feat: new model

backend/utils/constants.py

@@ -83,6 +83,14 @@ MODELS = {
             "output_cost_per_million_tokens": 60.00
         },
         "tier_availability": ["paid"]
+    },
+      "openai/gpt-5": {
+        "aliases": ["gpt-5"],
+        "pricing": {
+            "input_cost_per_million_tokens": 1.25,
+            "output_cost_per_million_tokens": 10.00
+        },
+        "tier_availability": ["paid"]
     },
     "openai/gpt-4.1-mini": {
         "aliases": ["gpt-4.1-mini"],

frontend/src/components/thread/chat-input/_use-model-selection.ts

@@ -78,7 +78,7 @@ export const MODELS = {
   },
   'gpt-4.1': { 
     tier: 'premium', 
-    priority: 96,
+    priority: 92,
     recommended: false,
     lowQuality: false
   },
@@ -94,6 +94,12 @@ export const MODELS = {
     recommended: false,
     lowQuality: false
   },
+  'gpt-5': { 
+    tier: 'premium', 
+    priority: 99,
+    recommended: false,
+    lowQuality: false
+  },
   'gemini-2.5-flash:thinking': { 
     tier: 'premium', 
     priority: 84,