chore: sync new models (#943)

Automated sync of model metadata and newly available models from the
approved provider allowlist.

---------

Co-authored-by: erin2722 <16248113+erin2722@users.noreply.github.com>
Co-authored-by: Erin McNulty <erin.mcnulty@braintrustdata.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

Author: 3 people

packages/proxy/schema/index.ts

@@ -200,6 +200,7 @@ export const DefaultEndpointTypes: {
 export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
   "gpt-5.6-sol": ["openai", "azure"],
   "gpt-5.6-terra": ["openai", "azure"],
+  "gpt-5.6": ["openai", "azure"],
   "gpt-5.6-luna": ["openai", "azure"],
   "gpt-5.5-2026-04-23": ["openai", "azure"],
   "gpt-5.5-pro-2026-04-23": ["openai", "azure"],

packages/proxy/schema/model_list.json

@@ -1,30 +1,31 @@
 {
-  "gpt-5.6-sol": {
+  "gpt-5.6": {
     "format": "openai",
     "flavor": "chat",
     "multimodal": true,
     "input_cost_per_mil_tokens": 5,
     "output_cost_per_mil_tokens": 30,
-    "input_cache_read_cost_per_mil_tokens": 4.5,
+    "input_cache_read_cost_per_mil_tokens": 0.5,
     "input_cache_write_cost_per_mil_tokens": 6.25,
-    "displayName": "GPT-5.6 Sol",
+    "displayName": "GPT-5.6",
     "reasoning": true,
+    "parent": "gpt-5.6-sol",
     "max_input_tokens": 1050000,
     "max_output_tokens": 128000,
     "available_providers": [
       "openai",
       "azure"
     ]
   },
-  "gpt-5.6-terra": {
+  "gpt-5.6-luna": {
     "format": "openai",
     "flavor": "chat",
     "multimodal": true,
-    "input_cost_per_mil_tokens": 2.5,
-    "output_cost_per_mil_tokens": 15,
-    "input_cache_read_cost_per_mil_tokens": 2.25,
-    "input_cache_write_cost_per_mil_tokens": 3.125,
-    "displayName": "GPT-5.6 Terra",
+    "input_cost_per_mil_tokens": 1,
+    "output_cost_per_mil_tokens": 6,
+    "input_cache_read_cost_per_mil_tokens": 0.1,
+    "input_cache_write_cost_per_mil_tokens": 1.25,
+    "displayName": "GPT-5.6 Luna",
     "reasoning": true,
     "max_input_tokens": 1050000,
     "max_output_tokens": 128000,
@@ -33,17 +34,34 @@
       "azure"
     ]
   },
-  "gpt-5.6-luna": {
+  "gpt-5.6-sol": {
     "format": "openai",
     "flavor": "chat",
     "multimodal": true,
-    "input_cost_per_mil_tokens": 1,
-    "output_cost_per_mil_tokens": 6,
-    "input_cache_read_cost_per_mil_tokens": 0.9,
-    "input_cache_write_cost_per_mil_tokens": 1.25,
-    "displayName": "GPT-5.6 Luna",
+    "input_cost_per_mil_tokens": 5,
+    "output_cost_per_mil_tokens": 30,
+    "input_cache_read_cost_per_mil_tokens": 0.5,
+    "input_cache_write_cost_per_mil_tokens": 6.25,
+    "displayName": "GPT-5.6 Sol",
     "reasoning": true,
-    "max_input_tokens": 400000,
+    "max_input_tokens": 1050000,
+    "max_output_tokens": 128000,
+    "available_providers": [
+      "openai",
+      "azure"
+    ]
+  },
+  "gpt-5.6-terra": {
+    "format": "openai",
+    "flavor": "chat",
+    "multimodal": true,
+    "input_cost_per_mil_tokens": 2.5,
+    "output_cost_per_mil_tokens": 15,
+    "input_cache_read_cost_per_mil_tokens": 0.25,
+    "input_cache_write_cost_per_mil_tokens": 3.125,
+    "displayName": "GPT-5.6 Terra",
+    "reasoning": true,
+    "max_input_tokens": 1050000,
     "max_output_tokens": 128000,
     "available_providers": [
       "openai",
@@ -1417,6 +1435,19 @@
       "together"
     ]
   },
+  "openai/gpt-oss-safeguard-20b": {
+    "format": "openai",
+    "flavor": "chat",
+    "input_cost_per_mil_tokens": 0.075,
+    "output_cost_per_mil_tokens": 0.3,
+    "displayName": "GPT-OSS Safeguard (20B)",
+    "experimental": true,
+    "max_input_tokens": 131072,
+    "max_output_tokens": 65536,
+    "available_providers": [
+      "groq"
+    ]
+  },
   "o4-mini-deep-research-2025-06-26": {
     "format": "openai",
     "flavor": "chat",
@@ -6644,9 +6675,10 @@
     "input_cost_per_mil_tokens": 2,
     "output_cost_per_mil_tokens": 6,
     "input_cache_read_cost_per_mil_tokens": 0.5,
-    "displayName": "Grok 4.5 (Latest)",
+    "displayName": "Grok 4.5",
     "reasoning": true,
     "max_input_tokens": 500000,
+    "max_output_tokens": 500000,
     "available_providers": [
       "xAI"
     ]
@@ -6658,9 +6690,11 @@
     "input_cost_per_mil_tokens": 2,
     "output_cost_per_mil_tokens": 6,
     "input_cache_read_cost_per_mil_tokens": 0.5,
-    "displayName": "Grok 4.5",
+    "displayName": "Grok 4.5 (Latest)",
     "reasoning": true,
+    "parent": "grok-4.5",
     "max_input_tokens": 500000,
+    "max_output_tokens": 500000,
     "available_providers": [
       "xAI"
     ]
@@ -11003,19 +11037,6 @@
       "azure"
     ]
   },
-  "openai/gpt-oss-safeguard-20b": {
-    "format": "openai",
-    "flavor": "chat",
-    "input_cost_per_mil_tokens": 0.075,
-    "output_cost_per_mil_tokens": 0.3,
-    "displayName": "GPT-OSS Safeguard (20B)",
-    "experimental": true,
-    "max_input_tokens": 131072,
-    "max_output_tokens": 65536,
-    "available_providers": [
-      "groq"
-    ]
-  },
   "sora-2": {
     "format": "openai",
     "flavor": "chat",