feat: add GLM-4.6-FP8 and LongCat-Flash-Thinking-FP8 models to Chutes AI provider

Author: roomote

packages/types/src/providers/chutes.ts

@@ -30,6 +30,8 @@ export type ChutesModelId =
 	| "zai-org/GLM-4.5-Air"
 	| "zai-org/GLM-4.5-FP8"
 	| "zai-org/GLM-4.5-turbo"
+	| "zai-org/GLM-4.6-FP8"
+	| "meituan-longcat/LongCat-Flash-Thinking-FP8"
 	| "moonshotai/Kimi-K2-Instruct-75k"
 	| "moonshotai/Kimi-K2-Instruct-0905"
 	| "Qwen/Qwen3-235B-A22B-Thinking-2507"
@@ -284,6 +286,26 @@ export const chutesModels = {
 		outputPrice: 3,
 		description: "GLM-4.5-turbo model with 128K token context window, optimized for fast inference.",
 	},
+	"zai-org/GLM-4.6-FP8": {
+		maxTokens: 32768,
+		contextWindow: 200000,
+		supportsImages: false,
+		supportsPromptCache: false,
+		inputPrice: 0,
+		outputPrice: 0,
+		description:
+			"GLM-4.6-FP8 model with 200K token context window, state-of-the-art performance with fast inference.",
+	},
+	"meituan-longcat/LongCat-Flash-Thinking-FP8": {
+		maxTokens: 32768,
+		contextWindow: 128000,
+		supportsImages: false,
+		supportsPromptCache: false,
+		inputPrice: 0,
+		outputPrice: 0,
+		description:
+			"LongCat Flash Thinking FP8 model with 128K context window, optimized for complex reasoning and coding tasks.",
+	},
 	"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": {
 		maxTokens: 32768,
 		contextWindow: 262144,

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

@@ -275,6 +275,52 @@ describe("ChutesHandler", () => {
 		)
 	})
 
+	it("should return zai-org/GLM-4.6-FP8 model with correct configuration", () => {
+		const testModelId: ChutesModelId = "zai-org/GLM-4.6-FP8"
+		const handlerWithModel = new ChutesHandler({
+			apiModelId: testModelId,
+			chutesApiKey: "test-chutes-api-key",
+		})
+		const model = handlerWithModel.getModel()
+		expect(model.id).toBe(testModelId)
+		expect(model.info).toEqual(
+			expect.objectContaining({
+				maxTokens: 32768,
+				contextWindow: 200000,
+				supportsImages: false,
+				supportsPromptCache: false,
+				inputPrice: 0,
+				outputPrice: 0,
+				description:
+					"GLM-4.6-FP8 model with 200K token context window, state-of-the-art performance with fast inference.",
+				temperature: 0.5, // Default temperature for non-DeepSeek models
+			}),
+		)
+	})
+
+	it("should return meituan-longcat/LongCat-Flash-Thinking-FP8 model with correct configuration", () => {
+		const testModelId: ChutesModelId = "meituan-longcat/LongCat-Flash-Thinking-FP8"
+		const handlerWithModel = new ChutesHandler({
+			apiModelId: testModelId,
+			chutesApiKey: "test-chutes-api-key",
+		})
+		const model = handlerWithModel.getModel()
+		expect(model.id).toBe(testModelId)
+		expect(model.info).toEqual(
+			expect.objectContaining({
+				maxTokens: 32768,
+				contextWindow: 128000,
+				supportsImages: false,
+				supportsPromptCache: false,
+				inputPrice: 0,
+				outputPrice: 0,
+				description:
+					"LongCat Flash Thinking FP8 model with 128K context window, optimized for complex reasoning and coding tasks.",
+				temperature: 0.5, // Default temperature for non-DeepSeek models
+			}),
+		)
+	})
+
 	it("should return Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 model with correct configuration", () => {
 		const testModelId: ChutesModelId = "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8"
 		const handlerWithModel = new ChutesHandler({