feat: collect model performance metrics (#4635)

This commit is contained in:
Calcium-Ion
2026-05-06 13:55:23 +08:00
committed by GitHub
parent 8b2b03d276
commit 9acf5fecae
26 changed files with 1078 additions and 120 deletions
+20
View File
@@ -29,6 +29,7 @@
"{{count}} disabled channel(s) deleted": "{{count}} disabled channel(s) deleted",
"{{count}} hours ago": "{{count}} hours ago",
"{{count}} incidents": "{{count}} incidents",
"{{count}} incidents in the last 24 hours": "{{count}} incidents in the last 24 hours",
"{{count}} incidents in the last 30 days": "{{count}} incidents in the last 30 days",
"{{count}} IP(s)": "{{count}} IP(s)",
"{{count}} log entries removed.": "{{count}} log entries removed.",
@@ -59,11 +60,14 @@
"© 2025 Your Company. All rights reserved.": "© 2025 Your Company. All rights reserved.",
"+{{count}} more": "+{{count}} more",
"| Based on": "| Based on",
"0 means data is kept permanently": "0 means data is kept permanently",
"0 means unlimited": "0 means unlimited",
"1 Day": "1 Day",
"1 day ago": "1 day ago",
"1 hour": "1 hour",
"1 Hour": "1H",
"1 hour ago": "1 hour ago",
"1 minute": "1 minute",
"1 minute ago": "1 minute ago",
"1 Month": "1M",
"1 month ago": "1 month ago",
@@ -86,6 +90,7 @@
"30 Days": "30 Days",
"30 days ago": "30 days ago",
"30d change": "30d change",
"5 minutes": "5 minutes",
"5-Hour Window": "5-Hour Window",
"50 / page": "50 / page",
"7 Days": "7 Days",
@@ -218,6 +223,7 @@
"Aggregated traffic by upstream model provider": "Aggregated traffic by upstream model provider",
"Aggregated usage metrics and trend charts.": "Aggregated usage metrics and trend charts.",
"aggregates 50+ AI providers behind one unified API. Manage access, track costs, and scale effortlessly.": "aggregates 50+ AI providers behind one unified API. Manage access, track costs, and scale effortlessly.",
"Aggregation bucket": "Aggregation bucket",
"AGPL v3.0 License": "AGPL v3.0 License",
"AI model testing environment": "AI model testing environment",
"AI models": "AI models",
@@ -423,13 +429,18 @@
"Automatically selects the best available group with circuit breaker mechanism": "Automatically selects the best available group with circuit breaker mechanism",
"Automatically sync model list when upstream changes are detected": "Automatically sync model list when upstream changes are detected",
"Automatically test channels and notify users when limits are hit": "Automatically test channels and notify users when limits are hit",
"Availability (last 24h)": "Availability (last 24h)",
"Available": "Available",
"Available disk space": "Available disk space",
"Available Models": "Available Models",
"Available Rewards": "Available Rewards",
"Average latency": "Average latency",
"Average latency, TTFT, and success rate by group": "Average latency, TTFT, and success rate by group",
"Average RPM": "Average RPM",
"Average time-to-first-token (TTFT) by group": "Average time-to-first-token (TTFT) by group",
"Average tokens per second sustained per group": "Average tokens per second sustained per group",
"Average TPM": "Average TPM",
"Average TTFT": "Average TTFT",
"AWS": "AWS",
"AWS Bedrock Claude Compat": "AWS Bedrock Claude Compat",
"AWS Key Format": "AWS Key Format",
@@ -710,6 +721,7 @@
"Cohere": "Cohere",
"Collapse": "Collapse",
"Collapse All": "Collapse All",
"Collect relay latency and success-rate metrics for the model square.": "Collect relay latency and success-rate metrics for the model square.",
"Color": "Color",
"Color is required": "Color is required",
"Color preset": "Color preset",
@@ -1294,6 +1306,7 @@
"Enable io.net deployments": "Enable io.net deployments",
"Enable io.net model deployment service in console": "Enable io.net model deployment service in console",
"Enable LinuxDO OAuth": "Enable LinuxDO OAuth",
"Enable model performance metrics": "Enable model performance metrics",
"Enable OIDC": "Enable OIDC",
"Enable or disable this channel": "Enable or disable this channel",
"Enable or disable this model": "Enable or disable this model",
@@ -1659,6 +1672,7 @@
"Fixed price (USD)": "Fixed price (USD)",
"Floating": "Floating",
"FluentRead extension not detected. Please ensure it is installed and active.": "FluentRead extension not detected. Please ensure it is installed and active.",
"Flush interval (minutes)": "Flush interval (minutes)",
"Follow the guided steps to prepare your workspace before the first login.": "Follow the guided steps to prepare your workspace before the first login.",
"Footer": "Footer",
"Footer text displayed at the bottom of pages": "Footer text displayed at the bottom of pages",
@@ -2221,6 +2235,7 @@
"Model name is required": "Model name is required",
"Model names copied to clipboard": "Model names copied to clipboard",
"Model not found": "Model not found",
"Model performance metrics": "Model performance metrics",
"Model Price": "Model Price",
"Model Price Not Configured": "Model Price Not Configured",
"Model Pricing": "Model Pricing",
@@ -2396,6 +2411,7 @@
"No groups match your search": "No groups match your search",
"No header overrides configured.": "No header overrides configured.",
"No history data available": "No history data available",
"No incidents in the last 24 hours": "No incidents in the last 24 hours",
"No incidents in the last 30 days": "No incidents in the last 30 days",
"No Inviter": "No Inviter",
"No keys found": "No keys found",
@@ -3106,6 +3122,8 @@
"Request Model:": "Request Model:",
"Request overrides, routing behavior, and upstream model automation": "Request overrides, routing behavior, and upstream model automation",
"Request rule pricing": "Request rule pricing",
"Request success rate sampled over the last 24 hours": "Request success rate sampled over the last 24 hours",
"Request success rate; {{incidents}} incident buckets in the last 24 hours": "Request success rate; {{incidents}} incident buckets in the last 24 hours",
"Request timed out, please refresh and restart GitHub login": "Request timed out, please refresh and restart GitHub login",
"Request-based": "Request-based",
"Requests (24h)": "Requests (24h)",
@@ -3154,6 +3172,7 @@
"Restrict user model request frequency (may impact high concurrency performance)": "Restrict user model request frequency (may impact high concurrency performance)",
"Retain last N days": "Retain last N days",
"Retain last N files": "Retain last N files",
"Retention days": "Retention days",
"Retry": "Retry",
"Retry Chain": "Retry Chain",
"Retry Suggestion": "Retry Suggestion",
@@ -3527,6 +3546,7 @@
"Subscription Plans": "Subscription Plans",
"Subtract": "Subtract",
"Success": "Success",
"Success rate": "Success rate",
"Successfully created {{count}} API Key(s)": "Successfully created {{count}} API Key(s)",
"Successfully created {{count}} redemption codes": "Successfully created {{count}} redemption codes",
"Successfully deleted {{count}} API key(s)": "Successfully deleted {{count}} API key(s)",
+20
View File
@@ -29,6 +29,7 @@
"{{count}} disabled channel(s) deleted": "{{count}} canal(canaux) désactivé(s) supprimé(s)",
"{{count}} hours ago": "il y a {{count}} heures",
"{{count}} incidents": "{{count}} incidents",
"{{count}} incidents in the last 24 hours": "{{count}} incidents au cours des dernières 24 heures",
"{{count}} incidents in the last 30 days": "{{count}} incidents au cours des 30 derniers jours",
"{{count}} IP(s)": "{{count}} IP",
"{{count}} log entries removed.": "{{count}} entrées de journal supprimées.",
@@ -59,11 +60,14 @@
"© 2025 Your Company. All rights reserved.": "© 2025 Votre entreprise. Tous droits réservés.",
"+{{count}} more": "+{{count}} de plus",
"| Based on": "| Basé sur",
"0 means data is kept permanently": "0 signifie que les données sont conservées indéfiniment",
"0 means unlimited": "0 signifie illimité",
"1 Day": "1 jour",
"1 day ago": "Il y a 1 jour",
"1 hour": "1 heure",
"1 Hour": "1H",
"1 hour ago": "Il y a 1 heure",
"1 minute": "1 minute",
"1 minute ago": "Il y a 1 minute",
"1 Month": "1M",
"1 month ago": "Il y a 1 mois",
@@ -86,6 +90,7 @@
"30 Days": "30 jours",
"30 days ago": "Il y a 30 jours",
"30d change": "Variation 30 j",
"5 minutes": "5 minutes",
"5-Hour Window": "Fenêtre de 5 heures",
"50 / page": "50 / page",
"7 Days": "7 jours",
@@ -218,6 +223,7 @@
"Aggregated traffic by upstream model provider": "Trafic agrégé par fournisseur de modèle amont",
"Aggregated usage metrics and trend charts.": "Métriques d'utilisation agrégées et graphiques de tendances.",
"aggregates 50+ AI providers behind one unified API. Manage access, track costs, and scale effortlessly.": "agrège plus de 50 fournisseurs IA derrière une API unifiée. Gérez l'accès, suivez les coûts et évoluez sans effort.",
"Aggregation bucket": "Fenêtre dagrégation",
"AGPL v3.0 License": "Licence AGPL v3.0",
"AI model testing environment": "Environnement de test de modèle IA",
"AI models": "Modèles d'IA",
@@ -423,13 +429,18 @@
"Automatically selects the best available group with circuit breaker mechanism": "Sélectionne automatiquement le meilleur groupe disponible avec un mécanisme de disjoncteur de circuit",
"Automatically sync model list when upstream changes are detected": "Synchroniser automatiquement la liste des modèles lorsque des changements en amont sont détectés",
"Automatically test channels and notify users when limits are hit": "Tester automatiquement les canaux et notifier les utilisateurs lorsque les limites sont atteintes",
"Availability (last 24h)": "Disponibilité (dernières 24 h)",
"Available": "Disponible",
"Available disk space": "Espace disque disponible",
"Available Models": "Modèles disponibles",
"Available Rewards": "Récompenses disponibles",
"Average latency": "Latence moyenne",
"Average latency, TTFT, and success rate by group": "Latence moyenne, TTFT et taux de réussite par groupe",
"Average RPM": "RPM moyen",
"Average time-to-first-token (TTFT) by group": "Temps moyen jusquau premier token (TTFT) par groupe",
"Average tokens per second sustained per group": "Tokens par seconde soutenus en moyenne par groupe",
"Average TPM": "TPM moyen",
"Average TTFT": "TTFT moyen",
"AWS": "AWS",
"AWS Bedrock Claude Compat": "AWS Bedrock Claude Compat",
"AWS Key Format": "Format de clé AWS",
@@ -710,6 +721,7 @@
"Cohere": "Cohere",
"Collapse": "Réduire",
"Collapse All": "Tout réduire",
"Collect relay latency and success-rate metrics for the model square.": "Collecte les métriques de latence Relay et de taux de réussite pour la place des modèles.",
"Color": "Couleur",
"Color is required": "La couleur est requise",
"Color preset": "Préréglage de couleur",
@@ -1294,6 +1306,7 @@
"Enable io.net deployments": "Activer les déploiements io.net",
"Enable io.net model deployment service in console": "Activer le service de déploiement de modèles io.net dans la console",
"Enable LinuxDO OAuth": "Activer LinuxDO OAuth",
"Enable model performance metrics": "Activer les indicateurs de performance des modèles",
"Enable OIDC": "Activer OIDC",
"Enable or disable this channel": "Activer ou désactiver ce canal",
"Enable or disable this model": "Activer ou désactiver ce modèle",
@@ -1659,6 +1672,7 @@
"Fixed price (USD)": "Prix fixe (USD)",
"Floating": "Flottant",
"FluentRead extension not detected. Please ensure it is installed and active.": "Extension FluentRead non détectée. Veuillez vous assurer qu'elle est installée et activée.",
"Flush interval (minutes)": "Intervalle d’écriture (minutes)",
"Follow the guided steps to prepare your workspace before the first login.": "Suivez les étapes guidées pour préparer votre espace de travail avant la première connexion.",
"Footer": "Pied de page",
"Footer text displayed at the bottom of pages": "Texte de pied de page affiché en bas des pages",
@@ -2221,6 +2235,7 @@
"Model name is required": "Le nom du modèle est requis",
"Model names copied to clipboard": "Noms des modèles copiés dans le presse-papiers",
"Model not found": "Modèle introuvable",
"Model performance metrics": "Indicateurs de performance des modèles",
"Model Price": "Prix du modèle",
"Model Price Not Configured": "Prix du modèle non configuré",
"Model Pricing": "Tarification des modèles",
@@ -2396,6 +2411,7 @@
"No groups match your search": "Aucun groupe ne correspond à votre recherche",
"No header overrides configured.": "Aucune surcharge d'en-têtes configurée.",
"No history data available": "Aucune donnée historique disponible",
"No incidents in the last 24 hours": "Aucun incident au cours des dernières 24 heures",
"No incidents in the last 30 days": "Aucun incident sur les 30 derniers jours",
"No Inviter": "Pas d'inviteur",
"No keys found": "Aucune clé trouvée",
@@ -3106,6 +3122,8 @@
"Request Model:": "Modèle demandé :",
"Request overrides, routing behavior, and upstream model automation": "Surcharges de requête, comportement de routage et automatisation des modèles amont",
"Request rule pricing": "Règles de tarification de requête",
"Request success rate sampled over the last 24 hours": "Taux de réussite des requêtes échantillonné sur les dernières 24 heures",
"Request success rate; {{incidents}} incident buckets in the last 24 hours": "Taux de réussite des requêtes ; {{incidents}} créneaux avec incident sur les dernières 24 heures",
"Request timed out, please refresh and restart GitHub login": "Délai dépassé, veuillez actualiser la page puis relancer la connexion GitHub",
"Request-based": "Selon la requête",
"Requests (24h)": "Requêtes (24 h)",
@@ -3154,6 +3172,7 @@
"Restrict user model request frequency (may impact high concurrency performance)": "Restreindre la fréquence des requêtes du modèle utilisateur (peut impacter les performances en cas de forte concurrence)",
"Retain last N days": "Conserver les N derniers jours",
"Retain last N files": "Conserver les N derniers fichiers",
"Retention days": "Jours de rétention",
"Retry": "Réessayer",
"Retry Chain": "Chaîne de tentatives",
"Retry Suggestion": "Suggestion de relance",
@@ -3527,6 +3546,7 @@
"Subscription Plans": "Plans d'abonnement",
"Subtract": "Soustraire",
"Success": "Succès",
"Success rate": "Taux de réussite",
"Successfully created {{count}} API Key(s)": "{{count}} clé(s) API créée(s) avec succès",
"Successfully created {{count}} redemption codes": "{{count}} codes de réduction créés avec succès",
"Successfully deleted {{count}} API key(s)": "{{count}} clé(s) API supprimée(s) avec succès",
+20
View File
@@ -29,6 +29,7 @@
"{{count}} disabled channel(s) deleted": "{{count}} 個の無効チャネルを削除しました",
"{{count}} hours ago": "{{count}} 時間前",
"{{count}} incidents": "{{count}} 件のインシデント",
"{{count}} incidents in the last 24 hours": "過去 24 時間に {{count}} 件のインシデント",
"{{count}} incidents in the last 30 days": "過去 30 日間で {{count}} 件のインシデント",
"{{count}} IP(s)": "{{count}} IP",
"{{count}} log entries removed.": "{{count}} 件のログエントリを削除しました。",
@@ -59,11 +60,14 @@
"© 2025 Your Company. All rights reserved.": "© 2025 Your Company. 全著作権所有。",
"+{{count}} more": "他 {{count}} 件",
"| Based on": "| に基づく",
"0 means data is kept permanently": "0 はデータを永続的に保持することを意味します",
"0 means unlimited": "0は無制限を意味します",
"1 Day": "1日",
"1 day ago": "1日前",
"1 hour": "1 時間",
"1 Hour": "1時間",
"1 hour ago": "1時間前",
"1 minute": "1 分",
"1 minute ago": "1分前",
"1 Month": "1ヶ月",
"1 month ago": "1ヶ月前",
@@ -86,6 +90,7 @@
"30 Days": "30日",
"30 days ago": "30日前",
"30d change": "30日変化",
"5 minutes": "5 分",
"5-Hour Window": "5時間ウィンドウ",
"50 / page": "50 / ページ",
"7 Days": "7日",
@@ -218,6 +223,7 @@
"Aggregated traffic by upstream model provider": "上流モデルプロバイダー別の集計トラフィック",
"Aggregated usage metrics and trend charts.": "集計された使用量メトリクスとトレンドチャート。",
"aggregates 50+ AI providers behind one unified API. Manage access, track costs, and scale effortlessly.": "50以上のAIプロバイダーを統一APIで集約。アクセス管理、コスト追跡、スケーリングを簡単に。",
"Aggregation bucket": "集計バケット",
"AGPL v3.0 License": "AGPL v3.0ライセンス",
"AI model testing environment": "AIモデルテスト環境",
"AI models": "AIモデル",
@@ -423,13 +429,18 @@
"Automatically selects the best available group with circuit breaker mechanism": "回路ブレーカーメカニズム付きで最適な利用可能なグループを自動的に選択",
"Automatically sync model list when upstream changes are detected": "アップストリームの変更が検出されたときにモデルリストを自動的に同期",
"Automatically test channels and notify users when limits are hit": "チャネルを自動的にテストし、制限に達したときにユーザーに通知する",
"Availability (last 24h)": "可用性(過去 24 時間)",
"Available": "空き",
"Available disk space": "利用可能なディスク容量",
"Available Models": "利用可能なモデル",
"Available Rewards": "利用可能な報酬",
"Average latency": "平均レイテンシ",
"Average latency, TTFT, and success rate by group": "グループ別の平均レイテンシ、TTFT、成功率",
"Average RPM": "平均RPM",
"Average time-to-first-token (TTFT) by group": "グループ別の平均 Time to First TokenTTFT",
"Average tokens per second sustained per group": "グループごとに持続する平均スループット (tokens/秒)",
"Average TPM": "平均TPM",
"Average TTFT": "平均 TTFT",
"AWS": "AWS",
"AWS Bedrock Claude Compat": "AWS Bedrock Claude 互換テンプレート",
"AWS Key Format": "AWSキーフォーマット",
@@ -710,6 +721,7 @@
"Cohere": "Cohere",
"Collapse": "折りたたむ",
"Collapse All": "すべて折りたたむ",
"Collect relay latency and success-rate metrics for the model square.": "モデル広場向けに Relay のレイテンシと成功率メトリクスを収集します。",
"Color": "カラー",
"Color is required": "色は必須です",
"Color preset": "カラープリセット",
@@ -1294,6 +1306,7 @@
"Enable io.net deployments": "io.net デプロイを有効化",
"Enable io.net model deployment service in console": "コンソールで io.net モデルデプロイサービスを有効化",
"Enable LinuxDO OAuth": "LinuxDO OAuthを有効にする",
"Enable model performance metrics": "モデル性能メトリクスを有効化",
"Enable OIDC": "OIDCを有効にする",
"Enable or disable this channel": "このチャネルを有効または無効にする",
"Enable or disable this model": "このモデルを有効または無効にする",
@@ -1659,6 +1672,7 @@
"Fixed price (USD)": "固定価格 (USD)",
"Floating": "フローティング",
"FluentRead extension not detected. Please ensure it is installed and active.": "FluentRead 拡張機能が検出されませんでした。インストールされていて有効になっていることを確認してください。",
"Flush interval (minutes)": "書き込み間隔(分)",
"Follow the guided steps to prepare your workspace before the first login.": "初回ログイン前に、ガイド付きの手順に従ってワークスペースを準備してください。",
"Footer": "フッター",
"Footer text displayed at the bottom of pages": "ページ下部に表示されるフッターテキスト",
@@ -2221,6 +2235,7 @@
"Model name is required": "モデル名は必須です",
"Model names copied to clipboard": "モデル名がクリップボードにコピーされました",
"Model not found": "モデルが見つかりません",
"Model performance metrics": "モデル性能メトリクス",
"Model Price": "モデル価格",
"Model Price Not Configured": "モデル価格が未設定",
"Model Pricing": "モデル料金",
@@ -2396,6 +2411,7 @@
"No groups match your search": "検索に一致するグループがありません",
"No header overrides configured.": "ヘッダーのオーバーライドが設定されていません。",
"No history data available": "履歴データがありません",
"No incidents in the last 24 hours": "過去 24 時間にインシデントはありません",
"No incidents in the last 30 days": "過去 30 日間でインシデントはありません",
"No Inviter": "招待者なし",
"No keys found": "キーが見つかりません",
@@ -3106,6 +3122,8 @@
"Request Model:": "リクエストモデル:",
"Request overrides, routing behavior, and upstream model automation": "リクエスト上書き、ルーティング動作、上流モデル自動化",
"Request rule pricing": "リクエストルールの課金",
"Request success rate sampled over the last 24 hours": "過去 24 時間にサンプリングされたリクエスト成功率",
"Request success rate; {{incidents}} incident buckets in the last 24 hours": "リクエスト成功率;過去 24 時間に {{incidents}} 個のインシデント時間枠",
"Request timed out, please refresh and restart GitHub login": "タイムアウトしました。ページをリロードして GitHub ログインをやり直してください",
"Request-based": "リクエスト条件あり",
"Requests (24h)": "リクエスト (24h)",
@@ -3154,6 +3172,7 @@
"Restrict user model request frequency (may impact high concurrency performance)": "ユーザーモデルのリクエスト頻度を制限する(高並行性パフォーマンスに影響を与える可能性があります)",
"Retain last N days": "最新N日間を保持",
"Retain last N files": "最新N個のファイルを保持",
"Retention days": "保持日数",
"Retry": "再試行",
"Retry Chain": "リトライチェーン",
"Retry Suggestion": "リトライ提案",
@@ -3527,6 +3546,7 @@
"Subscription Plans": "サブスクリプションプラン",
"Subtract": "減算",
"Success": "成功",
"Success rate": "成功率",
"Successfully created {{count}} API Key(s)": "{{count}}個のAPIキーが正常に作成されました",
"Successfully created {{count}} redemption codes": "{{count}}件の引き換えコードが正常に作成されました",
"Successfully deleted {{count}} API key(s)": "{{count}}個のAPIキーが正常に削除されました",
+20
View File
@@ -29,6 +29,7 @@
"{{count}} disabled channel(s) deleted": "Удалено {{count}} отключённых каналов",
"{{count}} hours ago": "{{count}} часов назад",
"{{count}} incidents": "{{count}} инцидентов",
"{{count}} incidents in the last 24 hours": "{{count}} инцидентов за последние 24 часа",
"{{count}} incidents in the last 30 days": "{{count}} инцидентов за последние 30 дней",
"{{count}} IP(s)": "{{count}} IP",
"{{count}} log entries removed.": "Удалено {{count}} записей журнала.",
@@ -59,11 +60,14 @@
"© 2025 Your Company. All rights reserved.": "© 2025 Ваша Компания. Все права защищены.",
"+{{count}} more": "ещё {{count}}",
"| Based on": "| На основе",
"0 means data is kept permanently": "0 означает, что данные хранятся постоянно",
"0 means unlimited": "0 означает без ограничений",
"1 Day": "1 день",
"1 day ago": "1 день назад",
"1 hour": "1 час",
"1 Hour": "1 ч.",
"1 hour ago": "1 час назад",
"1 minute": "1 минута",
"1 minute ago": "1 минуту назад",
"1 Month": "1 мес.",
"1 month ago": "1 месяц назад",
@@ -86,6 +90,7 @@
"30 Days": "30 дней",
"30 days ago": "30 дней назад",
"30d change": "Изменение за 30 дней",
"5 minutes": "5 минут",
"5-Hour Window": "5-часовое окно",
"50 / page": "50 / страница",
"7 Days": "7 дней",
@@ -218,6 +223,7 @@
"Aggregated traffic by upstream model provider": "Агрегированный трафик по поставщикам моделей",
"Aggregated usage metrics and trend charts.": "Агрегированные метрики использования и графики трендов.",
"aggregates 50+ AI providers behind one unified API. Manage access, track costs, and scale effortlessly.": "объединяет 50+ ИИ-провайдеров за единым API. Управляйте доступом, отслеживайте затраты и масштабируйтесь без усилий.",
"Aggregation bucket": "Интервал агрегации",
"AGPL v3.0 License": "Лицензия AGPL v3.0",
"AI model testing environment": "Среда тестирования ИИ моделей",
"AI models": "Модели ИИ",
@@ -423,13 +429,18 @@
"Automatically selects the best available group with circuit breaker mechanism": "Автоматически выбирает лучшую доступную группу с механизмом circuit breaker",
"Automatically sync model list when upstream changes are detected": "Автоматически синхронизировать список моделей при обнаружении изменений у провайдера",
"Automatically test channels and notify users when limits are hit": "Автоматически тестировать каналы и уведомлять пользователей при достижении лимитов",
"Availability (last 24h)": "Доступность (последние 24 ч)",
"Available": "Доступно",
"Available disk space": "Доступное дисковое пространство",
"Available Models": "Доступные модели",
"Available Rewards": "Доступные награды",
"Average latency": "Средняя задержка",
"Average latency, TTFT, and success rate by group": "Средняя задержка, TTFT и доля успешных запросов по группам",
"Average RPM": "Среднее число оборотов в минуту",
"Average time-to-first-token (TTFT) by group": "Среднее время до первого токена (TTFT) по группам",
"Average tokens per second sustained per group": "Средняя устойчивая пропускная способность (токенов/с) по группам",
"Average TPM": "Среднее число транзакций в минуту",
"Average TTFT": "Средний TTFT",
"AWS": "AWS",
"AWS Bedrock Claude Compat": "AWS Bedrock Claude совместимость",
"AWS Key Format": "Формат ключа AWS",
@@ -710,6 +721,7 @@
"Cohere": "Cohere",
"Collapse": "Свернуть",
"Collapse All": "Свернуть все",
"Collect relay latency and success-rate metrics for the model square.": "Собирает метрики задержки Relay и доли успешных запросов для витрины моделей.",
"Color": "Цвет",
"Color is required": "Цвет обязателен",
"Color preset": "Цветовая предустановка",
@@ -1294,6 +1306,7 @@
"Enable io.net deployments": "Включить развертывания io.net",
"Enable io.net model deployment service in console": "Включить сервис развертывания моделей io.net в консоли",
"Enable LinuxDO OAuth": "Включить LinuxDO OAuth",
"Enable model performance metrics": "Включить метрики производительности моделей",
"Enable OIDC": "Включить OIDC",
"Enable or disable this channel": "Включить или отключить этот канал",
"Enable or disable this model": "Включить или отключить эту модель",
@@ -1659,6 +1672,7 @@
"Fixed price (USD)": "Фиксированная цена (USD)",
"Floating": "Плавающая",
"FluentRead extension not detected. Please ensure it is installed and active.": "Расширение FluentRead не обнаружено. Убедитесь, что оно установлено и активно.",
"Flush interval (minutes)": "Интервал записи (минуты)",
"Follow the guided steps to prepare your workspace before the first login.": "Следуйте пошаговым инструкциям, чтобы подготовить рабочее пространство перед первым входом.",
"Footer": "Подвал",
"Footer text displayed at the bottom of pages": "Текст нижнего колонтитула, отображаемый внизу страниц",
@@ -2221,6 +2235,7 @@
"Model name is required": "Название модели обязательно",
"Model names copied to clipboard": "Названия моделей скопированы в буфер обмена",
"Model not found": "Модель не найдена",
"Model performance metrics": "Метрики производительности моделей",
"Model Price": "Цена модели",
"Model Price Not Configured": "Цена модели не настроена",
"Model Pricing": "Цены на модели",
@@ -2396,6 +2411,7 @@
"No groups match your search": "Нет групп, соответствующих вашему поиску",
"No header overrides configured.": "Нет настроенных переопределений заголовков.",
"No history data available": "Исторические данные недоступны",
"No incidents in the last 24 hours": "За последние 24 часа инцидентов не было",
"No incidents in the last 30 days": "За последние 30 дней инцидентов не было",
"No Inviter": "Нет пригласившего",
"No keys found": "Ключи не найдены",
@@ -3106,6 +3122,8 @@
"Request Model:": "Модель запроса:",
"Request overrides, routing behavior, and upstream model automation": "Переопределения запросов, маршрутизация и автоматизация upstream-моделей",
"Request rule pricing": "Правила ценообразования по запросу",
"Request success rate sampled over the last 24 hours": "Доля успешных запросов по выборкам за последние 24 часа",
"Request success rate; {{incidents}} incident buckets in the last 24 hours": "Доля успешных запросов; {{incidents}} интервалов с инцидентами за последние 24 часа",
"Request timed out, please refresh and restart GitHub login": "Время ожидания истекло, обновите страницу и снова запустите вход через GitHub",
"Request-based": "Зависит от запроса",
"Requests (24h)": "Запросы (24 ч)",
@@ -3154,6 +3172,7 @@
"Restrict user model request frequency (may impact high concurrency performance)": "Ограничить частоту запросов пользовательских моделей (может повлиять на производительность при высокой конкуренции)",
"Retain last N days": "Хранить последние N дней",
"Retain last N files": "Хранить последние N файлов",
"Retention days": "Дней хранения",
"Retry": "Повторить попытку",
"Retry Chain": "Цепочка повторов",
"Retry Suggestion": "Рекомендация по повтору",
@@ -3527,6 +3546,7 @@
"Subscription Plans": "Планы подписки",
"Subtract": "Вычесть",
"Success": "Успешно",
"Success rate": "Доля успешных запросов",
"Successfully created {{count}} API Key(s)": "Успешно создано {{count}} API-ключ(а/ей)",
"Successfully created {{count}} redemption codes": "Успешно создано {{count}} кодов активации",
"Successfully deleted {{count}} API key(s)": "Успешно удалено {{count}} API-ключ(а/ей)",
+20
View File
@@ -29,6 +29,7 @@
"{{count}} disabled channel(s) deleted": "Đã xóa {{count}} kênh đã tắt",
"{{count}} hours ago": "{{count}} giờ trước",
"{{count}} incidents": "{{count}} sự cố",
"{{count}} incidents in the last 24 hours": "{{count}} sự cố trong 24 giờ qua",
"{{count}} incidents in the last 30 days": "{{count}} sự cố trong 30 ngày qua",
"{{count}} IP(s)": "{{count}} IP",
"{{count}} log entries removed.": "Đã xóa {{count}} mục nhật ký.",
@@ -59,11 +60,14 @@
"© 2025 Your Company. All rights reserved.": "© 2025 Công ty của bạn. Mọi quyền được bảo lưu.",
"+{{count}} more": "thêm {{count}} mục",
"| Based on": "| Dựa trên",
"0 means data is kept permanently": "0 nghĩa là dữ liệu được giữ vĩnh viễn",
"0 means unlimited": "0 có nghĩa là không giới hạn",
"1 Day": "1 ngày",
"1 day ago": "1 ngày trước",
"1 hour": "1 giờ",
"1 Hour": "1 giờ",
"1 hour ago": "1 giờ trước",
"1 minute": "1 phút",
"1 minute ago": "1 phút trước",
"1 Month": "1 tháng",
"1 month ago": "1 tháng trước",
@@ -86,6 +90,7 @@
"30 Days": "30 ngày",
"30 days ago": "30 ngày trước",
"30d change": "Thay đổi 30 ngày",
"5 minutes": "5 phút",
"5-Hour Window": "Cửa sổ 5 giờ",
"50 / page": "50 / trang",
"7 Days": "7 ngày",
@@ -218,6 +223,7 @@
"Aggregated traffic by upstream model provider": "Lưu lượng tổng hợp theo nhà cung cấp mô hình",
"Aggregated usage metrics and trend charts.": "Chỉ số sử dụng tổng hợp và biểu đồ xu hướng.",
"aggregates 50+ AI providers behind one unified API. Manage access, track costs, and scale effortlessly.": "tổng hợp hơn 50 nhà cung cấp AI sau một API thống nhất. Quản lý truy cập, theo dõi chi phí và mở rộng dễ dàng.",
"Aggregation bucket": "Khoảng tổng hợp",
"AGPL v3.0 License": "Giấy phép AGPL v3.0",
"AI model testing environment": "Môi trường thử nghiệm mô hình AI",
"AI models": "mô hình AI",
@@ -423,13 +429,18 @@
"Automatically selects the best available group with circuit breaker mechanism": "Tự động chọn nhóm tốt nhất hiện có với cơ chế ngắt mạch",
"Automatically sync model list when upstream changes are detected": "Tự động đồng bộ danh sách mô hình khi phát hiện thay đổi từ nguồn",
"Automatically test channels and notify users when limits are hit": "Tự động kiểm tra các kênh và thông báo cho người dùng khi đạt đến giới hạn",
"Availability (last 24h)": "Khả dụng (24 giờ qua)",
"Available": "Khả dụng",
"Available disk space": "Dung lượng đĩa khả dụng",
"Available Models": "Mô hình khả dụng",
"Available Rewards": "Phần thưởng hiện có",
"Average latency": "Độ trễ trung bình",
"Average latency, TTFT, and success rate by group": "Độ trễ trung bình, TTFT và tỷ lệ thành công theo nhóm",
"Average RPM": "RPM trung bình",
"Average time-to-first-token (TTFT) by group": "Thời gian trung bình tới token đầu tiên (TTFT) theo nhóm",
"Average tokens per second sustained per group": "Số token mỗi giây trung bình duy trì cho từng nhóm",
"Average TPM": "TPM trung bình",
"Average TTFT": "TTFT trung bình",
"AWS": "AWS",
"AWS Bedrock Claude Compat": "AWS Bedrock Claude tương thích",
"AWS Key Format": "Định dạng khóa AWS",
@@ -710,6 +721,7 @@
"Cohere": "Cohere",
"Collapse": "Thu gọn",
"Collapse All": "Thu gọn tất cả",
"Collect relay latency and success-rate metrics for the model square.": "Thu thập độ trễ Relay và tỷ lệ thành công cho quảng trường mô hình.",
"Color": "Màu",
"Color is required": "Màu sắc là bắt buộc",
"Color preset": "Cài đặt màu sẵn",
@@ -1294,6 +1306,7 @@
"Enable io.net deployments": "Bật triển khai io.net",
"Enable io.net model deployment service in console": "Bật dịch vụ triển khai mô hình io.net trong bảng điều khiển",
"Enable LinuxDO OAuth": "Bật LinuxDO OAuth",
"Enable model performance metrics": "Bật chỉ số hiệu năng mô hình",
"Enable OIDC": "Bật OIDC",
"Enable or disable this channel": "Bật hoặc tắt kênh này",
"Enable or disable this model": "Bật hoặc tắt mô hình này",
@@ -1659,6 +1672,7 @@
"Fixed price (USD)": "Giá cố định (USD)",
"Floating": "Nổi",
"FluentRead extension not detected. Please ensure it is installed and active.": "Không phát hiện tiện ích mở rộng FluentRead. Vui lòng đảm bảo nó đã được cài đặt và kích hoạt.",
"Flush interval (minutes)": "Khoảng ghi xuống DB (phút)",
"Follow the guided steps to prepare your workspace before the first login.": "Thực hiện theo các bước hướng dẫn để chuẩn bị không gian làm việc của bạn trước lần đăng nhập đầu tiên.",
"Footer": "Chân trang",
"Footer text displayed at the bottom of pages": "Văn bản chân trang hiển thị ở cuối các trang",
@@ -2221,6 +2235,7 @@
"Model name is required": "Tên mô hình là bắt buộc",
"Model names copied to clipboard": "Tên mô hình đã được sao chép vào bộ nhớ tạm",
"Model not found": "Không tìm thấy mô hình",
"Model performance metrics": "Chỉ số hiệu năng mô hình",
"Model Price": "Giá mô hình",
"Model Price Not Configured": "Giá mô hình chưa được cấu hình",
"Model Pricing": "Bảng giá mô hình",
@@ -2396,6 +2411,7 @@
"No groups match your search": "Không có nhóm nào khớp với tìm kiếm của bạn",
"No header overrides configured.": "Không có ghi đè tiêu đề nào được cấu hình.",
"No history data available": "Không có dữ liệu lịch sử",
"No incidents in the last 24 hours": "Không có sự cố trong 24 giờ qua",
"No incidents in the last 30 days": "Không có sự cố trong 30 ngày qua",
"No Inviter": "Không có người mời",
"No keys found": "Không tìm thấy khóa",
@@ -3106,6 +3122,8 @@
"Request Model:": "Mô hình yêu cầu:",
"Request overrides, routing behavior, and upstream model automation": "Ghi đè yêu cầu, hành vi định tuyến và tự động hóa mô hình upstream",
"Request rule pricing": "Quy tắc tính giá theo request",
"Request success rate sampled over the last 24 hours": "Tỷ lệ yêu cầu thành công được lấy mẫu trong 24 giờ qua",
"Request success rate; {{incidents}} incident buckets in the last 24 hours": "Tỷ lệ yêu cầu thành công; {{incidents}} khoảng có sự cố trong 24 giờ qua",
"Request timed out, please refresh and restart GitHub login": "Yêu cầu đã hết thời gian chờ, vui lòng làm mới và đăng nhập lại GitHub",
"Request-based": "Theo yêu cầu",
"Requests (24h)": "Yêu cầu (24h)",
@@ -3154,6 +3172,7 @@
"Restrict user model request frequency (may impact high concurrency performance)": "Hạn chế tần suất yêu cầu mô hình người dùng (có thể ảnh hưởng đến hiệu suất khi có độ đồng thời cao)",
"Retain last N days": "Giữ lại N ngày gần nhất",
"Retain last N files": "Giữ lại N tệp gần nhất",
"Retention days": "Số ngày lưu giữ",
"Retry": "Thử lại",
"Retry Chain": "Chuỗi thử lại",
"Retry Suggestion": "Gợi ý thử lại",
@@ -3527,6 +3546,7 @@
"Subscription Plans": "Gói đăng ký",
"Subtract": "Trừ",
"Success": "Thành công",
"Success rate": "Tỷ lệ thành công",
"Successfully created {{count}} API Key(s)": "Đã tạo thành công {{count}} khóa API",
"Successfully created {{count}} redemption codes": "Đã tạo thành công {{count}} mã đổi thưởng",
"Successfully deleted {{count}} API key(s)": "Đã xóa thành công {{count}} khóa API",
+20
View File
@@ -29,6 +29,7 @@
"{{count}} disabled channel(s) deleted": "已删除 {{count}} 个已禁用的渠道",
"{{count}} hours ago": "{{count}} 小时前",
"{{count}} incidents": "{{count}} 起事件",
"{{count}} incidents in the last 24 hours": "最近 24 小时 {{count}} 个异常桶",
"{{count}} incidents in the last 30 days": "最近 30 天 {{count}} 起事件",
"{{count}} IP(s)": "{{count}} 个 IP",
"{{count}} log entries removed.": "已删除 {{count}} 条日志。",
@@ -59,11 +60,14 @@
"© 2025 Your Company. All rights reserved.": "© 2025 您的公司。保留所有权利。",
"+{{count}} more": "还有 {{count}} 项",
"| Based on": "| 基于",
"0 means data is kept permanently": "0 表示永久保留数据",
"0 means unlimited": "0 表示不限",
"1 Day": "1 天",
"1 day ago": "1 天前",
"1 hour": "1 小时",
"1 Hour": "1 小时",
"1 hour ago": "1 小时前",
"1 minute": "1 分钟",
"1 minute ago": "1 分钟前",
"1 Month": "1 个月",
"1 month ago": "1 个月前",
@@ -86,6 +90,7 @@
"30 Days": "30 天",
"30 days ago": "30 天前",
"30d change": "30 天变化",
"5 minutes": "5 分钟",
"5-Hour Window": "5小时窗口",
"50 / page": "50 条/页",
"7 Days": "7 天",
@@ -218,6 +223,7 @@
"Aggregated traffic by upstream model provider": "按上游模型提供商聚合的流量",
"Aggregated usage metrics and trend charts.": "聚合使用指标和趋势图表。",
"aggregates 50+ AI providers behind one unified API. Manage access, track costs, and scale effortlessly.": "聚合 50+ AI 提供商于统一 API 之后。轻松管理访问、追踪成本、弹性扩展。",
"Aggregation bucket": "聚合时间桶",
"AGPL v3.0 License": "AGPL v3.0 协议",
"AI model testing environment": "AI模型测试环境",
"AI models": "AI 模型",
@@ -423,13 +429,18 @@
"Automatically selects the best available group with circuit breaker mechanism": "自动选择可用分组,失败时触发熔断切换",
"Automatically sync model list when upstream changes are detected": "检测到上游模型变更时自动同步模型列表",
"Automatically test channels and notify users when limits are hit": "自动测试渠道并在达到限制时通知用户",
"Availability (last 24h)": "可用率(最近 24 小时)",
"Available": "可用",
"Available disk space": "可用磁盘空间",
"Available Models": "可用模型",
"Available Rewards": "可用奖励",
"Average latency": "平均延迟",
"Average latency, TTFT, and success rate by group": "各分组的平均延迟、首 Token 延迟和成功率",
"Average RPM": "平均 RPM",
"Average time-to-first-token (TTFT) by group": "各分组的平均首 Token 延迟(TTFT",
"Average tokens per second sustained per group": "各分组持续输出的平均每秒 token 数",
"Average TPM": "平均 TPM",
"Average TTFT": "平均首 Token 延迟",
"AWS": "AWS",
"AWS Bedrock Claude Compat": "AWS Bedrock Claude 兼容模板",
"AWS Key Format": "AWS 密钥格式",
@@ -710,6 +721,7 @@
"Cohere": "Cohere",
"Collapse": "收起",
"Collapse All": "全部收起",
"Collect relay latency and success-rate metrics for the model square.": "收集 Relay 延迟和成功率指标,用于模型广场展示。",
"Color": "颜色",
"Color is required": "颜色为必填项",
"Color preset": "颜色预设",
@@ -1294,6 +1306,7 @@
"Enable io.net deployments": "启用 io.net 部署",
"Enable io.net model deployment service in console": "在控制台启用 io.net 模型部署服务",
"Enable LinuxDO OAuth": "启用 LinuxDO OAuth",
"Enable model performance metrics": "启用模型性能指标",
"Enable OIDC": "启用 OIDC",
"Enable or disable this channel": "启用或禁用此渠道",
"Enable or disable this model": "启用或禁用此模型",
@@ -1659,6 +1672,7 @@
"Fixed price (USD)": "固定价格 (USD)",
"Floating": "浮动",
"FluentRead extension not detected. Please ensure it is installed and active.": "未检测到 FluentRead 扩展。请确保已安装并激活。",
"Flush interval (minutes)": "刷库间隔(分钟)",
"Follow the guided steps to prepare your workspace before the first login.": "请按照引导步骤在首次登录前准备您的工作区。",
"Footer": "页脚",
"Footer text displayed at the bottom of pages": "显示在页面底部的页脚文本",
@@ -2221,6 +2235,7 @@
"Model name is required": "模型名称为必填项",
"Model names copied to clipboard": "模型名称已复制到剪贴板",
"Model not found": "模型未找到",
"Model performance metrics": "模型性能指标",
"Model Price": "模型价格",
"Model Price Not Configured": "模型价格未配置",
"Model Pricing": "模型定价",
@@ -2396,6 +2411,7 @@
"No groups match your search": "没有组匹配您的搜索",
"No header overrides configured.": "未配置标头覆盖。",
"No history data available": "暂无历史数据",
"No incidents in the last 24 hours": "最近 24 小时无异常",
"No incidents in the last 30 days": "最近 30 天无事件",
"No Inviter": "无邀请人",
"No keys found": "未找到密钥",
@@ -3106,6 +3122,8 @@
"Request Model:": "请求模型:",
"Request overrides, routing behavior, and upstream model automation": "请求覆盖、路由行为和上游模型自动化",
"Request rule pricing": "请求规则计费",
"Request success rate sampled over the last 24 hours": "最近 24 小时按时间桶采样的请求成功率",
"Request success rate; {{incidents}} incident buckets in the last 24 hours": "请求成功率;最近 24 小时 {{incidents}} 个异常桶",
"Request timed out, please refresh and restart GitHub login": "请求超时,请刷新页面后重新发起 GitHub 登录",
"Request-based": "含请求条件",
"Requests (24h)": "请求数(24 小时)",
@@ -3154,6 +3172,7 @@
"Restrict user model request frequency (may impact high concurrency performance)": "限制用户模型请求频率(可能会影响高并发性能)",
"Retain last N days": "保留最近N天",
"Retain last N files": "保留最近 N 个文件",
"Retention days": "保留天数",
"Retry": "重试",
"Retry Chain": "重试链路",
"Retry Suggestion": "重试建议",
@@ -3527,6 +3546,7 @@
"Subscription Plans": "订阅套餐",
"Subtract": "减少",
"Success": "成功",
"Success rate": "成功率",
"Successfully created {{count}} API Key(s)": "成功创建了 {{count}} 个 API 密钥",
"Successfully created {{count}} redemption codes": "成功创建了 {{count}} 个兑换码",
"Successfully deleted {{count}} API key(s)": "成功删除了 {{count}} 个 API 密钥",