "openai/gpt-4o"
+            "example": "openai/gpt-5.2"
           },
           "choices": {
             "type": "array",
@@ -917,7 +917,7 @@
           "id": {
             "type": "string",
             "description": "The model identifier, which can be referenced in the API. Format: `{author_id}/{model_id}`.",
-            "example": "openai/gpt-4o"
+            "example": "openai/gpt-5.2"
           },
           "object": {
             "type": "string",
@@ -969,7 +969,7 @@
           "model": {
             "type": "string",
             "description": "The model used for the chat completion.",
-            "example": "openai/gpt-4o"
+            "example": "openai/gpt-5.2"
           },
           "choices": {
             "type": "array",

features/automatic-model-selection.mdx

@@ -57,7 +57,7 @@ const response = await edgee.send({
   max_latency_ms: 2000, // Must respond in under 2s
 });
 
-console.log(`Model used: ${response.model}`); // e.g., "gpt-4o"
+console.log(`Model used: ${response.model}`); // e.g., "gpt-5.2"
 console.log(`Latency: ${response.latency_ms}ms`);
 ```
 
@@ -93,12 +93,12 @@ When a provider fails, Edgee automatically retries with backup models:
 
 ```typescript
 const response = await edgee.send({
-  model: 'gpt-4o',
-  fallback_models: ['claude-3.5-sonnet', 'gemini-pro'], // Backup chain
+  model: 'gpt-5.2',
+  fallback_models: ['claude-sonnet-4-6', 'gemini-pro'], // Backup chain
   input: 'Your prompt here',
 });
 
-// If GPT-4o is unavailable, Edgee tries Claude 3.5, then Gemini
+// If GPT-5.2 is unavailable, Edgee tries Claude 3.5, then Gemini
 console.log(`Model used: ${response.model}`);
 console.log(`Fallback used: ${response.fallback_used}`); // true/false
 ```
@@ -138,15 +138,15 @@ Configure default routing strategies per use case:
 await edgee.routing.configure({
   name: 'rag-qa',
   strategy: 'cost',
-  allowed_models: ['gpt-5.2', 'gpt-5.1', 'claude-3.5-sonnet'],
+  allowed_models: ['gpt-5.2', 'gpt-5.1', 'claude-sonnet-4-6'],
   quality_threshold: 0.9,
 });
 
 // Code generation: Optimize for performance
 await edgee.routing.configure({
   name: 'code-gen',
   strategy: 'performance',
-  allowed_models: ['gpt-4o', 'claude-3.5-sonnet'],
+  allowed_models: ['gpt-5.2', 'claude-sonnet-4-6'],
   quality_threshold: 0.95,
 });
 
@@ -169,7 +169,7 @@ await edgee.routing.addRule({
     token_count: { gt: 10000 }, // Requests over 10k tokens
   },
   action: {
-    models: ['claude-3.5-sonnet'], // Use Claude for long contexts
+    models: ['claude-sonnet-4-6'], // Use Claude for long contexts
     strategy: 'cost',
   },
 });
@@ -180,7 +180,7 @@ await edgee.routing.addRule({
     metadata: { priority: 'high' }, // High-priority requests
   },
   action: {
-    models: ['gpt-4o', 'claude-opus'], // Use premium models
+    models: ['gpt-5.2', 'claude-opus'], // Use premium models
     strategy: 'performance',
   },
 });

features/observability.mdx

@@ -12,7 +12,7 @@ Every Edgee response includes detailed token usage information for tracking and
 
 ```typescript
 const response = await edgee.send({
-  model: 'gpt-4o',
+  model: 'gpt-5.2',
   input: 'Your prompt here',
 });
 
@@ -29,7 +29,7 @@ if (response.compression) {
 ```
 
 **Track usage by:**
-- Model (GPT-4o vs Claude vs Gemini)
+- Model (GPT-5.2 vs Claude vs Gemini)
 - Project or application
 - Environment (production vs staging)
 - User or tenant (for multi-tenant apps)
@@ -53,7 +53,7 @@ Tags allow you to categorize and label requests for filtering and grouping in yo
     const edgee = new Edgee("your-api-key");
 
     const response = await edgee.send({
-      model: 'gpt-4o',
+      model: 'gpt-5.2',
       input: {
         messages: [{ role: 'user', content: 'Hello!' }],
         tags: ['production', 'chat-feature', 'user-123', 'team-backend']
@@ -69,7 +69,7 @@ Tags allow you to categorize and label requests for filtering and grouping in yo
     edgee = Edgee("your-api-key")
 
     response = edgee.send(
-        model="gpt-4o",
+        model="gpt-5.2",
         input=InputObject(
             messages=[Message(role="user", content="Hello!")],
             tags=["production", "chat-feature", "user-123", "team-backend"]
@@ -84,7 +84,7 @@ Tags allow you to categorize and label requests for filtering and grouping in yo
 
     client, _ := edgee.NewClient("your-api-key")
 
-    response, err := client.Send("gpt-4o", edgee.InputObject{
+    response, err := client.Send("gpt-5.2", edgee.InputObject{
         Messages: []edgee.Message{
             {Role: "user", Content: "Hello!"},
         },
@@ -107,7 +107,7 @@ Tags allow you to categorize and label requests for filtering and grouping in yo
             "team-backend".to_string(),
         ]);
 
-    let response = client.send("gpt-4o", input).await?;
+    let response = client.send("gpt-5.2", input).await?;
     ```
   </Tab>
 </Tabs>
@@ -184,7 +184,7 @@ See exactly how much token compression is saving you on every request:
 
 ```typescript
 const response = await edgee.send({
-  model: 'gpt-4o',
+  model: 'gpt-5.2',
   input: 'Long prompt with lots of context...',
   enable_compression: true,
 });

features/token-compression.mdx

@@ -78,7 +78,7 @@ Enable compression for specific requests using the SDK:
   <Tab title="TypeScript">
     ```typescript
     const response = await edgee.send({
-      model: 'gpt-4o',
+      model: 'gpt-5.2',
       input: {
         "messages": [
           {"role": "user", "content": "Your prompt here"}
@@ -93,7 +93,7 @@ Enable compression for specific requests using the SDK:
   <Tab title="Python">
     ```python
     response = edgee.send(
-        model="gpt-4o",
+        model="gpt-5.2",
         input={
             "messages": [
                 {"role": "user", "content": "Your prompt here"}
@@ -107,7 +107,7 @@ Enable compression for specific requests using the SDK:
 
   <Tab title="Go">
     ```go
-    response, err := client.Send("gpt-4o", edgee.InputObject{
+    response, err := client.Send("gpt-5.2", edgee.InputObject{
         Messages: []edgee.Message{
             {Role: "user", Content: "Your prompt here"},
         },
@@ -123,7 +123,7 @@ Enable compression for specific requests using the SDK:
         .with_compression(true)
         .with_compression_rate(0.8); // Target ratio: compressed = 80% of original (optional)
 
-    let response = client.send("gpt-4o", input).await?;
+    let response = client.send("gpt-5.2", input).await?;
     ```
   </Tab>
 </Tabs>
@@ -215,7 +215,7 @@ const documents = [
 ];
 
 const response = await edgee.send({
-  model: 'gpt-4o',
+  model: 'gpt-5.2',
   input: `Answer the question based on these documents:\n\n${documents.join('\n\n')}\n\nQuestion: What is the main topic?`,
   enable_compression: true, // Enable compression for this request
   compression_rate: 0.8, // Target ratio (0-1): 0.8 = compressed is 80% of original
@@ -246,10 +246,10 @@ Here's what token compression means for your monthly AI bill:
 
 | Use Case | Monthly Requests | Without Edgee | With Edgee (50% compression) | **Monthly Savings** |
 |----------|-----------------|---------------|------------------------------|---------------------|
-| RAG Q&A (GPT-4o) | 100,000 @ 2,000 tokens | $3,000 | $1,500 | **$1,500** |
+| RAG Q&A (GPT-5.2) | 100,000 @ 2,000 tokens | $3,000 | $1,500 | **$1,500** |
 | Document Analysis (Claude 3.5) | 50,000 @ 4,000 tokens | $1,800 | $900 | **$900** |
 | Chatbot (GPT-4o-mini) | 500,000 @ 500 tokens | $375 | $188 | **$187** |
-| Multi-turn Agent (GPT-4o) | 200,000 @ 1,000 tokens | $3,000 | $1,500 | **$1,500** |
+| Multi-turn Agent (GPT-5.2) | 200,000 @ 1,000 tokens | $3,000 | $1,500 | **$1,500** |
 
 <Note>
   Savings calculations use list pricing for GPT-4o ($5/1M input tokens), Claude 3.5 Sonnet ($3/1M input tokens), and GPT-4o-mini ($0.15/1M input tokens). Actual compression ratios vary by use case.

integrations/anthropic-sdk.mdx

@@ -313,7 +313,7 @@ With Edgee, you can access models from multiple providers using the same Anthrop
 
     # Use GPT-4 through the same client
     gpt_response = client.messages.create(
-        model="gpt-4o",
+        model="gpt-5.2",
         max_tokens=1024,
         messages=[{"role": "user", "content": "Hello!"}]
     )
@@ -345,7 +345,7 @@ With Edgee, you can access models from multiple providers using the same Anthrop
 
     // Use GPT-4 through the same client
     const gptResponse = await client.messages.create({
-      model: 'gpt-4o',
+      model: 'gpt-5.2',
       max_tokens: 1024,
       messages: [{ role: 'user', content: 'Hello!' }]
     });

integrations/claude-code.mdx

@@ -82,7 +82,7 @@ When using Edgee with Claude Code, you can specify which Claude model to use thr
 claude --model claude-sonnet-4.5 "Explain this codebase"
 
 # Use different providers through Edgee
-claude --model gpt-4o "Refactor this function"
+claude --model gpt-5.2 "Refactor this function"
 ```
 
 ## Advanced Configuration

integrations/langchain.mdx

@@ -125,7 +125,7 @@ import os
 llm = ChatOpenAI(
     base_url="https://api.edgee.ai/v1",
     api_key=os.getenv("API_KEY"),
-    model="gpt-4o",
+    model="gpt-5.2",
     default_headers={
         "x-edgee-enable-compression": "true",
         "x-edgee-compression-rate": "0.8",  # Target 80% compression