feat(types,zai): sync Z.AI international model map and tests

- Update pricing, context window, and capabilities for:
  glm-4.5-x, glm-4.5-airx, glm-4.5-flash, glm-4.5v, glm-4.6
- Add glm-4-32b-0414-128k
- Align tests with new model specs

Author: roomote

packages/types/src/providers/zai.ts

@@ -37,10 +37,10 @@ export const internationalZAiModels = {
 		contextWindow: 131_072,
 		supportsImages: false,
 		supportsPromptCache: true,
-		inputPrice: 0.6,
-		outputPrice: 2.2,
+		inputPrice: 2.2,
+		outputPrice: 8.9,
 		cacheWritesPrice: 0,
-		cacheReadsPrice: 0.11,
+		cacheReadsPrice: 0.45,
 		description:
 			"GLM-4.5-X is a high-performance variant optimized for strong reasoning with ultra-fast responses.",
 	},
@@ -49,25 +49,25 @@ export const internationalZAiModels = {
 		contextWindow: 131_072,
 		supportsImages: false,
 		supportsPromptCache: true,
-		inputPrice: 0.2,
-		outputPrice: 1.1,
+		inputPrice: 1.1,
+		outputPrice: 4.5,
 		cacheWritesPrice: 0,
-		cacheReadsPrice: 0.03,
+		cacheReadsPrice: 0.22,
 		description: "GLM-4.5-AirX is a lightweight, ultra-fast variant delivering strong performance with lower cost.",
 	},
 	"glm-4.5-flash": {
 		maxTokens: 98_304,
 		contextWindow: 131_072,
 		supportsImages: false,
-		supportsPromptCache: true,
+		supportsPromptCache: false,
 		inputPrice: 0,
 		outputPrice: 0,
 		cacheWritesPrice: 0,
 		cacheReadsPrice: 0,
 		description: "GLM-4.5-Flash is a free, high-speed model excellent for reasoning, coding, and agentic tasks.",
 	},
 	"glm-4.5v": {
-		maxTokens: 16_384,
+		maxTokens: 98_304,
 		contextWindow: 131_072,
 		supportsImages: true,
 		supportsPromptCache: true,
@@ -80,7 +80,7 @@ export const internationalZAiModels = {
 	},
 	"glm-4.6": {
 		maxTokens: 98_304,
-		contextWindow: 204_800,
+		contextWindow: 200_000,
 		supportsImages: false,
 		supportsPromptCache: true,
 		inputPrice: 0.6,
@@ -90,6 +90,17 @@ export const internationalZAiModels = {
 		description:
 			"GLM-4.6 is Zhipu's newest model with an extended context window of up to 200k tokens, providing enhanced capabilities for processing longer documents and conversations.",
 	},
+	"glm-4-32b-0414-128k": {
+		maxTokens: 98_304,
+		contextWindow: 131_072,
+		supportsImages: false,
+		supportsPromptCache: false,
+		inputPrice: 0.1,
+		outputPrice: 0.1,
+		cacheWritesPrice: 0,
+		cacheReadsPrice: 0,
+		description: "GLM-4-32B is a 32 billion parameter model with 128k context length, optimized for efficiency.",
+	},
 } as const satisfies Record<string, ModelInfo>
 
 export type MainlandZAiModelId = keyof typeof mainlandZAiModels

src/api/providers/__tests__/zai.spec.ts

@@ -82,7 +82,7 @@ describe("ZAiHandler", () => {
 			const model = handlerWithModel.getModel()
 			expect(model.id).toBe(testModelId)
 			expect(model.info).toEqual(internationalZAiModels[testModelId])
-			expect(model.info.contextWindow).toBe(204_800)
+			expect(model.info.contextWindow).toBe(200_000)
 		})
 
 		it("should return GLM-4.5v international model with vision support", () => {
@@ -96,7 +96,7 @@ describe("ZAiHandler", () => {
 			expect(model.id).toBe(testModelId)
 			expect(model.info).toEqual(internationalZAiModels[testModelId])
 			expect(model.info.supportsImages).toBe(true)
-			expect(model.info.maxTokens).toBe(16_384)
+			expect(model.info.maxTokens).toBe(98_304)
 			expect(model.info.contextWindow).toBe(131_072)
 		})
 	})