chore: update OpenAPI spec from monorepo

.speakeasy/in.openapi.yaml

@@ -22836,6 +22836,7 @@ components:
           enum:
             - 'artificial-analysis'
             - 'design-arena'
+            - 'openrouter'
             - null
           example: 'artificial-analysis'
           type:
@@ -22866,6 +22867,76 @@ components:
         - 'model_count'
         - 'task_type'
       type: 'object'
+    UnifiedBenchmarksORItem:
+      example:
+        accuracy: 0.72
+        accuracy_stddev: 0.03
+        avg_cost_per_task: 0.002
+        benchmark_type: 'gpqa_diamond'
+        display_name: 'GPT-4o'
+        last_run_timestamp: '2026-06-03T12:00:00Z'
+        model_permaslug: 'openai/gpt-4o'
+        source: 'openrouter'
+        total_tasks: 300
+      properties:
+        accuracy:
+          description: 'Aggregate accuracy score from 0 to 1. Higher is better.'
+          example: 0.72
+          format: 'double'
+          type: 'number'
+        accuracy_stddev:
+          description: 'Standard deviation of run accuracy, or null for a single run.'
+          example: 0.03
+          format: 'double'
+          type:
+            - 'number'
+            - 'null'
+        avg_cost_per_task:
+          description: 'Average cost per task in USD, or null if unavailable.'
+          example: 0.002
+          format: 'double'
+          type:
+            - 'number'
+            - 'null'
+        benchmark_type:
+          description: 'OpenRouter benchmark evaluation type.'
+          enum:
+            - 'gpqa_diamond'
+            - 'tau_bench_verified_airline'
+          example: 'gpqa_diamond'
+          type: 'string'
+        display_name:
+          description: 'Human-readable model name.'
+          example: 'GPT-4o'
+          type: 'string'
+        last_run_timestamp:
+          description: 'Timestamp of the most recent public benchmark run.'
+          example: '2026-06-03T12:00:00Z'
+          type: 'string'
+        model_permaslug:
+          description: 'Stable OpenRouter model identifier.'
+          example: 'openai/gpt-4o'
+          type: 'string'
+        source:
+          description: 'Benchmark source discriminator.'
+          enum:
+            - 'openrouter'
+          type: 'string'
+        total_tasks:
+          description: 'Total benchmark tasks across runs.'
+          example: 300
+          type: 'integer'
+      required:
+        - 'source'
+        - 'model_permaslug'
+        - 'display_name'
+        - 'benchmark_type'
+        - 'accuracy'
+        - 'accuracy_stddev'
+        - 'avg_cost_per_task'
+        - 'total_tasks'
+        - 'last_run_timestamp'
+      type: 'object'
     UnifiedBenchmarksResponse:
       example:
         data:
@@ -22878,6 +22949,15 @@ components:
               completion: '0.00001'
               prompt: '0.0000025'
             source: 'artificial-analysis'
+          - accuracy: 0.72
+            accuracy_stddev: 0.03
+            avg_cost_per_task: 0.002
+            benchmark_type: 'gpqa_diamond'
+            display_name: 'GPT-4o'
+            last_run_timestamp: '2026-06-03T12:00:00Z'
+            model_permaslug: 'openai/gpt-4o'
+            source: 'openrouter'
+            total_tasks: 300
         meta:
           as_of: '2026-06-03T12:00:00Z'
           citation: null
@@ -22893,10 +22973,12 @@ components:
               mapping:
                 artificial-analysis: '#/components/schemas/UnifiedBenchmarksAAItem'
                 design-arena: '#/components/schemas/UnifiedBenchmarksDAItem'
+                openrouter: '#/components/schemas/UnifiedBenchmarksORItem'
               propertyName: 'source'
             oneOf:
               - $ref: '#/components/schemas/UnifiedBenchmarksAAItem'
               - $ref: '#/components/schemas/UnifiedBenchmarksDAItem'
+              - $ref: '#/components/schemas/UnifiedBenchmarksORItem'
           type: 'array'
         meta:
           $ref: '#/components/schemas/UnifiedBenchmarksMeta'
@@ -25620,7 +25702,7 @@ paths:
       x-speakeasy-name-override: 'createAuthCode'
   /benchmarks:
     get:
-      description: 'Unified benchmark endpoint that aggregates scores from multiple benchmark sources (Artificial Analysis, Design Arena). Filter by source to reproduce the exact shapes from the legacy per-source endpoints, or use task_type to find models suited for specific workloads. Authenticate with any valid OpenRouter API key. Rate-limited to 30 requests/minute per key and 500 requests/day per account.'
+      description: 'Unified benchmark endpoint that aggregates scores from multiple benchmark sources (Artificial Analysis, Design Arena, and OpenRouter''s own tau-bench and GPQA evals). Filter by source to reproduce the exact shapes from the legacy per-source endpoints, or use task_type to find models suited for specific workloads. Authenticate with any valid OpenRouter API key. Rate-limited to 30 requests/minute per key and 500 requests/day per account.'
       operationId: 'getBenchmarks'
       parameters:
         - description: 'Benchmark source to query. Determines the shape of the returned items. When omitted, returns results from all sources.'
@@ -25632,6 +25714,7 @@ paths:
             enum:
               - 'artificial-analysis'
               - 'design-arena'
+              - 'openrouter'
             example: 'artificial-analysis'
             type: 'string'
         - description: 'Filter results by task type. For Artificial Analysis, maps to the corresponding index. For Design Arena, maps to the matching category.'
@@ -25690,6 +25773,15 @@ paths:
                       completion: '0.00001'
                       prompt: '0.0000025'
                     source: 'artificial-analysis'
+                  - accuracy: 0.72
+                    accuracy_stddev: 0.03
+                    avg_cost_per_task: 0.002
+                    benchmark_type: 'gpqa_diamond'
+                    display_name: 'GPT-4o'
+                    last_run_timestamp: '2026-06-03T12:00:00Z'
+                    model_permaslug: 'openai/gpt-4o'
+                    source: 'openrouter'
+                    total_tasks: 300
                 meta:
                   as_of: '2026-06-03T12:00:00Z'
                   citation: null