mirror of
https://git.openapi.site/https://github.com/desirecore/config-center.git
synced 2026-10-21 04:04:31 +08:00
Yige
b64ee77342
* feat(compute): update current model catalog * feat(compute): add MiMo V2.6 model profiles
459 lines
11 KiB
JSON
459 lines
11 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-flashx",
|
||
"displayName": "GLM-5.3-FlashX",
|
||
"family": "glm-5.3-flashx",
|
||
"match": {
|
||
"exact": [
|
||
"glm-5.3-flashx",
|
||
"z-ai/glm-5.3-flashx"
|
||
]
|
||
},
|
||
"spec": {
|
||
"contextWindow": 1000000,
|
||
"maxOutputTokens": 128000,
|
||
"capabilities": [
|
||
"chat",
|
||
"reasoning",
|
||
"code",
|
||
"multilingual",
|
||
"vision",
|
||
"video_understanding",
|
||
"tool_use",
|
||
"long_context",
|
||
"fast"
|
||
],
|
||
"serviceType": [
|
||
"chat",
|
||
"reasoning",
|
||
"vision"
|
||
],
|
||
"supportsReasoning": true,
|
||
"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": {
|
||
"thinkingOnly": true
|
||
}
|
||
},
|
||
"routing": {
|
||
"tier": "balanced",
|
||
"routingPriority": 49,
|
||
"eligibleForAgent": true,
|
||
"defaultReference": false,
|
||
"reasoning": {
|
||
"supportedModes": [
|
||
"auto",
|
||
"low",
|
||
"high",
|
||
"max"
|
||
],
|
||
"defaultMode": "max"
|
||
}
|
||
}
|
||
},
|
||
{
|
||
"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"
|
||
}
|
||
}
|
||
]
|
||
}
|