mirror of
https://git.openapi.site/https://github.com/desirecore/config-center.git
synced 2026-09-05 21:33:40 +08:00
Yige
c46cf07d2f
* feat(compute): 补 GLM-5.3 系列规格并标注 Ox Alpha 真身 Ox Alpha 是智谱 GLM-5.3-Flash 的匿名发布别名（canonical_slug z-ai/glm-5.3-flash-20260826，2026-08-26 揭晓后已从 OpenRouter 列表下架）。 改动： - model-specs/zhipu.json 新增 glm-5.3 与 glm-5.3-flash 正式规格。两者均 强制思考（z.ai 文档：thinking.type 仅接受 enabled；OpenRouter models API： reasoning.mandatory=true，supported_efforts=[max,high,low]），故 routing.reasoning.supportedModes 不含 off。按 #79 的教训只用 exact 匹配， 避免 glm-5.3* 误吞 glm-5.3-flash。 - model-specs/stealth.json 的 ox-alpha 用 spec.extra.modelOrigin 标注真身。 条目保留：云端算力可能仍以旧别名下发该模型。 - schemas/model-spec.schema.json 为 extra.thinkingOnly / thinkingDefault 补正式定义与 description。此前这两个键无任何说明，客户端因此从未消费， 用户选「关闭思考」即触发上游 400（见 desirecore#2307）。 - scripts/validate.mjs 新增静默失效键名巡检：extra 是开放对象，写错键名 既不报错也无告警。当前巡出 17 处扁平 extra.reasoningEffort。刻意只告警 不失败——存量取值需逐个核实各自接入面实际接受哪些 effort。 * docs(schema): 写明 extra.reasoning 与 thinkingOnly 的职责边界 provider schema 的 extra.reasoning 此前只有子字段 description、对象本身没有， 维护者看不出它与 model-spec 的 thinkingOnly 分别回答什么问题——issue desirecore#2307 的误解正源于此。补上对象级说明：本键答「接入面接受哪些 effort 值」且只能写在 provider model；thinkingOnly 答「off 能不能用」、不声明深度档位。
408 lines
9.5 KiB
JSON
408 lines
9.5 KiB
JSON
{
|
||
"description": "智谱 GLM 系列模型规格。参数来源：config-center compute/providers/zhipu.json。glm-5 与 glm-5.1/glm-5-turbo/glm-5v-turbo 前缀相近，故各自仅用 exact 主键匹配，不用宽 pattern 以防误吞。",
|
||
"specs": [
|
||
{
|
||
"id": "glm-5.3",
|
||
"displayName": "GLM-5.3",
|
||
"family": "glm-5.3",
|
||
"match": {
|
||
"exact": [
|
||
"glm-5.3",
|
||
"z-ai/glm-5.3"
|
||
]
|
||
},
|
||
"spec": {
|
||
"contextWindow": 1048576,
|
||
"maxOutputTokens": 131072,
|
||
"capabilities": [
|
||
"chat",
|
||
"reasoning",
|
||
"deep_thinking",
|
||
"code",
|
||
"math",
|
||
"multilingual",
|
||
"tool_use",
|
||
"agent",
|
||
"long_context"
|
||
],
|
||
"serviceType": [
|
||
"chat"
|
||
],
|
||
"defaultTemperature": 1,
|
||
"defaultTopP": 0.95,
|
||
"supportsReasoning": true,
|
||
"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": {
|
||
"thinkingDefault": true,
|
||
"thinkingOnly": true
|
||
},
|
||
"releasedAt": "2026-08-16"
|
||
},
|
||
"routing": {
|
||
"tier": "flagship",
|
||
"routingPriority": 50,
|
||
"eligibleForAgent": true,
|
||
"defaultReference": false,
|
||
"reasoning": {
|
||
"supportedModes": [
|
||
"auto",
|
||
"low",
|
||
"high",
|
||
"max"
|
||
],
|
||
"defaultMode": "high"
|
||
}
|
||
}
|
||
},
|
||
{
|
||
"id": "glm-5.3-flash",
|
||
"displayName": "GLM-5.3-Flash",
|
||
"family": "glm-5.3-flash",
|
||
"match": {
|
||
"exact": [
|
||
"glm-5.3-flash",
|
||
"z-ai/glm-5.3-flash"
|
||
]
|
||
},
|
||
"spec": {
|
||
"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,
|
||
"supportsReasoning": true,
|
||
"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": {
|
||
"thinkingDefault": true,
|
||
"thinkingOnly": true
|
||
},
|
||
"releasedAt": "2026-08-26"
|
||
},
|
||
"routing": {
|
||
"tier": "balanced",
|
||
"routingPriority": 48,
|
||
"eligibleForAgent": true,
|
||
"defaultReference": false,
|
||
"reasoning": {
|
||
"supportedModes": [
|
||
"auto",
|
||
"low",
|
||
"high",
|
||
"max"
|
||
],
|
||
"defaultMode": "high"
|
||
}
|
||
}
|
||
},
|
||
{
|
||
"id": "glm-5.2",
|
||
"displayName": "GLM-5.2",
|
||
"family": "glm-5.2",
|
||
"match": {
|
||
"exact": [
|
||
"glm-5.2"
|
||
],
|
||
"patterns": [
|
||
"glm-5.2*"
|
||
]
|
||
},
|
||
"spec": {
|
||
"contextWindow": 1048576,
|
||
"maxOutputTokens": 32768,
|
||
"capabilities": [
|
||
"reasoning",
|
||
"deep_thinking",
|
||
"code",
|
||
"multilingual",
|
||
"tool_use",
|
||
"long_context"
|
||
],
|
||
"serviceType": [
|
||
"chat"
|
||
],
|
||
"supportsReasoning": true,
|
||
"description": "智谱 GLM-5.2 大推理模型，100 万上下文"
|
||
},
|
||
"routing": {
|
||
"tier": "flagship",
|
||
"routingPriority": 45,
|
||
"eligibleForAgent": true,
|
||
"defaultReference": false,
|
||
"reasoning": {
|
||
"supportedModes": [
|
||
"auto",
|
||
"off",
|
||
"minimal",
|
||
"low",
|
||
"medium",
|
||
"high",
|
||
"xhigh"
|
||
],
|
||
"defaultMode": "high"
|
||
}
|
||
}
|
||
},
|
||
{
|
||
"id": "glm-5.1",
|
||
"displayName": "GLM-5.1",
|
||
"family": "glm-5.1",
|
||
"spec": {
|
||
"contextWindow": 200000,
|
||
"maxOutputTokens": 128000,
|
||
"capabilities": [
|
||
"chat",
|
||
"reasoning",
|
||
"code",
|
||
"multilingual",
|
||
"deep_thinking",
|
||
"long_context",
|
||
"math",
|
||
"tool_use",
|
||
"agent"
|
||
],
|
||
"serviceType": [
|
||
"chat"
|
||
],
|
||
"defaultTemperature": 1,
|
||
"supportsReasoning": true
|
||
},
|
||
"routing": {
|
||
"tier": "balanced",
|
||
"routingPriority": 65,
|
||
"eligibleForAgent": true,
|
||
"defaultReference": false,
|
||
"reasoning": {
|
||
"supportedModes": [
|
||
"auto",
|
||
"off",
|
||
"minimal",
|
||
"low",
|
||
"medium",
|
||
"high",
|
||
"xhigh"
|
||
],
|
||
"defaultMode": "medium"
|
||
}
|
||
}
|
||
},
|
||
{
|
||
"id": "glm-5",
|
||
"displayName": "GLM-5",
|
||
"family": "glm-5",
|
||
"spec": {
|
||
"contextWindow": 200000,
|
||
"maxOutputTokens": 128000,
|
||
"capabilities": [
|
||
"chat",
|
||
"reasoning",
|
||
"code",
|
||
"multilingual",
|
||
"deep_thinking",
|
||
"long_context",
|
||
"math",
|
||
"tool_use",
|
||
"agent"
|
||
],
|
||
"serviceType": [
|
||
"chat"
|
||
],
|
||
"defaultTemperature": 1,
|
||
"supportsReasoning": true
|
||
}
|
||
},
|
||
{
|
||
"id": "glm-5-turbo",
|
||
"displayName": "GLM-5 Turbo",
|
||
"family": "glm-5-turbo",
|
||
"spec": {
|
||
"contextWindow": 200000,
|
||
"maxOutputTokens": 128000,
|
||
"capabilities": [
|
||
"chat",
|
||
"reasoning",
|
||
"code",
|
||
"deep_thinking",
|
||
"long_context",
|
||
"tool_use",
|
||
"agent"
|
||
],
|
||
"serviceType": [
|
||
"chat"
|
||
],
|
||
"defaultTemperature": 1,
|
||
"supportsReasoning": true
|
||
}
|
||
},
|
||
{
|
||
"id": "glm-4.7",
|
||
"displayName": "GLM-4.7",
|
||
"family": "glm-4.7",
|
||
"spec": {
|
||
"contextWindow": 200000,
|
||
"maxOutputTokens": 128000,
|
||
"capabilities": [
|
||
"chat",
|
||
"reasoning",
|
||
"code",
|
||
"multilingual",
|
||
"deep_thinking",
|
||
"long_context",
|
||
"tool_use"
|
||
],
|
||
"serviceType": [
|
||
"chat"
|
||
],
|
||
"defaultTemperature": 1,
|
||
"supportsReasoning": true
|
||
}
|
||
},
|
||
{
|
||
"id": "glm-4.6",
|
||
"displayName": "GLM-4.6",
|
||
"family": "glm-4.6",
|
||
"spec": {
|
||
"contextWindow": 200000,
|
||
"maxOutputTokens": 128000,
|
||
"capabilities": [
|
||
"chat",
|
||
"reasoning",
|
||
"code",
|
||
"multilingual",
|
||
"deep_thinking"
|
||
],
|
||
"serviceType": [
|
||
"chat"
|
||
],
|
||
"defaultTemperature": 1,
|
||
"supportsReasoning": true
|
||
}
|
||
},
|
||
{
|
||
"id": "glm-4.7-thinking",
|
||
"displayName": "GLM-4.7 Thinking",
|
||
"family": "glm-4.7",
|
||
"match": {
|
||
"exact": [
|
||
"glm-4.7-thinking"
|
||
]
|
||
},
|
||
"spec": {
|
||
"contextWindow": 200000,
|
||
"maxOutputTokens": 128000,
|
||
"capabilities": [
|
||
"reasoning",
|
||
"math",
|
||
"code",
|
||
"deep_thinking",
|
||
"long_context"
|
||
],
|
||
"serviceType": [
|
||
"reasoning"
|
||
],
|
||
"defaultTemperature": null,
|
||
"supportsReasoning": true,
|
||
"description": "智谱GLM-4.7深度思考模式，交错式/保留式/轮级思考"
|
||
}
|
||
},
|
||
{
|
||
"id": "glm-5v-turbo",
|
||
"displayName": "GLM-5V-Turbo",
|
||
"family": "glm-5v",
|
||
"match": {
|
||
"exact": [
|
||
"glm-5v-turbo"
|
||
]
|
||
},
|
||
"spec": {
|
||
"contextWindow": 200000,
|
||
"maxOutputTokens": 128000,
|
||
"capabilities": [
|
||
"chat",
|
||
"vision",
|
||
"video_understanding",
|
||
"image_understanding",
|
||
"file_understanding",
|
||
"reasoning",
|
||
"code",
|
||
"deep_thinking",
|
||
"long_context",
|
||
"tool_use",
|
||
"agent"
|
||
],
|
||
"serviceType": [
|
||
"vision"
|
||
],
|
||
"defaultTemperature": 1,
|
||
"supportsReasoning": true,
|
||
"description": "智谱首个多模态 Coding 基座模型，支持视频、图像、文本和文件输入"
|
||
}
|
||
},
|
||
{
|
||
"id": "glm-4.6v",
|
||
"displayName": "GLM-4.6V",
|
||
"family": "glm-4.6",
|
||
"match": {
|
||
"exact": [
|
||
"glm-4.6v"
|
||
]
|
||
},
|
||
"spec": {
|
||
"contextWindow": 128000,
|
||
"maxOutputTokens": 32768,
|
||
"capabilities": [
|
||
"chat",
|
||
"vision",
|
||
"video_understanding",
|
||
"image_understanding",
|
||
"long_context",
|
||
"tool_use"
|
||
],
|
||
"serviceType": [
|
||
"vision"
|
||
],
|
||
"defaultTemperature": 1,
|
||
"description": "智谱GLM-4.6V多模态版，106B/12B MoE，支持图像视频理解"
|
||
}
|
||
},
|
||
{
|
||
"id": "embedding-3",
|
||
"displayName": "智谱 embedding-3",
|
||
"family": "zhipu-embedding",
|
||
"match": {
|
||
"exact": [
|
||
"embedding-3"
|
||
]
|
||
},
|
||
"spec": {
|
||
"contextWindow": 8192,
|
||
"capabilities": [
|
||
"text_embedding",
|
||
"semantic_search",
|
||
"rag",
|
||
"custom_dimensions"
|
||
],
|
||
"serviceType": [
|
||
"embedding"
|
||
],
|
||
"description": "智谱嵌入模型v3，支持自定义维度；单条输入最多 3072 tokens"
|
||
}
|
||
}
|
||
]
|
||
}
|