From 93ea8298ab070f284694a8f76a5cdf78db149981 Mon Sep 17 00:00:00 2001
From: Anton Kuzmenko <1917237+default-anton@users.noreply.github.com>
Date: Sun, 28 Dec 2025 13:29:36 -0800
Subject: [PATCH] fix: update zai model API and baseUrl in generate-models
 script

---
 packages/ai/scripts/generate-models.ts | 45 ++++++++++++++------------
 1 file changed, 24 insertions(+), 21 deletions(-)

diff --git a/packages/ai/scripts/generate-models.ts b/packages/ai/scripts/generate-models.ts
index 8d3c86fd..e2d460e9 100644
--- a/packages/ai/scripts/generate-models.ts
+++ b/packages/ai/scripts/generate-models.ts
@@ -260,28 +260,31 @@ async function loadModelsDevData(): Promise<Model<any>[]> {
 
 		// Process xAi models
 		if (data.zai?.models) {
-			for (const [modelId, model] of Object.entries(data.zai.models)) {
-				const m = model as ModelsDevModel;
-				if (m.tool_call !== true) continue;
+      for (const [modelId, model] of Object.entries(data.zai.models)) {
+        const m = model as ModelsDevModel;
+        if (m.tool_call !== true) continue;
 
-				models.push({
-					id: modelId,
-					name: m.name || modelId,
-					api: "anthropic-messages",
-					provider: "zai",
-					baseUrl: "https://api.z.ai/api/anthropic",
-					reasoning: m.reasoning === true,
-					input: m.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
-					cost: {
-						input: m.cost?.input || 0,
-						output: m.cost?.output || 0,
-						cacheRead: m.cost?.cache_read || 0,
-						cacheWrite: m.cost?.cache_write || 0,
-					},
-					contextWindow: m.limit?.context || 4096,
-					maxTokens: m.limit?.output || 4096,
-				});
-			}
+        models.push({
+          id: modelId,
+          name: m.name || modelId,
+          api: "openai-completions",
+          provider: "zai",
+          baseUrl: "https://api.z.ai/api/coding/paas/v4",
+          reasoning: m.reasoning === true,
+          input: m.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
+          cost: {
+            input: m.cost?.input || 0,
+            output: m.cost?.output || 0,
+            cacheRead: m.cost?.cache_read || 0,
+            cacheWrite: m.cost?.cache_write || 0,
+          },
+          compat: {
+            supportsDeveloperRole: false,
+          },
+          contextWindow: m.limit?.context || 4096,
+          maxTokens: m.limit?.output || 4096,
+        });
+      }
 		}
 
 		// Process Mistral models