desirecore/config-center
2
0
Fork 0
mirror of https://git.openapi.site/https://github.com/desirecore/config-center.git synced 2026-10-21 06:04:08 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
d97b9c105aca70750320b5f106a173525027cad5
config-center/compute/providers/zhipu.json
Yige 73b278df51 fix(compute): GLM-5.3 系列在 anthropic 协议按官网用 output_config.effort 控制思考强度 (#120) 
智谱官网（国内 coding-plan/latest-model、国际 devpack/latest-model）写明 /api/anthropic
以 thinking.type 与 output_config.effort 控制思考强度，thinking.type=enabled 一律按默认 max
处理，budget_tokens 不是控制项。两个 anthropic-messages 接入面的 GLM-5.3 系列此前只有按
OpenAI 协议文档写的 low/high/max 矩阵，客户端按 budget 形态发送：low/high 在上游都成了 max，
max（也是默认档）在客户端本机被拒绝；经 new-api 的 OpenAI 类渠道转换时 low 变成
reasoning_effort=medium，被智谱标准 API 拒绝。

- zhipu、zhipu-coding 接入面的 GLM-5.3 / 5.3-Flash / 5.3-FlashX 声明 adaptiveThinking
- GLM-5.3 系列规格加 anthropic-messages 协议 profile（V1 副本为 spec.extra.adaptiveThinking），
  覆盖经 ModelSpec 补全的云端条目
- 来源记录补国际 Coding Plan 页；按量 API Key 与 FlashX 按同一端点推定，未列入已核字段
- presetDataVersion 130
2026-10-05 09:17:43 -07:00

557 lines
14 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"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-5.3-flashx",
"displayName": "GLM-5.3-FlashX",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"capabilities": [
"chat",
"reasoning",
"code",
"multilingual",
"vision",
"video_understanding",
"tool_use",
"long_context",
"fast"
],
"serviceType": [
"chat",
"reasoning",
"vision"
],
"description": "Z.ai GLM-5.3-FlashX，高速多模态推理模型，100 万上下文，始终开启推理",
"extra": {
"adaptiveThinking": true,
"thinkingOnly": true,
"cacheHitPrice": 0.57,
"reasoning": {
"supportedEfforts": [
"low",
"high",
"max"
],
"defaultEffort": "max"
},
"pricingNotes": "国内官方标准价，人民币/百万 tokens；Flash 限时优惠以控制台实际结算为准。"
},
"inputPrice": 2,
"outputPrice": 7
},
{
"modelName": "glm-5.3-flash",
"displayName": "GLM-5.3-Flash",
"contextWindow": 1048576,
"maxOutputTokens": 131072,
"capabilities": [
"chat",
"reasoning",
"deep_thinking",
"code",
"tool_use",
"agent",
"long_context",
"vision",
"image_understanding",
"video_understanding"
],
"serviceType": [
"chat",
"reasoning",
"vision"
],
"defaultTemperature": 1,
"defaultTopP": 0.95,
"description": "智谱 GLM-5.3-Flash 原生多模态模型，混合稀疏与线性注意力，面向高效编码与长程 Agent 任务，100 万上下文；强制思考，无法关闭",
"extra": {
"adaptiveThinking": true,
"thinkingDefault": true,
"thinkingOnly": true,
"cacheHitPrice": 0.23,
"reasoning": {
"supportedEfforts": [
"low",
"high",
"max"
],
"defaultEffort": "max"
},
"pricingNotes": "国内官方标准价，人民币/百万 tokens；Flash 限时优惠以控制台实际结算为准。"
},
"inputPrice": 0.8,
"outputPrice": 2.8
},
{
"modelName": "glm-5.3",
"displayName": "GLM-5.3",
"contextWindow": 1048576,
"maxOutputTokens": 131072,
"capabilities": [
"chat",
"reasoning",
"deep_thinking",
"code",
"math",
"multilingual",
"tool_use",
"agent",
"long_context"
],
"serviceType": [
"chat"
],
"defaultTemperature": 1,
"defaultTopP": 0.95,
"description": "智谱 GLM-5.3 大推理模型，面向复杂软件工程与长程 Agent 任务，100 万上下文；强制思考，无法关闭",
"extra": {
"adaptiveThinking": true,
"thinkingDefault": true,
"thinkingOnly": true,
"cacheHitPrice": 2,
"reasoning": {
"supportedEfforts": [
"low",
"high",
"max"
],
"defaultEffort": "max"
},
"pricingNotes": "国内官方标准价，人民币/百万 tokens；Flash 限时优惠以控制台实际结算为准。"
},
"inputPrice": 8,
"outputPrice": 28
},
{
"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"
},
"reasoning": {
"supportedEfforts": [
"max",
"xhigh",
"high",
"medium",
"low",
"minimal",
"none"
],
"defaultEffort": "max"
}
}
},
{
"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",
"tool_use"
],
"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"
}
}
}
]
}
Reference in New Issue View Git Blame Copy Permalink