{ "id": "provider-zhipu-001", "provider": "zhipu", "label": "智谱 GLM", "baseUrl": "https://open.bigmodel.cn/api/anthropic", "apiFormat": "anthropic-messages", "apiKeyRef": "zhipu", "apiKeyVerified": false, "enabled": false, "status": "unconfigured", "priceCurrency": "CNY", "services": [ "chat", "vision", "reasoning", "fast" ], "tombstones": [ "embedding-3", "glm-4.7-thinking", "glm-z1-air", "glm-z1-airx", "glm-z1-flash", "glm-z1-flashx", "glm-4-0520" ], "models": [ { "modelName": "glm-5.2", "displayName": "GLM-5.2", "serviceType": [ "chat", "reasoning" ], "description": "智谱 GLM-5.2 最新旗舰模型，面向复杂长程任务与项目级工程交付，1M 上下文，128K 最大输出", "contextWindow": 1000000, "maxOutputTokens": 131072, "capabilities": [ "chat", "reasoning", "code", "multilingual", "deep_thinking", "long_context", "math", "tool_use", "agent" ], "inputPrice": 8, "outputPrice": 28, "defaultTemperature": 1, "defaultTopP": 0.95, "extra": { "cacheHitPrice": 2, "cacheStoragePrice": 0, "thinking": { "default": "enabled" }, "reasoningEffort": { "default": "max", "supported": [ "max", "xhigh", "high", "medium", "low", "minimal", "none" ] } } }, { "modelName": "glm-5.1", "displayName": "GLM-5.1", "serviceType": [ "chat", "reasoning" ], "description": "智谱 GLM-5.1 旗舰模型，面向长程 Agentic Coding 与 Autonomous Agent 场景，200K 上下文，128K 最大输出", "contextWindow": 200000, "maxOutputTokens": 131072, "capabilities": [ "chat", "reasoning", "code", "multilingual", "deep_thinking", "long_context", "math", "tool_use", "agent" ], "inputPrice": 6, "outputPrice": 24, "defaultTemperature": 1, "defaultTopP": 0.95, "extra": { "cacheHitPrice": 1.3, "cacheStoragePrice": 0, "thinking": { "default": "enabled" }, "pricingTiers": [ { "condition": "input_length_k_tokens: [0, 32)", "inputPrice": 6, "outputPrice": 24, "cacheHitPrice": 1.3 }, { "condition": "input_length_k_tokens: [32+)", "inputPrice": 8, "outputPrice": 28, "cacheHitPrice": 2 } ] } }, { "modelName": "glm-5-turbo", "displayName": "GLM-5-Turbo", "serviceType": [ "chat", "reasoning" ], "description": "智谱 GLM-5-Turbo，高阶快速模型，面向长链路任务优化，200K 上下文，128K 最大输出", "contextWindow": 200000, "maxOutputTokens": 131072, "capabilities": [ "chat", "reasoning", "code", "deep_thinking", "long_context", "tool_use", "agent", "fast" ], "inputPrice": 5, "outputPrice": 22, "defaultTemperature": 1, "defaultTopP": 0.95, "extra": { "cacheHitPrice": 1.2, "cacheStoragePrice": 0, "decodeSpeed": "40-60 tokens/s", "thinking": { "default": "enabled" }, "pricingTiers": [ { "condition": "input_length_k_tokens: [0, 32)", "inputPrice": 5, "outputPrice": 22, "cacheHitPrice": 1.2 }, { "condition": "input_length_k_tokens: [32+)", "inputPrice": 7, "outputPrice": 26, "cacheHitPrice": 1.8 } ] } }, { "modelName": "glm-5", "displayName": "GLM-5", "serviceType": [ "chat", "reasoning" ], "description": "智谱 GLM-5，面向 Agentic Engineering 的旗舰基座模型，200K 上下文，128K 最大输出", "contextWindow": 200000, "maxOutputTokens": 131072, "capabilities": [ "chat", "reasoning", "code", "multilingual", "deep_thinking", "long_context", "math", "tool_use", "agent" ], "inputPrice": 4, "outputPrice": 18, "defaultTemperature": 1, "defaultTopP": 0.95, "extra": { "cacheHitPrice": 1, "cacheStoragePrice": 0, "decodeSpeed": "30-50 tokens/s", "thinking": { "default": "enabled" }, "pricingTiers": [ { "condition": "input_length_k_tokens: [0, 32)", "inputPrice": 4, "outputPrice": 18, "cacheHitPrice": 1 }, { "condition": "input_length_k_tokens: [32+)", "inputPrice": 6, "outputPrice": 22, "cacheHitPrice": 1.5 } ] } }, { "modelName": "glm-4.7", "displayName": "GLM-4.7", "serviceType": [ "chat", "reasoning" ], "description": "智谱 GLM-4.7，高智能模型，通用对话、推理与智能体能力全面升级，200K 上下文，128K 最大输出", "contextWindow": 200000, "maxOutputTokens": 131072, "capabilities": [ "chat", "reasoning", "code", "multilingual", "deep_thinking", "long_context", "tool_use", "agent" ], "inputPrice": 2, "outputPrice": 8, "defaultTemperature": 1, "defaultTopP": 0.95, "extra": { "cacheHitPrice": 0.4, "cacheStoragePrice": 0, "decodeSpeed": "30-50 tokens/s", "thinking": { "default": "enabled", "mode": "forced" }, "pricingTiers": [ { "condition": "input_length_k_tokens: [0, 32); output_length_k_tokens: [0, 0.2)", "inputPrice": 2, "outputPrice": 8, "cacheHitPrice": 0.4 }, { "condition": "input_length_k_tokens: [0, 32); output_length_k_tokens: [0.2+)", "inputPrice": 3, "outputPrice": 14, "cacheHitPrice": 0.6 }, { "condition": "input_length_k_tokens: [32, 200)", "inputPrice": 4, "outputPrice": 16, "cacheHitPrice": 0.8 } ] } }, { "modelName": "glm-4.7-flashx", "displayName": "GLM-4.7-FlashX", "serviceType": [ "chat", "fast" ], "description": "智谱 GLM-4.7-FlashX 轻量高速模型，适用于中文写作、翻译、角色扮演等通用场景，200K 上下文，128K 最大输出", "contextWindow": 200000, "maxOutputTokens": 131072, "capabilities": [ "chat", "fast", "long_context", "multilingual" ], "inputPrice": 0.5, "outputPrice": 3, "defaultTemperature": 1, "defaultTopP": 0.95, "extra": { "cacheHitPrice": 0.1, "cacheStoragePrice": 0, "decodeSpeed": "30-40 tokens/s" } }, { "modelName": "glm-5v-turbo", "displayName": "GLM-5V-Turbo", "serviceType": [ "vision" ], "description": "智谱首个多模态 Agent 基座模型，支持视频、图像、文本和文件输入，200K 上下文，128K 最大输出", "contextWindow": 200000, "maxOutputTokens": 131072, "capabilities": [ "chat", "vision", "video_understanding", "image_understanding", "file_understanding", "reasoning", "code", "deep_thinking", "long_context", "tool_use", "agent" ], "inputPrice": 5, "outputPrice": 22, "defaultTemperature": 1, "defaultTopP": 0.95, "extra": { "cacheHitPrice": 1.2, "cacheStoragePrice": 0, "decodeSpeed": "30-50 tokens/s", "thinking": { "default": "enabled" }, "inputModalities": [ "image", "video", "file", "text" ], "pricingTiers": [ { "condition": "input_length_k_tokens: [0, 32)", "inputPrice": 5, "outputPrice": 22, "cacheHitPrice": 1.2 }, { "condition": "input_length_k_tokens: [32+)", "inputPrice": 7, "outputPrice": 26, "cacheHitPrice": 1.8 } ] } }, { "modelName": "glm-4.6v", "displayName": "GLM-4.6V", "serviceType": [ "vision" ], "description": "智谱 GLM-4.6V 多模态模型，支持图像、视频、文本和文件理解，128K 上下文，32K 最大输出", "contextWindow": 128000, "maxOutputTokens": 32768, "capabilities": [ "chat", "vision", "video_understanding", "image_understanding", "file_understanding", "long_context", "tool_use", "reasoning" ], "inputPrice": 1, "outputPrice": 3, "defaultTemperature": 1, "defaultTopP": 0.95, "extra": { "cacheHitPrice": 0.2, "cacheStoragePrice": 0, "decodeSpeed": "30-50 tokens/s", "thinking": { "default": "enabled" }, "inputModalities": [ "image", "video", "file", "text" ], "pricingTiers": [ { "condition": "input_length_k_tokens: [0, 32)", "inputPrice": 1, "outputPrice": 3, "cacheHitPrice": 0.2 }, { "condition": "input_length_k_tokens: [32, 128)", "inputPrice": 2, "outputPrice": 6, "cacheHitPrice": 0.4 } ] } }, { "modelName": "glm-4.6", "displayName": "GLM-4.6", "serviceType": [ "chat", "reasoning" ], "description": "智谱 GLM-4.6，擅长高级编码、复杂推理与工具调用，200K 上下文，128K 最大输出", "contextWindow": 200000, "maxOutputTokens": 131072, "capabilities": [ "chat", "reasoning", "code", "multilingual", "deep_thinking", "long_context", "tool_use" ], "inputPrice": 2, "outputPrice": 8, "defaultTemperature": 1, "defaultTopP": 0.95, "extra": { "cacheHitPrice": 0.5, "thinking": { "default": "enabled" } } } ] }