Merge branch 'main' into 04-01-native_inference_billing

Author: knjiang

.github/workflows/enforce-pnpm.yml

@@ -0,0 +1,17 @@
+name: Enforce pnpm
+
+on:
+  pull_request:
+  push:
+
+jobs:
+  reject-npm-lockfile:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+      - name: Reject npm lockfiles
+        run: |
+          if git ls-files | grep -E '(^|/)package-lock\.json$'; then
+            echo "Remove package-lock.json and use pnpm."
+            exit 1
+          fi

.npmrc

@@ -1 +1,2 @@
 min-release-age=3
+engine-strict=true

package.json

@@ -7,13 +7,26 @@
     "packages/*"
   ],
   "scripts": {
+    "preinstall": "node -e \"const userAgent = process.env.npm_config_user_agent || ''; if (process.env.INIT_CWD === process.cwd() && !userAgent.includes('pnpm/')) { console.error('Use pnpm in this repo.'); process.exit(1); }\"",
     "build": "turbo run build",
     "dev": "turbo run dev",
     "start": "turbo run start",
     "lint": "turbo run lint",
     "clean": "turbo run clean",
     "test": "vitest run"
   },
+  "engines": {
+    "pnpm": ">=10.27.0",
+    "npm": "please-use-pnpm",
+    "yarn": "please-use-pnpm"
+  },
+  "devEngines": {
+    "packageManager": {
+      "name": "pnpm",
+      "version": ">=10.27.0",
+      "onFail": "error"
+    }
+  },
   "devDependencies": {
     "eslint": "^8.57.1",
     "eslint-config-turbo": "latest",

packages/proxy/schema/model_list.json

@@ -1492,7 +1492,8 @@
     "max_input_tokens": 131072,
     "max_output_tokens": 32766,
     "available_providers": [
-      "groq"
+      "groq",
+      "together"
     ]
   },
   "openai/gpt-oss-20b": {
@@ -1506,7 +1507,8 @@
     "max_input_tokens": 131072,
     "max_output_tokens": 32768,
     "available_providers": [
-      "groq"
+      "groq",
+      "together"
     ]
   },
   "accounts/fireworks/models/gpt-oss-120b": {
@@ -2924,6 +2926,7 @@
     "max_input_tokens": 1048576,
     "max_output_tokens": 65536,
     "available_providers": [
+      "google",
       "vertex"
     ]
   },
@@ -2940,6 +2943,7 @@
     "max_input_tokens": 1048576,
     "max_output_tokens": 65536,
     "available_providers": [
+      "google",
       "vertex"
     ]
   },
@@ -2956,6 +2960,7 @@
     "max_input_tokens": 1048576,
     "max_output_tokens": 65536,
     "available_providers": [
+      "google",
       "vertex"
     ]
   },
@@ -2969,10 +2974,11 @@
     "displayName": "Gemini 3 Pro (Preview)",
     "reasoning": true,
     "reasoning_budget": true,
-    "deprecation_date": "2026-03-26",
+    "deprecation_date": "2026-03-09",
     "max_input_tokens": 1048576,
     "max_output_tokens": 65535,
     "available_providers": [
+      "google",
       "vertex"
     ]
   },
@@ -2989,7 +2995,8 @@
     "max_input_tokens": 1048576,
     "max_output_tokens": 65535,
     "available_providers": [
-      "google"
+      "google",
+      "vertex"
     ]
   },
   "gemini-2.5-flash": {
@@ -3005,6 +3012,7 @@
     "max_input_tokens": 1048576,
     "max_output_tokens": 65535,
     "available_providers": [
+      "google",
       "vertex"
     ]
   },
@@ -3021,6 +3029,7 @@
     "max_input_tokens": 1048576,
     "max_output_tokens": 65535,
     "available_providers": [
+      "google",
       "vertex"
     ]
   },
@@ -3038,6 +3047,7 @@
     "max_input_tokens": 1048576,
     "max_output_tokens": 65535,
     "available_providers": [
+      "google",
       "vertex"
     ]
   },
@@ -3164,6 +3174,7 @@
     "max_input_tokens": 1048576,
     "max_output_tokens": 65535,
     "available_providers": [
+      "google",
       "vertex"
     ]
   },
@@ -3183,6 +3194,7 @@
     "max_input_tokens": 1048576,
     "max_output_tokens": 65535,
     "available_providers": [
+      "google",
       "vertex"
     ]
   },
@@ -3199,6 +3211,7 @@
     "max_input_tokens": 1048576,
     "max_output_tokens": 65535,
     "available_providers": [
+      "google",
       "vertex"
     ]
   },
@@ -3214,21 +3227,23 @@
     "max_input_tokens": 1048576,
     "max_output_tokens": 8192,
     "available_providers": [
+      "google",
       "vertex"
     ]
   },
   "gemini-2.0-flash-001": {
     "format": "google",
     "flavor": "chat",
     "multimodal": true,
-    "input_cost_per_mil_tokens": 0.15,
-    "output_cost_per_mil_tokens": 0.6,
-    "input_cache_read_cost_per_mil_tokens": 0.0375,
+    "input_cost_per_mil_tokens": 0.1,
+    "output_cost_per_mil_tokens": 0.4,
+    "input_cache_read_cost_per_mil_tokens": 0.025,
     "deprecation_date": "2026-06-01",
     "parent": "gemini-2.0-flash",
     "max_input_tokens": 1048576,
     "max_output_tokens": 8192,
     "available_providers": [
+      "google",
       "vertex"
     ]
   },
@@ -3244,6 +3259,7 @@
     "max_input_tokens": 1048576,
     "max_output_tokens": 8192,
     "available_providers": [
+      "google",
       "vertex"
     ]
   },
@@ -3259,6 +3275,7 @@
     "max_input_tokens": 1048576,
     "max_output_tokens": 8192,
     "available_providers": [
+      "google",
       "vertex"
     ]
   },
@@ -3272,6 +3289,7 @@
     "max_input_tokens": 65536,
     "max_output_tokens": 32768,
     "available_providers": [
+      "google",
       "vertex"
     ]
   },
@@ -3280,13 +3298,13 @@
     "flavor": "chat",
     "multimodal": true,
     "input_cost_per_mil_tokens": 0.075,
-    "output_cost_per_mil_tokens": 0.3,
+    "output_cost_per_mil_tokens": 0,
     "displayName": "Gemini 1.5 Flash",
     "deprecation_date": "2025-09-29",
-    "max_input_tokens": 1000000,
+    "max_input_tokens": 8192,
     "max_output_tokens": 8192,
     "available_providers": [
-      "vertex"
+      "google"
     ]
   },
   "gemini-1.5-flash-latest": {
@@ -3488,12 +3506,13 @@
     "format": "google",
     "flavor": "chat",
     "multimodal": true,
-    "input_cost_per_mil_tokens": 0,
-    "output_cost_per_mil_tokens": 0,
+    "input_cost_per_mil_tokens": 0.3,
+    "output_cost_per_mil_tokens": 2.5,
+    "input_cache_read_cost_per_mil_tokens": 0.03,
     "experimental": true,
     "deprecated": true,
-    "max_input_tokens": 2097152,
-    "max_output_tokens": 8192,
+    "max_input_tokens": 1048576,
+    "max_output_tokens": 65535,
     "available_providers": [
       "google"
     ]
@@ -6189,6 +6208,23 @@
       "azure"
     ]
   },
+  "gpt-5.4-mini-2026-03-17": {
+    "format": "openai",
+    "flavor": "chat",
+    "multimodal": true,
+    "input_cost_per_mil_tokens": 0.75,
+    "output_cost_per_mil_tokens": 4.5,
+    "input_cache_read_cost_per_mil_tokens": 0.075,
+    "displayName": "GPT-5.4 mini (2026-03-17)",
+    "reasoning": true,
+    "parent": "gpt-5.4-mini",
+    "max_input_tokens": 400000,
+    "max_output_tokens": 128000,
+    "available_providers": [
+      "openai",
+      "azure"
+    ]
+  },
   "gpt-5.4-nano": {
     "format": "openai",
     "flavor": "chat",