docs(openrouter-models): sync with openrouter-web changes

skills/openrouter-models/README.md

@@ -22,7 +22,7 @@ For other install methods (Claude Code plugin marketplace, Cursor Rules, etc.) s
 
 See [SKILL.md](SKILL.md) for the full reference, including:
 
-- Listing and sorting models by newest, price, or throughput (`list-models.ts`)
+- Listing and sorting models by newest, price, throughput, intelligence, or Design Arena ELO (`list-models.ts`)
 - Filtering by category (programming, roleplay, vision, etc.)
 - Looking up a specific model's pricing, context length, and modalities
 - Per-provider latency, uptime, and throughput via `get-endpoints.ts`

skills/openrouter-models/SKILL.md

@@ -27,6 +27,8 @@ Pick the right script based on what the user is asking:
 | Find recently added models | `list-models.ts --sort newest` | "What are the newest models?" |
 | Find cheapest models | `list-models.ts --sort price` | "What's the cheapest model?" |
 | Find highest throughput models | `list-models.ts --sort throughput` | "Which models have the most output capacity?" |
+| Find most intelligent models | `list-models.ts --sort intelligence` | "What are the smartest models?" |
+| Find best design models | `list-models.ts --sort design-arena-elo` | "Best models for design/UI tasks?" |
 | Find models in a category | `list-models.ts --category X` | "Best programming models?" |
 | Search by name | `search-models.ts "query"` | "Do they have Claude?" |
 | Resolve an informal model name | `resolve-model.ts "query"` | "Use the nano banana 2.0 model" |
@@ -77,12 +79,18 @@ Categories: `programming`, `roleplay`, `marketing`, `marketing/seo`, `technology
 ### Sort Results
 
 ```bash
-cd <skill-path>/scripts && npx tsx list-models.ts --sort newest      # Recently added first
-cd <skill-path>/scripts && npx tsx list-models.ts --sort price       # Cheapest first
-cd <skill-path>/scripts && npx tsx list-models.ts --sort context     # Largest context first
-cd <skill-path>/scripts && npx tsx list-models.ts --sort throughput  # Most output tokens first
+cd <skill-path>/scripts && npx tsx list-models.ts --sort newest           # Recently added first
+cd <skill-path>/scripts && npx tsx list-models.ts --sort price            # Cheapest first
+cd <skill-path>/scripts && npx tsx list-models.ts --sort context          # Largest context first
+cd <skill-path>/scripts && npx tsx list-models.ts --sort throughput       # Most output tokens first
+cd <skill-path>/scripts && npx tsx list-models.ts --sort latency          # Lowest latency first
+cd <skill-path>/scripts && npx tsx list-models.ts --sort popular          # Most popular first
+cd <skill-path>/scripts && npx tsx list-models.ts --sort intelligence     # Highest Artificial Analysis intelligence index first
+cd <skill-path>/scripts && npx tsx list-models.ts --sort design-arena-elo # Highest Design Arena ELO first
 ```
 
+Sorting is performed server-side. Models without a score for benchmark-based sorts (intelligence, design-arena-elo) are placed last.
+
 Models with upcoming `expiration_date` values trigger a stderr warning.
 
 ## Search Models
@@ -136,6 +144,9 @@ Returns for each provider:
 |---|---|---|
 | `category` | `?category=programming` | Server-side category filter |
 | `supported_parameters` | `?supported_parameters=tools` | Only models supporting this parameter |
+| `sort` | `?sort=intelligence-high-to-low` | Server-side sort order |
+
+Available `sort` values: `most-popular`, `newest`, `top-weekly`, `pricing-low-to-high`, `pricing-high-to-low`, `context-high-to-low`, `throughput-high-to-low`, `latency-low-to-high`, `intelligence-high-to-low`, `design-arena-elo-high-to-low`. Models without a score for the chosen benchmark are placed last.
 
 **Tips for working with the response:**
 

skills/openrouter-models/scripts/list-models.ts

@@ -5,9 +5,30 @@ const args = parseArgs(process.argv.slice(2));
 const category = args.get("category") as string | undefined;
 const sort = args.get("sort") as string | undefined;
 
-const path = category
-  ? `/models?category=${encodeURIComponent(category)}`
-  : "/models";
+// Map user-friendly sort flags to the API's server-side sort parameter values
+const SORT_MAP: Record<string, string> = {
+  newest: "newest",
+  price: "pricing-low-to-high",
+  context: "context-high-to-low",
+  throughput: "throughput-high-to-low",
+  speed: "throughput-high-to-low",
+  latency: "latency-low-to-high",
+  popular: "most-popular",
+  intelligence: "intelligence-high-to-low",
+  "design-arena-elo": "design-arena-elo-high-to-low",
+};
+
+const apiSort = sort ? SORT_MAP[sort] : undefined;
+if (sort && !apiSort) {
+  console.error(`Unknown sort option: "${sort}". Available: ${Object.keys(SORT_MAP).join(", ")}`);
+  process.exit(1);
+}
+
+const params = new URLSearchParams();
+if (category) params.set("category", category);
+if (apiSort) params.set("sort", apiSort);
+
+const path = params.size > 0 ? `/models?${params}` : "/models";
 
 const json = await fetchApi(path, apiKey);
 let models = (json.data ?? []).map(formatModel);
@@ -20,16 +41,4 @@ if (expiring.length > 0) {
   );
 }
 
-if (sort === "newest") {
-  models.sort((a: any, b: any) => (b.created ?? 0) - (a.created ?? 0));
-} else if (sort === "price") {
-  models.sort((a: any, b: any) => parseFloat(a.pricing?.prompt ?? "0") - parseFloat(b.pricing?.prompt ?? "0"));
-} else if (sort === "context") {
-  models.sort((a: any, b: any) => (b.context_length ?? 0) - (a.context_length ?? 0));
-} else if (sort === "throughput" || sort === "speed") {
-  models.sort((a: any, b: any) =>
-    (b.top_provider?.max_completion_tokens ?? 0) - (a.top_provider?.max_completion_tokens ?? 0)
-  );
-}
-
 console.log(JSON.stringify(models, null, 2));