@swiss-ai-hub/web 0.291.6 → 0.291.7

package/components/Models/ModelDetailsPanel.vue

@@ -221,9 +221,19 @@ const advancedPricingItems = computed<Array<{ key: string, label: string, value:
     },
     { key: 'output_cost_per_image', label: t('models.modelDetails.imageCost'), value: info.output_cost_per_image },
     {
-      key: 'search_context_cost_per_query',
-      label: t('models.modelDetails.searchContextCost'),
-      value: info.search_context_cost_per_query,
+      key: 'search_context_cost_per_query_low',
+      label: t('models.modelDetails.searchContextCostLow'),
+      value: info.search_context_cost_per_query?.search_context_size_low,
+    },
+    {
+      key: 'search_context_cost_per_query_medium',
+      label: t('models.modelDetails.searchContextCostMedium'),
+      value: info.search_context_cost_per_query?.search_context_size_medium,
+    },
+    {
+      key: 'search_context_cost_per_query_high',
+      label: t('models.modelDetails.searchContextCostHigh'),
+      value: info.search_context_cost_per_query?.search_context_size_high,
     },
   ]
 

package/i18n/locales/de.yaml

@@ -39,7 +39,9 @@ models:
     outputCostAbove128k: Output-Kosten (über 128K)
     outputCostAbove200k: Output-Kosten (über 200K)
     imageCost: Bild-Kosten
-    searchContextCost: Suchkontext-Kosten
+    searchContextCostLow: Suchkontext-Kosten (Niedrig)
+    searchContextCostMedium: Suchkontext-Kosten (Mittel)
+    searchContextCostHigh: Suchkontext-Kosten (Hoch)
     rateLimits: Rate Limits
     tokensPerMinute: Token pro Minute
     requestsPerMinute: Anfragen pro Minute

package/i18n/locales/en.yaml

@@ -39,7 +39,9 @@ models:
     outputCostAbove128k: Output Cost (Above 128K)
     outputCostAbove200k: Output Cost (Above 200K)
     imageCost: Image Cost
-    searchContextCost: Search Context Cost
+    searchContextCostLow: Search Context Cost (Low)
+    searchContextCostMedium: Search Context Cost (Medium)
+    searchContextCostHigh: Search Context Cost (High)
     rateLimits: Rate Limits
     tokensPerMinute: Tokens per Minute
     requestsPerMinute: Requests per Minute

package/i18n/locales/fr.yaml

@@ -39,7 +39,9 @@ models:
     outputCostAbove128k: Coût de sortie (au-dessus de 128K)
     outputCostAbove200k: Coût de sortie (au-dessus de 200K)
     imageCost: Coût d'image
-    searchContextCost: Coût du contexte de recherche
+    searchContextCostLow: Coût du contexte de recherche (Faible)
+    searchContextCostMedium: Coût du contexte de recherche (Moyen)
+    searchContextCostHigh: Coût du contexte de recherche (Élevé)
     rateLimits: Limites de taux
     tokensPerMinute: Jetons par minute
     requestsPerMinute: Requêtes par minute

package/i18n/locales/it.yaml

@@ -39,7 +39,9 @@ models:
     outputCostAbove128k: Costo output (sopra 128K)
     outputCostAbove200k: Costo output (sopra 200K)
     imageCost: Costo immagine
-    searchContextCost: Costo contesto ricerca
+    searchContextCostLow: Costo contesto ricerca (Basso)
+    searchContextCostMedium: Costo contesto ricerca (Medio)
+    searchContextCostHigh: Costo contesto ricerca (Alto)
     rateLimits: Limiti di velocità
     tokensPerMinute: Token per minuto
     requestsPerMinute: Richieste per minuto

package/package.json

@@ -3,7 +3,7 @@
   "license": "AGPL-3.0-or-later",
   "author": "bbv Software Services AG (https://www.bbv.ch)",
   "type": "module",
-  "version": "0.291.6",
+  "version": "0.291.7",
   "description": "Swiss AI Hub - Admin & Management UI (Nuxt 3 layer)",
   "main": "./nuxt.config.ts",
   "repository": {

package/sdk/client/index.ts

@@ -835,6 +835,7 @@ export {
   type RouterEventWritable,
   type RunStatistics,
   type RunStatisticsWritable,
+  type SearchContextCostPerQueryDto,
   type SearchOrganizationMemoriesData,
   type SearchOrganizationMemoriesError,
   type SearchOrganizationMemoriesErrors,

package/sdk/client/schemas.gen.ts

@@ -13893,7 +13893,14 @@ export const ModelDetailsSchema = {
 export const ModelInfoDTOSchema = {
   properties: {
     mode: {
-      type: "string",
+      anyOf: [
+        {
+          type: "string",
+        },
+        {
+          type: "null",
+        },
+      ],
       title: "Mode",
       description:
         "The mode of the model (e.g., 'chat', 'completion', 'embedding')",
@@ -14094,14 +14101,13 @@ export const ModelInfoDTOSchema = {
     search_context_cost_per_query: {
       anyOf: [
         {
-          type: "number",
+          $ref: "#/components/schemas/SearchContextCostPerQueryDTO",
         },
         {
           type: "null",
         },
       ],
-      title: "Search Context Cost Per Query",
-      description: "Cost per search context query",
+      description: "Cost per search context query by context size",
     },
     output_vector_size: {
       anyOf: [
@@ -14348,7 +14354,6 @@ export const ModelInfoDTOSchema = {
     },
   },
   type: "object",
-  required: ["mode"],
   title: "ModelInfoDTO",
 } as const;
 
@@ -18400,6 +18405,51 @@ export const RunStatisticsSchema = {
   description: "Statistics for a single run, intended for API response.",
 } as const;
 
+export const SearchContextCostPerQueryDTOSchema = {
+  properties: {
+    search_context_size_low: {
+      anyOf: [
+        {
+          type: "number",
+        },
+        {
+          type: "null",
+        },
+      ],
+      title: "Search Context Size Low",
+      description: "Cost per query with low search context size",
+    },
+    search_context_size_medium: {
+      anyOf: [
+        {
+          type: "number",
+        },
+        {
+          type: "null",
+        },
+      ],
+      title: "Search Context Size Medium",
+      description: "Cost per query with medium search context size",
+    },
+    search_context_size_high: {
+      anyOf: [
+        {
+          type: "number",
+        },
+        {
+          type: "null",
+        },
+      ],
+      title: "Search Context Size High",
+      description: "Cost per query with high search context size",
+    },
+  },
+  type: "object",
+  title: "SearchContextCostPerQueryDTO",
+  description:
+    "LiteLLM reports search context cost per query broken down by context size, not as a single value.",
+} as const;
+
 export const SelectSchema = {
   properties: {
     is_formkit_element: {

package/sdk/client/types.gen.ts

@@ -9359,7 +9359,7 @@ export type ModelInfoDto = {
    *
    * The mode of the model (e.g., 'chat', 'completion', 'embedding')
    */
-  mode: string;
+  mode?: string | null;
   /**
    * Max Input Tokens
    *
@@ -9457,11 +9457,9 @@ export type ModelInfoDto = {
    */
   output_cost_per_image?: number | null;
   /**
-   * Search Context Cost Per Query
-   *
-   * Cost per search context query
+   * Cost per search context query by context size
    */
-  search_context_cost_per_query?: number | null;
+  search_context_cost_per_query?: SearchContextCostPerQueryDto | null;
   /**
    * Output Vector Size
    *
@@ -12408,6 +12406,32 @@ export type RunStatistics = {
   agent: MinimalAgentInstanceDto;
 };
 
+/**
+ * SearchContextCostPerQueryDTO
+ *
+ * LiteLLM reports search context cost per query broken down by context size, not as a single value.
+ */
+export type SearchContextCostPerQueryDto = {
+  /**
+   * Search Context Size Low
+   *
+   * Cost per query with low search context size
+   */
+  search_context_size_low?: number | null;
+  /**
+   * Search Context Size Medium
+   *
+   * Cost per query with medium search context size
+   */
+  search_context_size_medium?: number | null;
+  /**
+   * Search Context Size High
+   *
+   * Cost per query with high search context size
+   */
+  search_context_size_high?: number | null;
+};
+
 /**
  * Select
  *