mirror of
https://git.openapi.site/https://github.com/desirecore/config-center.git
synced 2026-06-06 04:30:51 +08:00
Revert "Merge pull request #1 from desirecore/model-field-official-audit"
This reverts commit88a8cf2db6, reversing changes made toca99ea272f.
This commit is contained in:
@@ -10,10 +10,7 @@
|
||||
"enabled": false,
|
||||
"status": "unconfigured",
|
||||
"accessMode": "coding-plan",
|
||||
"services": [
|
||||
"chat",
|
||||
"reasoning"
|
||||
],
|
||||
"services": ["chat", "reasoning"],
|
||||
"codingPlan": {
|
||||
"quotas": {},
|
||||
"usageTracking": {
|
||||
@@ -25,47 +22,22 @@
|
||||
{
|
||||
"modelName": "qwen3-coder-plus",
|
||||
"displayName": "Qwen3 Coder Plus (Coding)",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "阿里云百炼 Coding Plan，Qwen3 编程增强版，100万上下文",
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 65536,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"tool_use"
|
||||
],
|
||||
"source": "preset",
|
||||
"inputPrice": 1,
|
||||
"outputPrice": 5,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.8
|
||||
"serviceType": ["chat"],
|
||||
"description": "阿里云百炼 Coding Plan，Qwen3 编程增强版",
|
||||
"contextWindow": 131072,
|
||||
"maxOutputTokens": 16384,
|
||||
"capabilities": ["chat", "reasoning", "code", "tool_use"],
|
||||
"source": "preset"
|
||||
},
|
||||
{
|
||||
"modelName": "qwen3-max",
|
||||
"displayName": "Qwen3 Max (Coding)",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "阿里云百炼 Coding Plan，Qwen3 Max 旗舰模型，262K 上下文",
|
||||
"contextWindow": 262144,
|
||||
"maxOutputTokens": 65536,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"multilingual",
|
||||
"tool_use",
|
||||
"long_context",
|
||||
"vision"
|
||||
],
|
||||
"source": "preset",
|
||||
"inputPrice": 1.2,
|
||||
"outputPrice": 6,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.8
|
||||
"serviceType": ["chat"],
|
||||
"description": "阿里云百炼 Coding Plan，Qwen3 Max 旗舰模型",
|
||||
"contextWindow": 131072,
|
||||
"maxOutputTokens": 16384,
|
||||
"capabilities": ["chat", "reasoning", "code", "multilingual", "tool_use", "long_context", "vision"],
|
||||
"source": "preset"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -27,8 +27,6 @@
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": ["chat", "reasoning", "code", "multilingual"],
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"source": "preset"
|
||||
}
|
||||
]
|
||||
|
||||
@@ -25,10 +25,6 @@
|
||||
"serviceType": ["chat"],
|
||||
"description": "快手 KwaiKAT Coding Plan，编程辅助模型",
|
||||
"capabilities": ["chat", "code"],
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 8192,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"source": "preset"
|
||||
}
|
||||
]
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"id": "provider-minimax-coding-001",
|
||||
"provider": "minimax",
|
||||
"brandGroup": "minimax",
|
||||
"label": "MiniMax Token Plan",
|
||||
"label": "MiniMax Coding Plan",
|
||||
"baseUrl": "https://api.minimaxi.com/v1",
|
||||
"apiFormat": "openai-completions",
|
||||
"apiKeyRef": "",
|
||||
@@ -10,109 +10,25 @@
|
||||
"enabled": false,
|
||||
"status": "unconfigured",
|
||||
"accessMode": "coding-plan",
|
||||
"services": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"fast"
|
||||
],
|
||||
"services": ["chat", "reasoning"],
|
||||
"codingPlan": {
|
||||
"quotas": {
|
||||
"textWindow": "5h",
|
||||
"standard": {
|
||||
"starterRequestsPer5h": 1500,
|
||||
"plusRequestsPer5h": 4500,
|
||||
"maxRequestsPer5h": 15000
|
||||
},
|
||||
"highspeed": {
|
||||
"plusHighspeedRequestsPer5h": 4500,
|
||||
"maxHighspeedRequestsPer5h": 15000,
|
||||
"ultraHighspeedRequestsPer5h": 30000
|
||||
}
|
||||
},
|
||||
"quotas": {},
|
||||
"usageTracking": {
|
||||
"method": "rest-api",
|
||||
"endpoint": "https://www.minimax.io/v1/token_plan/remains",
|
||||
"consoleUrl": "https://www.minimax.io/user-center/token-plan"
|
||||
"endpoint": "https://api.minimaxi.com/v1/coding/usage",
|
||||
"consoleUrl": "https://platform.minimaxi.com/"
|
||||
}
|
||||
},
|
||||
"models": [
|
||||
{
|
||||
"modelName": "MiniMax-M2.7",
|
||||
"displayName": "MiniMax-M2.7 (Token Plan)",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "MiniMax Token Plan 默认文本模型，M2.7，204,800 上下文，约 60 TPS 输出",
|
||||
"contextWindow": 204800,
|
||||
"modelName": "MiniMax-M1",
|
||||
"displayName": "MiniMax-M1 (Coding)",
|
||||
"serviceType": ["chat"],
|
||||
"description": "MiniMax Coding Plan，M1 旗舰模型",
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 131072,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"tool_use",
|
||||
"long_context"
|
||||
],
|
||||
"source": "preset",
|
||||
"inputPrice": 0.3,
|
||||
"outputPrice": 1.2,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"billing": "token_plan_request_quota",
|
||||
"cacheReadPrice": 0.06,
|
||||
"cacheWritePrice": 0.375,
|
||||
"outputSpeedTps": 60
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "MiniMax-M2.7-highspeed",
|
||||
"displayName": "MiniMax-M2.7 高速版 (Token Plan)",
|
||||
"serviceType": [
|
||||
"fast"
|
||||
],
|
||||
"description": "MiniMax Token Plan 高速订阅支持模型，M2.7-highspeed，效果与 M2.7 一致但输出更快",
|
||||
"contextWindow": 204800,
|
||||
"maxOutputTokens": 131072,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"tool_use",
|
||||
"long_context",
|
||||
"fast"
|
||||
],
|
||||
"source": "preset",
|
||||
"inputPrice": 0.6,
|
||||
"outputPrice": 2.4,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"billing": "token_plan_highspeed_request_quota",
|
||||
"cacheReadPrice": 0.06,
|
||||
"cacheWritePrice": 0.375,
|
||||
"outputSpeedTps": 100
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "MiniMax-M2.5",
|
||||
"displayName": "MiniMax-M2.5 (Coding)",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "MiniMax Token Plan，M2.5 模型，204.8K 上下文",
|
||||
"contextWindow": 204800,
|
||||
"maxOutputTokens": 32768,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"long_context"
|
||||
],
|
||||
"source": "preset",
|
||||
"inputPrice": 0.3,
|
||||
"outputPrice": 1.2,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95
|
||||
"capabilities": ["chat", "reasoning", "code", "long_context"],
|
||||
"source": "preset"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -10,77 +10,24 @@
|
||||
"enabled": false,
|
||||
"status": "unconfigured",
|
||||
"accessMode": "coding-plan",
|
||||
"services": [
|
||||
"chat",
|
||||
"reasoning"
|
||||
],
|
||||
"services": ["chat", "reasoning"],
|
||||
"codingPlan": {
|
||||
"quotas": {
|
||||
"window": "5h",
|
||||
"approxApiCallsPerWindow": "300-1200",
|
||||
"maxConcurrency": 30
|
||||
},
|
||||
"quotas": {},
|
||||
"usageTracking": {
|
||||
"method": "none",
|
||||
"consoleUrl": "https://www.kimi.com/code/console"
|
||||
"consoleUrl": "https://platform.moonshot.cn/"
|
||||
}
|
||||
},
|
||||
"models": [
|
||||
{
|
||||
"modelName": "kimi-for-coding",
|
||||
"displayName": "Kimi for Coding",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "Kimi Code 会员权益模型，官方第三方 Coding Agent 推荐模型 ID，Kimi Code 平台按会员额度计费",
|
||||
"contextWindow": 262144,
|
||||
"maxOutputTokens": 32768,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"tool_use",
|
||||
"agent",
|
||||
"long_context",
|
||||
"vision",
|
||||
"video_understanding"
|
||||
],
|
||||
"source": "preset",
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"billing": "kimi_membership_quota",
|
||||
"baseUrlNote": "Kimi Code API Key must use https://api.kimi.com/coding/v1",
|
||||
"recommendedFor": [
|
||||
"Kimi Code CLI",
|
||||
"Claude Code",
|
||||
"Roo Code"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "kimi-k2.5",
|
||||
"displayName": "Kimi K2.5 (Coding)",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "Kimi Code 套餐，Kimi K2.5 模型，256K 上下文",
|
||||
"contextWindow": 256000,
|
||||
"maxOutputTokens": 32768,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"tool_use",
|
||||
"agent",
|
||||
"long_context",
|
||||
"vision"
|
||||
],
|
||||
"source": "preset",
|
||||
"inputPrice": 0.58,
|
||||
"outputPrice": 3.02,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95
|
||||
"modelName": "kimi-k2",
|
||||
"displayName": "Kimi K2 (Coding)",
|
||||
"serviceType": ["chat"],
|
||||
"description": "Kimi Code 套餐，万亿参数 MoE 模型，128K 上下文",
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": ["chat", "reasoning", "code", "tool_use", "agent", "long_context", "vision"],
|
||||
"source": "preset"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -25,10 +25,6 @@
|
||||
"serviceType": ["chat"],
|
||||
"description": "摩尔线程 Coding Plan，国产 GPU 推理",
|
||||
"capabilities": ["chat", "code"],
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 8192,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"source": "preset"
|
||||
}
|
||||
]
|
||||
|
||||
@@ -31,10 +31,6 @@
|
||||
"serviceType": ["chat"],
|
||||
"description": "自动路由最优编程模型（Doubao-Seed-Code / GLM-4.7 / DeepSeek-V3.2 / Kimi-K2 等）",
|
||||
"capabilities": ["code", "reasoning", "chat"],
|
||||
"contextWindow": 256000,
|
||||
"maxOutputTokens": 32000,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"source": "preset"
|
||||
}
|
||||
]
|
||||
|
||||
@@ -10,10 +10,7 @@
|
||||
"enabled": false,
|
||||
"status": "unconfigured",
|
||||
"accessMode": "coding-plan",
|
||||
"services": [
|
||||
"chat",
|
||||
"reasoning"
|
||||
],
|
||||
"services": ["chat", "reasoning"],
|
||||
"codingPlan": {
|
||||
"quotas": {},
|
||||
"usageTracking": {
|
||||
@@ -22,119 +19,25 @@
|
||||
}
|
||||
},
|
||||
"models": [
|
||||
{
|
||||
"modelName": "glm-5.1",
|
||||
"displayName": "GLM-5.1 (Coding)",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "GLM Coding Plan 全量套餐支持的 GLM-5.1，面向复杂推理和大型工程任务，204,800 上下文，131,072 最大输出",
|
||||
"contextWindow": 204800,
|
||||
"maxOutputTokens": 131072,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"deep_thinking",
|
||||
"long_context",
|
||||
"tool_use",
|
||||
"agent",
|
||||
"math",
|
||||
"multilingual"
|
||||
],
|
||||
"source": "preset",
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"quotaMultiplier": {
|
||||
"peakHoursUtc8": "14:00-18:00",
|
||||
"peak": 3,
|
||||
"offPeak": 2,
|
||||
"promotionalOffPeak": 1,
|
||||
"promotionalOffPeakEndsAt": "2026-04-30"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "glm-5-turbo",
|
||||
"displayName": "GLM-5-Turbo (Coding)",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "GLM Coding Plan 支持的 GLM-5-Turbo，面向 OpenClaw 等长链路任务优化，204,800 上下文，131,072 最大输出",
|
||||
"contextWindow": 204800,
|
||||
"maxOutputTokens": 131072,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"deep_thinking",
|
||||
"long_context",
|
||||
"tool_use",
|
||||
"agent"
|
||||
],
|
||||
"source": "preset",
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"quotaMultiplier": {
|
||||
"peakHoursUtc8": "14:00-18:00",
|
||||
"peak": 3,
|
||||
"offPeak": 2,
|
||||
"promotionalOffPeak": 1,
|
||||
"promotionalOffPeakEndsAt": "2026-04-30"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "glm-5",
|
||||
"displayName": "GLM-5 (Coding)",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "智谱 GLM-5 Coding Plan 版本，202,752 token 上下文，编程能力登顶",
|
||||
"contextWindow": 200000,
|
||||
"serviceType": ["chat"],
|
||||
"description": "智谱 GLM-5 Coding Plan 版本，745B MoE，编程能力登顶",
|
||||
"contextWindow": 192000,
|
||||
"maxOutputTokens": 128000,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"deep_thinking",
|
||||
"long_context",
|
||||
"tool_use",
|
||||
"agent",
|
||||
"math",
|
||||
"multilingual"
|
||||
],
|
||||
"source": "preset",
|
||||
"inputPrice": 0.58,
|
||||
"outputPrice": 2.6,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95
|
||||
"capabilities": ["chat", "reasoning", "code", "deep_thinking", "long_context", "tool_use", "agent", "math", "multilingual"],
|
||||
"source": "preset"
|
||||
},
|
||||
{
|
||||
"modelName": "glm-4.7",
|
||||
"displayName": "GLM-4.7 (Coding)",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "智谱 GLM-4.7 Coding Plan 版本，202,752 token 上下文",
|
||||
"serviceType": ["chat"],
|
||||
"description": "智谱 GLM-4.7 Coding Plan 版本，200K 上下文",
|
||||
"contextWindow": 200000,
|
||||
"maxOutputTokens": 128000,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"deep_thinking",
|
||||
"long_context",
|
||||
"tool_use",
|
||||
"multilingual"
|
||||
],
|
||||
"source": "preset",
|
||||
"inputPrice": 0.2911,
|
||||
"outputPrice": 1.1645,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95
|
||||
"capabilities": ["chat", "reasoning", "code", "deep_thinking", "long_context", "tool_use", "multilingual"],
|
||||
"source": "preset"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -15,14 +15,12 @@
|
||||
],
|
||||
"models": [
|
||||
{
|
||||
"modelName": "claude-opus-4-7",
|
||||
"displayName": "Claude Opus 4.7",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "Anthropic 当前最强通用模型，适合复杂推理和智能体编码任务",
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 128000,
|
||||
"modelName": "claude-opus-4-6",
|
||||
"displayName": "Claude Opus 4.6",
|
||||
"serviceType": ["chat"],
|
||||
"description": "Anthropic 最新旗舰 Opus 模型，最强能力",
|
||||
"contextWindow": 200000,
|
||||
"maxOutputTokens": 32768,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -33,54 +31,32 @@
|
||||
"inputPrice": 5,
|
||||
"outputPrice": 25,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"cachePricing": {
|
||||
"write5m": 6.25,
|
||||
"write1h": 10,
|
||||
"read": 0.5
|
||||
},
|
||||
"pricingNotes": "Prices are per 1M tokens. Opus 4.7 includes the full 1M context window at standard pricing."
|
||||
}
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "claude-sonnet-4-6",
|
||||
"displayName": "Claude Sonnet 4.6",
|
||||
"serviceType": [
|
||||
"chat",
|
||||
"computer_use"
|
||||
],
|
||||
"description": "Anthropic 高智能高速度模型，适合编码、工具使用和智能体任务",
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 64000,
|
||||
"modelName": "claude-opus-4-5",
|
||||
"displayName": "Claude Opus 4.5",
|
||||
"serviceType": ["chat"],
|
||||
"description": "Anthropic Opus 4.5，顶级推理能力",
|
||||
"contextWindow": 200000,
|
||||
"maxOutputTokens": 32768,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"vision",
|
||||
"tool_use",
|
||||
"computer_use"
|
||||
"tool_use"
|
||||
],
|
||||
"inputPrice": 3,
|
||||
"outputPrice": 15,
|
||||
"inputPrice": 5,
|
||||
"outputPrice": 25,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"cachePricing": {
|
||||
"write5m": 3.75,
|
||||
"write1h": 6,
|
||||
"read": 0.3
|
||||
},
|
||||
"pricingNotes": "Prices are per 1M tokens. Sonnet 4.6 includes the full 1M context window at standard pricing."
|
||||
}
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "claude-haiku-4-5",
|
||||
"displayName": "Claude Haiku 4.5",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "Anthropic 最快模型，具备接近前沿模型的智能水平",
|
||||
"modelName": "claude-sonnet-4-5",
|
||||
"displayName": "Claude Sonnet 4.5",
|
||||
"serviceType": ["chat"],
|
||||
"description": "Anthropic Sonnet 4.5，高性能性价比",
|
||||
"contextWindow": 200000,
|
||||
"maxOutputTokens": 64000,
|
||||
"capabilities": [
|
||||
@@ -90,19 +66,48 @@
|
||||
"vision",
|
||||
"tool_use"
|
||||
],
|
||||
"inputPrice": 1,
|
||||
"outputPrice": 5,
|
||||
"inputPrice": 3,
|
||||
"outputPrice": 15,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"modelId": "claude-haiku-4-5-20251001",
|
||||
"cachePricing": {
|
||||
"write5m": 1.25,
|
||||
"write1h": 2,
|
||||
"read": 0.1
|
||||
},
|
||||
"pricingNotes": "Prices are per 1M tokens."
|
||||
}
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "claude-sonnet-4",
|
||||
"displayName": "Claude Sonnet 4",
|
||||
"serviceType": ["chat"],
|
||||
"description": "Anthropic Sonnet 4 旗舰模型",
|
||||
"contextWindow": 200000,
|
||||
"maxOutputTokens": 64000,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"vision",
|
||||
"tool_use"
|
||||
],
|
||||
"inputPrice": 3,
|
||||
"outputPrice": 15,
|
||||
"defaultTemperature": 1,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "claude-sonnet-4-5-computer",
|
||||
"displayName": "Claude Sonnet 4.5 Computer Use",
|
||||
"serviceType": ["computer_use"],
|
||||
"description": "Anthropic 最佳 Computer Use 模型",
|
||||
"contextWindow": 200000,
|
||||
"maxOutputTokens": 64000,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"vision",
|
||||
"computer_use",
|
||||
"tool_use",
|
||||
"reasoning"
|
||||
],
|
||||
"inputPrice": 3,
|
||||
"outputPrice": 15,
|
||||
"defaultTemperature": 1,
|
||||
"extra": {}
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -18,8 +18,8 @@
|
||||
"displayName": "百川 M3-Plus",
|
||||
"serviceType": ["chat"],
|
||||
"description": "百川智能M3-Plus医疗增强模型，235B参数，幻觉率仅2.6%，API价格较前代下降70%",
|
||||
"contextWindow": 32000,
|
||||
"maxOutputTokens": 32000,
|
||||
"contextWindow": 192000,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -31,8 +31,8 @@
|
||||
],
|
||||
"inputPrice": 5,
|
||||
"outputPrice": 9,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.9,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
@@ -40,8 +40,8 @@
|
||||
"displayName": "百川 M3",
|
||||
"serviceType": ["chat"],
|
||||
"description": "百川智能M3新一代开源医疗增强模型，235B参数",
|
||||
"contextWindow": 32000,
|
||||
"maxOutputTokens": 32000,
|
||||
"contextWindow": 192000,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -52,8 +52,8 @@
|
||||
],
|
||||
"inputPrice": 10,
|
||||
"outputPrice": 30,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.9,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
@@ -61,8 +61,8 @@
|
||||
"displayName": "百川 M2-Plus",
|
||||
"serviceType": ["chat"],
|
||||
"description": "百川智能M2-Plus旗舰模型，最强推理和创作能力",
|
||||
"contextWindow": 32000,
|
||||
"maxOutputTokens": 32000,
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -72,8 +72,8 @@
|
||||
],
|
||||
"inputPrice": 10,
|
||||
"outputPrice": 30,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.9,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
@@ -81,8 +81,8 @@
|
||||
"displayName": "百川 M2",
|
||||
"serviceType": ["chat"],
|
||||
"description": "百川智能M2模型，高性能通用模型",
|
||||
"contextWindow": 32000,
|
||||
"maxOutputTokens": 32000,
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -91,8 +91,8 @@
|
||||
],
|
||||
"inputPrice": 2,
|
||||
"outputPrice": 20,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.9,
|
||||
"extra": {}
|
||||
}
|
||||
]
|
||||
|
||||
@@ -9,20 +9,14 @@
|
||||
"enabled": false,
|
||||
"status": "unconfigured",
|
||||
"priceCurrency": "CNY",
|
||||
"services": [
|
||||
"chat",
|
||||
"reasoning"
|
||||
],
|
||||
"services": ["chat", "reasoning"],
|
||||
"models": [
|
||||
{
|
||||
"modelName": "ernie-5.0-thinking-latest",
|
||||
"displayName": "文心 ERNIE 5.0",
|
||||
"serviceType": [
|
||||
"chat",
|
||||
"reasoning"
|
||||
],
|
||||
"serviceType": ["chat", "reasoning"],
|
||||
"description": "百度最新旗舰模型，支持深度推理、多模态和工具调用，119K输入/64K输出",
|
||||
"contextWindow": 128000,
|
||||
"contextWindow": 131072,
|
||||
"maxOutputTokens": 65536,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
@@ -31,69 +25,19 @@
|
||||
"multimodal",
|
||||
"tool_use"
|
||||
],
|
||||
"inputPrice": 6,
|
||||
"outputPrice": 24,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"pricingTiers": [
|
||||
{
|
||||
"maxInputTokens": 32768,
|
||||
"inputPrice": 6,
|
||||
"outputPrice": 24
|
||||
},
|
||||
{
|
||||
"maxInputTokens": 131072,
|
||||
"inputPrice": 10,
|
||||
"outputPrice": 40
|
||||
}
|
||||
],
|
||||
"thinkingMaxTokens": 60000
|
||||
}
|
||||
"inputPrice": 8,
|
||||
"outputPrice": 32,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "ernie-5.0",
|
||||
"displayName": "文心 ERNIE 5.0 非思考",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "百度 ERNIE 5.0 旗舰模型，128K 上下文，119K 最大输入，最大输出 65,536 token",
|
||||
"contextWindow": 131072,
|
||||
"maxOutputTokens": 65536,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"vision",
|
||||
"multimodal",
|
||||
"tool_use"
|
||||
],
|
||||
"inputPrice": 6,
|
||||
"outputPrice": 24,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"pricingTiers": [
|
||||
{
|
||||
"maxInputTokens": 32768,
|
||||
"inputPrice": 6,
|
||||
"outputPrice": 24
|
||||
},
|
||||
{
|
||||
"maxInputTokens": 131072,
|
||||
"inputPrice": 10,
|
||||
"outputPrice": 40
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "ernie-4.5-turbo-128k",
|
||||
"modelName": "ernie-4.5-turbo-128k-latest",
|
||||
"displayName": "文心 ERNIE 4.5 Turbo",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "百度高性价比长上下文模型，128K 窗口，最大输出 12,288 token",
|
||||
"serviceType": ["chat"],
|
||||
"description": "百度高性价比长上下文模型，128K 窗口，适合日常对话和文档处理",
|
||||
"contextWindow": 131072,
|
||||
"maxOutputTokens": 12288,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"code",
|
||||
@@ -103,59 +47,9 @@
|
||||
],
|
||||
"inputPrice": 0.8,
|
||||
"outputPrice": 3.2,
|
||||
"defaultTemperature": 0.8,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {
|
||||
"cacheHitPrice": 0.2
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "ernie-4.5-turbo-20260402",
|
||||
"displayName": "文心 ERNIE 4.5 Turbo 20260402",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "百度 ERNIE 4.5 Turbo 20260402 快照，128K 上下文，最大输出 12,288 token",
|
||||
"contextWindow": 131072,
|
||||
"maxOutputTokens": 12288,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"code",
|
||||
"vision",
|
||||
"long_context",
|
||||
"fast"
|
||||
],
|
||||
"inputPrice": 0.8,
|
||||
"outputPrice": 3.2,
|
||||
"defaultTemperature": 0.8,
|
||||
"defaultTopP": 1,
|
||||
"extra": {
|
||||
"cacheHitPrice": 0.2
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "ernie-x1.1",
|
||||
"displayName": "文心 ERNIE X1.1",
|
||||
"serviceType": [
|
||||
"reasoning"
|
||||
],
|
||||
"description": "百度 ERNIE X1.1 深度思考模型，64K 上下文，最大输出 65,536 token",
|
||||
"contextWindow": 65536,
|
||||
"maxOutputTokens": 65536,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"deep_thinking",
|
||||
"math",
|
||||
"code"
|
||||
],
|
||||
"inputPrice": 1,
|
||||
"outputPrice": 4,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"thinkingMaxTokens": 65536
|
||||
}
|
||||
"extra": {}
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -15,9 +15,9 @@
|
||||
"modelName": "command-a-03-2025",
|
||||
"displayName": "Command A",
|
||||
"serviceType": ["chat"],
|
||||
"description": "Cohere 旗舰对话模型，256K 上下文，擅长 RAG 和工具调用",
|
||||
"contextWindow": 256000,
|
||||
"maxOutputTokens": 8000,
|
||||
"description": "Cohere 旗舰对话模型，262K 上下文，擅长 RAG 和工具调用",
|
||||
"contextWindow": 262144,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -29,40 +29,16 @@
|
||||
],
|
||||
"inputPrice": 2.50,
|
||||
"outputPrice": 10.00,
|
||||
"defaultTemperature": 0.3,
|
||||
"defaultTopP": 0.75,
|
||||
"extra": {
|
||||
"pricingNotes": "Prices are per 1M tokens."
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "command-r7b-12-2024",
|
||||
"displayName": "Command R7B",
|
||||
"serviceType": ["fast"],
|
||||
"description": "Cohere 小型高速对话模型，适合高吞吐、低延迟场景",
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 4000,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"tool_use",
|
||||
"rag",
|
||||
"fast"
|
||||
],
|
||||
"inputPrice": 0.0375,
|
||||
"outputPrice": 0.15,
|
||||
"defaultTemperature": 0.3,
|
||||
"defaultTopP": 0.75,
|
||||
"extra": {
|
||||
"pricingNotes": "Prices are per 1M tokens."
|
||||
}
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "embed-v4.0",
|
||||
"displayName": "Embed V4",
|
||||
"serviceType": ["embedding"],
|
||||
"description": "Cohere 最新 Embedding 模型，128K 上下文，多语言支持",
|
||||
"contextWindow": 128000,
|
||||
"description": "Cohere 最新 Embedding 模型，131K 上下文，多语言支持",
|
||||
"contextWindow": 131072,
|
||||
"maxOutputTokens": 0,
|
||||
"capabilities": [
|
||||
"text_embedding",
|
||||
@@ -70,20 +46,14 @@
|
||||
],
|
||||
"inputPrice": 0.12,
|
||||
"outputPrice": 0,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"dimensions": [256, 512, 1024, 1536],
|
||||
"defaultDimension": 1536,
|
||||
"pricingNotes": "Embedding models are priced by embedded tokens; price is per 1M tokens."
|
||||
}
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "rerank-v3.5",
|
||||
"displayName": "Rerank V3.5",
|
||||
"serviceType": ["rerank"],
|
||||
"description": "Cohere 语义重排序模型，用于检索结果精排，默认单文档截断 4096 token",
|
||||
"contextWindow": 4096,
|
||||
"description": "Cohere 语义重排序模型，用于检索结果精排",
|
||||
"contextWindow": 0,
|
||||
"maxOutputTokens": 0,
|
||||
"capabilities": [
|
||||
"rerank",
|
||||
@@ -91,11 +61,7 @@
|
||||
],
|
||||
"inputPrice": 2.00,
|
||||
"outputPrice": 0,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"pricingNotes": "Cohere Rerank is priced by search units, not input/output tokens; one search unit is one query with up to 100 documents. The token price fields are retained for schema compatibility."
|
||||
}
|
||||
"extra": {}
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -23,97 +23,13 @@
|
||||
"translation"
|
||||
],
|
||||
"models": [
|
||||
{
|
||||
"modelName": "qwen3.6-plus",
|
||||
"displayName": "阿里云 Qwen3.6-Plus",
|
||||
"serviceType": [
|
||||
"chat",
|
||||
"vision"
|
||||
],
|
||||
"description": "通义千问3.6 Plus，支持文本/图像/视频输入，100万上下文，支持内置工具和 Function Calling",
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 65536,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"multilingual",
|
||||
"long_context",
|
||||
"tool_use",
|
||||
"agent",
|
||||
"vision"
|
||||
],
|
||||
"inputPrice": 2,
|
||||
"outputPrice": 12,
|
||||
"defaultTemperature": 0.6,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"pricingTiers": [
|
||||
{
|
||||
"maxInputTokens": 256000,
|
||||
"inputPrice": 2,
|
||||
"outputPrice": 12,
|
||||
"thinkingOutputPrice": 12
|
||||
},
|
||||
{
|
||||
"maxInputTokens": 1000000,
|
||||
"inputPrice": 8,
|
||||
"outputPrice": 48,
|
||||
"thinkingOutputPrice": 48
|
||||
}
|
||||
],
|
||||
"thinkingMaxTokens": 81920
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "qwen3.6-flash",
|
||||
"displayName": "阿里云 Qwen3.6-Flash",
|
||||
"serviceType": [
|
||||
"chat",
|
||||
"vision"
|
||||
],
|
||||
"description": "通义千问3.6 Flash，高性价比多模态模型，100万上下文，支持内置工具和 Function Calling",
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 65536,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"multilingual",
|
||||
"long_context",
|
||||
"tool_use",
|
||||
"vision",
|
||||
"fast"
|
||||
],
|
||||
"inputPrice": 1.2,
|
||||
"outputPrice": 7.2,
|
||||
"defaultTemperature": 0.6,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"pricingTiers": [
|
||||
{
|
||||
"maxInputTokens": 256000,
|
||||
"inputPrice": 1.2,
|
||||
"outputPrice": 7.2
|
||||
},
|
||||
{
|
||||
"maxInputTokens": 1000000,
|
||||
"inputPrice": 4.8,
|
||||
"outputPrice": 28.8
|
||||
}
|
||||
],
|
||||
"thinkingMaxTokens": 131072
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "qwen3.5-plus",
|
||||
"displayName": "阿里云 Qwen3.5-Plus",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "通义千问3.5旗舰模型，支持文本/图像/视频输入，100万上下文，默认开启思考模式",
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 65536,
|
||||
"serviceType": ["chat"],
|
||||
"description": "通义千问3.5旗舰模型，支持文本/图像/视频输入，效果媲美Qwen3 Max，性价比更优",
|
||||
"contextWindow": 262144,
|
||||
"maxOutputTokens": 16384,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -126,37 +42,16 @@
|
||||
],
|
||||
"inputPrice": 0.8,
|
||||
"outputPrice": 4.8,
|
||||
"defaultTemperature": 0.6,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"pricingTiers": [
|
||||
{
|
||||
"maxInputTokens": 128000,
|
||||
"inputPrice": 0.8,
|
||||
"outputPrice": 4.8
|
||||
},
|
||||
{
|
||||
"maxInputTokens": 256000,
|
||||
"inputPrice": 2,
|
||||
"outputPrice": 12
|
||||
},
|
||||
{
|
||||
"maxInputTokens": 1000000,
|
||||
"inputPrice": 4,
|
||||
"outputPrice": 24
|
||||
}
|
||||
],
|
||||
"thinkingMaxTokens": 81920
|
||||
}
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.8,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "qwen-max",
|
||||
"displayName": "阿里云 qwen-max",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "通义千问Max，千亿参数旗舰模型，32K 上下文",
|
||||
"contextWindow": 32768,
|
||||
"serviceType": ["chat"],
|
||||
"description": "通义千问Max，千亿参数旗舰模型，最强性能",
|
||||
"contextWindow": 131072,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
@@ -174,12 +69,10 @@
|
||||
{
|
||||
"modelName": "qwen-plus",
|
||||
"displayName": "阿里云 qwen-plus",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "通义千问Plus，支持思考模式，100万上下文",
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 32768,
|
||||
"serviceType": ["chat"],
|
||||
"description": "通义千问Plus，支持思考模式，128K 上下文",
|
||||
"contextWindow": 131072,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -188,66 +81,36 @@
|
||||
],
|
||||
"inputPrice": 0.8,
|
||||
"outputPrice": 2,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"pricingTiers": [
|
||||
{
|
||||
"maxInputTokens": 128000,
|
||||
"inputPrice": 0.8,
|
||||
"outputPrice": 2,
|
||||
"thinkingOutputPrice": 8
|
||||
},
|
||||
{
|
||||
"maxInputTokens": 256000,
|
||||
"inputPrice": 2.4,
|
||||
"outputPrice": 20,
|
||||
"thinkingOutputPrice": 24
|
||||
},
|
||||
{
|
||||
"maxInputTokens": 1000000,
|
||||
"inputPrice": 4.8,
|
||||
"outputPrice": 48,
|
||||
"thinkingOutputPrice": 64
|
||||
}
|
||||
],
|
||||
"thinkingMaxTokens": 81920
|
||||
}
|
||||
"defaultTemperature": 0.6,
|
||||
"defaultTopP": 0.8,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "qwen-turbo",
|
||||
"displayName": "阿里云 qwen-turbo",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "通义千问Turbo，非思考模式支持100万上下文，思考模式支持131K上下文",
|
||||
"serviceType": ["chat"],
|
||||
"description": "通义千问Turbo，支持100万上下文，高性价比",
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 16384,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"code",
|
||||
"long_context",
|
||||
"fast"
|
||||
],
|
||||
"inputPrice": 0.367,
|
||||
"outputPrice": 1.468,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"thinkingContextWindow": 131072,
|
||||
"thinkingOutputPrice": 3.67,
|
||||
"thinkingMaxTokens": 38912
|
||||
}
|
||||
"inputPrice": 0.3,
|
||||
"outputPrice": 0.6,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.8,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "qwen-long",
|
||||
"displayName": "阿里云 qwen-long",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "通义千问Long，支持1000万上下文，适合超长文档处理，降价97%",
|
||||
"contextWindow": 10000000,
|
||||
"maxOutputTokens": 32768,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"ultra_long_context",
|
||||
@@ -255,16 +118,14 @@
|
||||
],
|
||||
"inputPrice": 0.5,
|
||||
"outputPrice": 2,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.8,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "qwen3-max",
|
||||
"displayName": "阿里云 Qwen3-Max",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "通义千问3代旗舰模型，262K 上下文，支持思考模式",
|
||||
"contextWindow": 262144,
|
||||
"maxOutputTokens": 65536,
|
||||
@@ -280,19 +141,17 @@
|
||||
],
|
||||
"inputPrice": 2.5,
|
||||
"outputPrice": 10,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.8,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "qwen3-vl-plus",
|
||||
"displayName": "阿里云 Qwen3-VL-Plus",
|
||||
"serviceType": [
|
||||
"vision"
|
||||
],
|
||||
"serviceType": ["vision"],
|
||||
"description": "通义千问3代视觉模型Plus版，支持图像理解",
|
||||
"contextWindow": 262144,
|
||||
"maxOutputTokens": 32768,
|
||||
"contextWindow": 131072,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"vision",
|
||||
@@ -302,19 +161,15 @@
|
||||
],
|
||||
"inputPrice": 1.5,
|
||||
"outputPrice": 6,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.8,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "qwen3-vl-flash",
|
||||
"displayName": "阿里云 Qwen3-VL-Flash",
|
||||
"serviceType": [
|
||||
"vision"
|
||||
],
|
||||
"serviceType": ["vision"],
|
||||
"description": "通义千问3代视觉模型Flash版，高性价比",
|
||||
"contextWindow": 262144,
|
||||
"maxOutputTokens": 32768,
|
||||
"contextWindow": 131072,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"vision",
|
||||
@@ -323,78 +178,57 @@
|
||||
],
|
||||
"inputPrice": 0.8,
|
||||
"outputPrice": 3,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.8,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "text-embedding-v3",
|
||||
"displayName": "text-embedding-v3",
|
||||
"serviceType": [
|
||||
"embedding"
|
||||
],
|
||||
"serviceType": ["embedding"],
|
||||
"description": "阿里云文本向量化",
|
||||
"contextWindow": 8192,
|
||||
"capabilities": [
|
||||
"text_embedding",
|
||||
"semantic_search",
|
||||
"chinese_optimized"
|
||||
],
|
||||
"inputPrice": 0.7,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "text-embedding-v4",
|
||||
"displayName": "阿里云 text-embedding-v4",
|
||||
"serviceType": [
|
||||
"embedding"
|
||||
],
|
||||
"serviceType": ["embedding"],
|
||||
"description": "阿里云百炼文本向量模型v4，支持多维度与多语种",
|
||||
"contextWindow": 8192,
|
||||
"capabilities": [
|
||||
"text_embedding",
|
||||
"semantic_search",
|
||||
"rag"
|
||||
],
|
||||
"inputPrice": 0.5,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "qwen3-rerank",
|
||||
"displayName": "Qwen3-Rerank",
|
||||
"serviceType": [
|
||||
"rerank"
|
||||
],
|
||||
"serviceType": ["rerank"],
|
||||
"description": "检索重排序，支持 100+ 语种",
|
||||
"contextWindow": 120000,
|
||||
"capabilities": [
|
||||
"rerank",
|
||||
"semantic_reranking",
|
||||
"multilingual"
|
||||
],
|
||||
"inputPrice": 1,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "cosyvoice-v2",
|
||||
"displayName": "CosyVoice V2",
|
||||
"serviceType": [
|
||||
"tts"
|
||||
],
|
||||
"serviceType": ["tts"],
|
||||
"description": "通义语音合成，支持中英文",
|
||||
"capabilities": [
|
||||
"tts",
|
||||
"multilingual",
|
||||
"chinese_optimized"
|
||||
],
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"voices": [
|
||||
"longxiaochun",
|
||||
@@ -412,16 +246,12 @@
|
||||
{
|
||||
"modelName": "paraformer-v2",
|
||||
"displayName": "Paraformer V2",
|
||||
"serviceType": [
|
||||
"asr"
|
||||
],
|
||||
"serviceType": ["asr"],
|
||||
"description": "通义语音识别",
|
||||
"capabilities": [
|
||||
"asr",
|
||||
"chinese_optimized"
|
||||
],
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"maxAudioLength": 3600,
|
||||
"supportedInputFormats": [
|
||||
@@ -436,16 +266,12 @@
|
||||
{
|
||||
"modelName": "wanx-v2",
|
||||
"displayName": "通义万相 V2",
|
||||
"serviceType": [
|
||||
"image_gen"
|
||||
],
|
||||
"serviceType": ["image_gen"],
|
||||
"description": "通义万相文生图",
|
||||
"capabilities": [
|
||||
"image_generation",
|
||||
"chinese_optimized"
|
||||
],
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"supportedImageSizes": [
|
||||
"1024x1024",
|
||||
@@ -463,16 +289,12 @@
|
||||
{
|
||||
"modelName": "wanx-video",
|
||||
"displayName": "通义万相视频",
|
||||
"serviceType": [
|
||||
"video_gen"
|
||||
],
|
||||
"serviceType": ["video_gen"],
|
||||
"description": "通义万相文生视频",
|
||||
"capabilities": [
|
||||
"video_generation",
|
||||
"chinese_optimized"
|
||||
],
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"maxVideoDuration": 10,
|
||||
"supportedResolutions": [
|
||||
@@ -484,17 +306,13 @@
|
||||
{
|
||||
"modelName": "cosyvoice-clone",
|
||||
"displayName": "CosyVoice 声音复刻",
|
||||
"serviceType": [
|
||||
"voice_clone"
|
||||
],
|
||||
"serviceType": ["voice_clone"],
|
||||
"description": "通义声音复刻，少量样本即可克隆",
|
||||
"capabilities": [
|
||||
"voice_clone",
|
||||
"chinese_optimized",
|
||||
"few_shot"
|
||||
],
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"maxCloneSamples": 5,
|
||||
"minCloneDuration": 3
|
||||
@@ -503,12 +321,9 @@
|
||||
{
|
||||
"modelName": "qwen-omni-turbo",
|
||||
"displayName": "Qwen-Omni-Turbo",
|
||||
"serviceType": [
|
||||
"omni"
|
||||
],
|
||||
"serviceType": ["omni"],
|
||||
"description": "通义全能模型，支持音视频文本多模态",
|
||||
"contextWindow": 32768,
|
||||
"maxOutputTokens": 2048,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"vision",
|
||||
@@ -517,26 +332,19 @@
|
||||
"multimodal",
|
||||
"tool_use"
|
||||
],
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": 0.01,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "qwen3-max-trans",
|
||||
"displayName": "Qwen3-Max（翻译）",
|
||||
"serviceType": [
|
||||
"translation"
|
||||
],
|
||||
"serviceType": ["translation"],
|
||||
"description": "通义千问翻译，中英日韩等多语种互译",
|
||||
"contextWindow": 131072,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"translation",
|
||||
"multilingual",
|
||||
"chinese_optimized"
|
||||
],
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {}
|
||||
}
|
||||
]
|
||||
|
||||
@@ -17,12 +17,10 @@
|
||||
{
|
||||
"modelName": "deepseek-chat",
|
||||
"displayName": "DeepSeek V3.2",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "高性价比通用对话模型，128K 上下文",
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 8192,
|
||||
"serviceType": ["chat"],
|
||||
"description": "高性价比通用对话模型，64K 上下文",
|
||||
"contextWindow": 64000,
|
||||
"maxOutputTokens": 8000,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"code",
|
||||
@@ -30,22 +28,18 @@
|
||||
"multilingual"
|
||||
],
|
||||
"inputPrice": 2,
|
||||
"outputPrice": 3,
|
||||
"outputPrice": 8,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {
|
||||
"cacheHitPrice": 0.2
|
||||
}
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "deepseek-reasoner",
|
||||
"displayName": "DeepSeek R1",
|
||||
"serviceType": [
|
||||
"reasoning"
|
||||
],
|
||||
"description": "DeepSeek V3.2 思考模式，128K 上下文，思维链默认 32K，最大输出 64K",
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 65536,
|
||||
"serviceType": ["reasoning"],
|
||||
"description": "DeepSeek R1 推理模型，64K 上下文，深度推理能力，思维链最长 32K",
|
||||
"contextWindow": 64000,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -55,11 +49,9 @@
|
||||
],
|
||||
"inputPrice": 4,
|
||||
"outputPrice": 16,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"cacheHitPrice": 0.2
|
||||
}
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -15,98 +15,12 @@
|
||||
"embedding"
|
||||
],
|
||||
"models": [
|
||||
{
|
||||
"modelName": "gemini-3.1-pro-preview",
|
||||
"displayName": "Gemini 3.1 Pro Preview",
|
||||
"serviceType": ["chat"],
|
||||
"description": "Google Gemini 3.1 Pro Preview，面向复杂推理、编码和智能体工作流",
|
||||
"contextWindow": 1048576,
|
||||
"maxOutputTokens": 65536,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"vision",
|
||||
"ultra_long_context",
|
||||
"tool_use"
|
||||
],
|
||||
"inputPrice": 2.00,
|
||||
"outputPrice": 12.00,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"pricingNotes": "Standard paid tier text/image/video price for prompts <= 200K tokens; prompts > 200K are $4 input and $18 output per 1M tokens.",
|
||||
"cachePricing": {
|
||||
"inputCacheRead": 0.20,
|
||||
"inputCacheReadOver200k": 0.40,
|
||||
"storagePerMillionTokensPerHour": 4.50
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "gemini-3-flash-preview",
|
||||
"displayName": "Gemini 3 Flash Preview",
|
||||
"serviceType": ["chat"],
|
||||
"description": "Google Gemini 3 Flash Preview，高速多模态推理模型",
|
||||
"contextWindow": 1048576,
|
||||
"maxOutputTokens": 65536,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"vision",
|
||||
"ultra_long_context",
|
||||
"tool_use",
|
||||
"fast"
|
||||
],
|
||||
"inputPrice": 0.50,
|
||||
"outputPrice": 3.00,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"pricingNotes": "Standard paid tier text/image/video price; audio input is $1.00 per 1M tokens.",
|
||||
"cachePricing": {
|
||||
"inputCacheRead": 0.05,
|
||||
"audioInputCacheRead": 0.10,
|
||||
"storagePerMillionTokensPerHour": 1.00
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "gemini-3.1-flash-lite-preview",
|
||||
"displayName": "Gemini 3.1 Flash-Lite Preview",
|
||||
"serviceType": ["fast"],
|
||||
"description": "Google Gemini 3.1 Flash-Lite Preview，低成本高吞吐多模态模型",
|
||||
"contextWindow": 1048576,
|
||||
"maxOutputTokens": 65536,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"vision",
|
||||
"ultra_long_context",
|
||||
"tool_use",
|
||||
"fast"
|
||||
],
|
||||
"inputPrice": 0.25,
|
||||
"outputPrice": 1.50,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"pricingNotes": "Standard paid tier text/image/video price; audio input is $0.50 per 1M tokens.",
|
||||
"cachePricing": {
|
||||
"inputCacheRead": 0.025,
|
||||
"audioInputCacheRead": 0.05,
|
||||
"storagePerMillionTokensPerHour": 1.00
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "gemini-2.5-pro",
|
||||
"displayName": "Gemini 2.5 Pro",
|
||||
"serviceType": ["chat"],
|
||||
"description": "Google 最新旗舰模型，1,048,576 token 上下文，多模态",
|
||||
"contextWindow": 1048576,
|
||||
"description": "Google 最新旗舰模型，100万上下文，多模态",
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 65536,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
@@ -118,7 +32,7 @@
|
||||
],
|
||||
"inputPrice": 1.25,
|
||||
"outputPrice": 10,
|
||||
"defaultTemperature": null,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {}
|
||||
},
|
||||
@@ -126,8 +40,8 @@
|
||||
"modelName": "gemini-2.5-flash",
|
||||
"displayName": "Gemini 2.5 Flash",
|
||||
"serviceType": ["chat"],
|
||||
"description": "Google 高性价比模型，1,048,576 token 上下文，速度快",
|
||||
"contextWindow": 1048576,
|
||||
"description": "Google 高性价比模型，100万上下文，速度快",
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 65536,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
@@ -140,7 +54,7 @@
|
||||
],
|
||||
"inputPrice": 0.30,
|
||||
"outputPrice": 2.50,
|
||||
"defaultTemperature": null,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {}
|
||||
},
|
||||
@@ -149,14 +63,11 @@
|
||||
"displayName": "Text Embedding 005",
|
||||
"serviceType": ["embedding"],
|
||||
"description": "Google 文本嵌入模型，768维度",
|
||||
"contextWindow": 2048,
|
||||
"capabilities": [
|
||||
"text_embedding",
|
||||
"semantic_search"
|
||||
],
|
||||
"inputPrice": 0.10,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {}
|
||||
}
|
||||
]
|
||||
|
||||
@@ -23,7 +23,7 @@
|
||||
"chat"
|
||||
],
|
||||
"description": "MiniMax M2.7 高速版，低延迟吞吐优化，200K 上下文",
|
||||
"contextWindow": 204800,
|
||||
"contextWindow": 200000,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
@@ -33,7 +33,6 @@
|
||||
"inputPrice": 0,
|
||||
"outputPrice": 0,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
@@ -42,9 +41,9 @@
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "智谱 GLM-5.1 新一代旗舰模型，编程与推理能力断档领先，200K 上下文",
|
||||
"contextWindow": 200000,
|
||||
"maxOutputTokens": 128000,
|
||||
"description": "智谱 GLM-5.1 新一代旗舰模型，编程与推理能力断档领先，204K 上下文",
|
||||
"contextWindow": 204800,
|
||||
"maxOutputTokens": 131072,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -55,8 +54,7 @@
|
||||
],
|
||||
"inputPrice": 0,
|
||||
"outputPrice": 0,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"defaultTemperature": 0.95,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
@@ -65,9 +63,9 @@
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "智谱 GLM-5 大语言模型，200K 上下文",
|
||||
"contextWindow": 200000,
|
||||
"maxOutputTokens": 128000,
|
||||
"description": "智谱 GLM-5 大语言模型",
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -76,7 +74,6 @@
|
||||
"inputPrice": 0,
|
||||
"outputPrice": 0,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
@@ -86,8 +83,8 @@
|
||||
"chat"
|
||||
],
|
||||
"description": "智谱 GLM-5-Turbo 大语言模型，更快的推理速度",
|
||||
"contextWindow": 200000,
|
||||
"maxOutputTokens": 128000,
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -96,7 +93,6 @@
|
||||
"inputPrice": 0,
|
||||
"outputPrice": 0,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
@@ -116,7 +112,6 @@
|
||||
"inputPrice": 0,
|
||||
"outputPrice": 0,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
@@ -127,7 +122,7 @@
|
||||
],
|
||||
"description": "月之暗面 Kimi K2.6 Code Preview，万亿参数 MoE 架构（32B 激活），256K 上下文，代码与智能体能力增强",
|
||||
"contextWindow": 256000,
|
||||
"maxOutputTokens": 32768,
|
||||
"maxOutputTokens": 16384,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -139,8 +134,7 @@
|
||||
],
|
||||
"inputPrice": 0,
|
||||
"outputPrice": 0,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"defaultTemperature": 0.7,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
@@ -150,8 +144,8 @@
|
||||
"chat"
|
||||
],
|
||||
"description": "月之暗面 Kimi-2.5 大语言模型",
|
||||
"contextWindow": 256000,
|
||||
"maxOutputTokens": 32768,
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -164,7 +158,6 @@
|
||||
"inputPrice": 0,
|
||||
"outputPrice": 0,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
@@ -174,7 +167,7 @@
|
||||
"chat"
|
||||
],
|
||||
"description": "MiniMax M2.5 大语言模型",
|
||||
"contextWindow": 204800,
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
@@ -186,7 +179,6 @@
|
||||
"inputPrice": 0,
|
||||
"outputPrice": 0,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
@@ -210,7 +202,6 @@
|
||||
"inputPrice": 0,
|
||||
"outputPrice": 0,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.8,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
@@ -220,8 +211,8 @@
|
||||
"chat"
|
||||
],
|
||||
"description": "阿里通义千问 Qwen3.5 Plus",
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 65536,
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -233,8 +224,7 @@
|
||||
],
|
||||
"inputPrice": 0,
|
||||
"outputPrice": 0,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.8,
|
||||
"defaultTemperature": 1,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
@@ -256,7 +246,6 @@
|
||||
"inputPrice": 0,
|
||||
"outputPrice": 0,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.8,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
@@ -278,7 +267,6 @@
|
||||
"inputPrice": 0,
|
||||
"outputPrice": 0,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.8,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
@@ -288,8 +276,8 @@
|
||||
"chat"
|
||||
],
|
||||
"description": "阿里通义千问 Qwen3 Max (2026-01-23)",
|
||||
"contextWindow": 262144,
|
||||
"maxOutputTokens": 32768,
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -301,8 +289,7 @@
|
||||
],
|
||||
"inputPrice": 0,
|
||||
"outputPrice": 0,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.8,
|
||||
"defaultTemperature": 1,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
@@ -312,8 +299,8 @@
|
||||
"chat"
|
||||
],
|
||||
"description": "字节跳动豆包 Seed 2.0 Code Preview (260215)",
|
||||
"contextWindow": 256000,
|
||||
"maxOutputTokens": 128000,
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -322,7 +309,6 @@
|
||||
"inputPrice": 0,
|
||||
"outputPrice": 0,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.7,
|
||||
"extra": {}
|
||||
}
|
||||
]
|
||||
|
||||
@@ -30,8 +30,8 @@
|
||||
],
|
||||
"inputPrice": 0.99,
|
||||
"outputPrice": 0.99,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.9,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
@@ -51,8 +51,8 @@
|
||||
],
|
||||
"inputPrice": 6,
|
||||
"outputPrice": 6,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.9,
|
||||
"extra": {}
|
||||
}
|
||||
]
|
||||
|
||||
@@ -9,19 +9,12 @@
|
||||
"enabled": false,
|
||||
"status": "unconfigured",
|
||||
"priceCurrency": "CNY",
|
||||
"services": [
|
||||
"chat",
|
||||
"fast",
|
||||
"reasoning"
|
||||
],
|
||||
"services": ["chat", "fast", "reasoning"],
|
||||
"models": [
|
||||
{
|
||||
"modelName": "MiniMax-M2.7",
|
||||
"displayName": "MiniMax M2.7",
|
||||
"serviceType": [
|
||||
"chat",
|
||||
"reasoning"
|
||||
],
|
||||
"serviceType": ["chat", "reasoning"],
|
||||
"description": "MiniMax 新一代旗舰模型，擅长复杂 Agent、软件工程与专业办公任务",
|
||||
"contextWindow": 204800,
|
||||
"maxOutputTokens": 131072,
|
||||
@@ -31,22 +24,14 @@
|
||||
"code",
|
||||
"tool_use"
|
||||
],
|
||||
"inputPrice": 2.1,
|
||||
"outputPrice": 8.4,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"cacheReadPrice": 0.42,
|
||||
"cacheWritePrice": 2.625,
|
||||
"outputSpeedTps": 60
|
||||
}
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "MiniMax-M2.7-highspeed",
|
||||
"displayName": "MiniMax M2.7 高速版",
|
||||
"serviceType": [
|
||||
"fast"
|
||||
],
|
||||
"serviceType": ["fast"],
|
||||
"description": "MiniMax M2.7 极速版，效果一致，输出更快，适合低延迟场景",
|
||||
"contextWindow": 204800,
|
||||
"maxOutputTokens": 131072,
|
||||
@@ -57,25 +42,16 @@
|
||||
"tool_use",
|
||||
"fast"
|
||||
],
|
||||
"inputPrice": 4.2,
|
||||
"outputPrice": 16.8,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"cacheReadPrice": 0.42,
|
||||
"cacheWritePrice": 2.625,
|
||||
"outputSpeedTps": 100
|
||||
}
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "MiniMax-M2.5",
|
||||
"displayName": "MiniMax M2.5",
|
||||
"serviceType": [
|
||||
"chat",
|
||||
"reasoning"
|
||||
],
|
||||
"description": "MiniMax M2.5，204.8K 上下文，支持深度推理和工具调用",
|
||||
"contextWindow": 204800,
|
||||
"serviceType": ["chat", "reasoning"],
|
||||
"description": "MiniMax 最新旗舰模型，230B参数(10B激活)MoE架构，百万级上下文，支持深度推理和工具调用",
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 131072,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
@@ -87,21 +63,15 @@
|
||||
"inputPrice": 2.1,
|
||||
"outputPrice": 8.4,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"cacheReadPrice": 0.21,
|
||||
"cacheWritePrice": 2.625,
|
||||
"outputSpeedTps": 60
|
||||
}
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "MiniMax-M2.5-highspeed",
|
||||
"displayName": "MiniMax M2.5 高速版",
|
||||
"serviceType": [
|
||||
"fast"
|
||||
],
|
||||
"serviceType": ["fast"],
|
||||
"description": "MiniMax M2.5 高速推理版本(100TPS)，适合低延迟场景",
|
||||
"contextWindow": 204800,
|
||||
"contextWindow": 200000,
|
||||
"maxOutputTokens": 131072,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
@@ -110,22 +80,16 @@
|
||||
"tool_use",
|
||||
"fast"
|
||||
],
|
||||
"inputPrice": 4.2,
|
||||
"inputPrice": 2.1,
|
||||
"outputPrice": 16.8,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"cacheReadPrice": 0.21,
|
||||
"cacheWritePrice": 2.625,
|
||||
"outputSpeedTps": 100
|
||||
}
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "MiniMax-M2.1",
|
||||
"displayName": "MiniMax M2.1",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "MiniMax 上一代主力模型，200K 上下文，性价比优秀",
|
||||
"contextWindow": 204800,
|
||||
"maxOutputTokens": 131072,
|
||||
@@ -138,19 +102,13 @@
|
||||
"inputPrice": 2.1,
|
||||
"outputPrice": 8.4,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"cacheReadPrice": 0.21,
|
||||
"cacheWritePrice": 2.625,
|
||||
"outputSpeedTps": 60
|
||||
}
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "MiniMax-M2.1-highspeed",
|
||||
"displayName": "MiniMax M2.1 高速版",
|
||||
"serviceType": [
|
||||
"fast"
|
||||
],
|
||||
"serviceType": ["fast"],
|
||||
"description": "MiniMax M2.1 高速推理版本，适合低延迟场景",
|
||||
"contextWindow": 204800,
|
||||
"maxOutputTokens": 131072,
|
||||
@@ -161,22 +119,16 @@
|
||||
"tool_use",
|
||||
"fast"
|
||||
],
|
||||
"inputPrice": 4.2,
|
||||
"inputPrice": 2.1,
|
||||
"outputPrice": 16.8,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"cacheReadPrice": 0.21,
|
||||
"cacheWritePrice": 2.625,
|
||||
"outputSpeedTps": 100
|
||||
}
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "MiniMax-Text-01",
|
||||
"displayName": "MiniMax Text 01",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "MiniMax 百万级长上下文文本模型，擅长长文档处理",
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 131072,
|
||||
@@ -188,8 +140,8 @@
|
||||
],
|
||||
"inputPrice": 1.4,
|
||||
"outputPrice": 7.7,
|
||||
"defaultTemperature": 0.1,
|
||||
"defaultTopP": 0.95,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
}
|
||||
]
|
||||
|
||||
@@ -9,17 +9,12 @@
|
||||
"enabled": false,
|
||||
"status": "unconfigured",
|
||||
"priceCurrency": "USD",
|
||||
"services": [
|
||||
"chat",
|
||||
"fast"
|
||||
],
|
||||
"services": ["chat", "fast"],
|
||||
"models": [
|
||||
{
|
||||
"modelName": "mistral-large-latest",
|
||||
"displayName": "Mistral Large 3",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "Mistral 旗舰模型，256K 上下文，支持视觉和工具调用",
|
||||
"contextWindow": 256000,
|
||||
"maxOutputTokens": 262144,
|
||||
@@ -31,20 +26,18 @@
|
||||
"tool_use",
|
||||
"long_context"
|
||||
],
|
||||
"inputPrice": 0.5,
|
||||
"outputPrice": 1.5,
|
||||
"defaultTemperature": null,
|
||||
"inputPrice": 0.50,
|
||||
"outputPrice": 1.50,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "mistral-small-latest",
|
||||
"displayName": "Mistral Small 3.2",
|
||||
"serviceType": [
|
||||
"fast"
|
||||
],
|
||||
"serviceType": ["fast"],
|
||||
"description": "Mistral 高效小模型，低延迟，适合快速推理场景",
|
||||
"contextWindow": 128000,
|
||||
"contextWindow": 130000,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
@@ -54,28 +47,26 @@
|
||||
"fast",
|
||||
"tool_use"
|
||||
],
|
||||
"inputPrice": 0.1,
|
||||
"outputPrice": 0.3,
|
||||
"defaultTemperature": null,
|
||||
"inputPrice": 0.10,
|
||||
"outputPrice": 0.30,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "codestral-latest",
|
||||
"displayName": "Codestral",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "Mistral 专业代码模型，支持 Fill-in-the-Middle 补全",
|
||||
"contextWindow": 128000,
|
||||
"contextWindow": 256000,
|
||||
"maxOutputTokens": 32768,
|
||||
"capabilities": [
|
||||
"code",
|
||||
"fill_in_the_middle"
|
||||
],
|
||||
"inputPrice": 0.3,
|
||||
"outputPrice": 0.9,
|
||||
"defaultTemperature": null,
|
||||
"inputPrice": 0.30,
|
||||
"outputPrice": 0.90,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
}
|
||||
|
||||
@@ -14,64 +14,13 @@
|
||||
"reasoning"
|
||||
],
|
||||
"models": [
|
||||
{
|
||||
"modelName": "kimi-k2.6",
|
||||
"displayName": "Kimi K2.6",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "月之暗面 Kimi K2.6，最新多模态模型，长程代码编写与 Agent 自主执行能力增强，256K 上下文，支持思考/非思考模式",
|
||||
"contextWindow": 256000,
|
||||
"maxOutputTokens": 32768,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"tool_use",
|
||||
"agent",
|
||||
"long_context",
|
||||
"vision",
|
||||
"video_understanding",
|
||||
"image_understanding"
|
||||
],
|
||||
"inputPrice": 6.5,
|
||||
"outputPrice": 27,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"thinking": {
|
||||
"default": "enabled",
|
||||
"disabledTemperature": 0.6
|
||||
},
|
||||
"cacheHitPrice": 1.1,
|
||||
"supportedImageFormats": [
|
||||
"png",
|
||||
"jpeg",
|
||||
"webp",
|
||||
"gif"
|
||||
],
|
||||
"supportedVideoFormats": [
|
||||
"mp4",
|
||||
"mpeg",
|
||||
"mov",
|
||||
"avi",
|
||||
"x-flv",
|
||||
"mpg",
|
||||
"webm",
|
||||
"wmv",
|
||||
"3gpp"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "kimi-k2.5",
|
||||
"displayName": "Kimi K2.5",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "月之暗面Kimi K2.5，原生多模态模型，256K 上下文，支持思考/非思考模式",
|
||||
"serviceType": ["chat"],
|
||||
"description": "月之暗面Kimi K2.5，2026年1月发布的原生多模态模型，支持视觉编码和智能体集群",
|
||||
"contextWindow": 256000,
|
||||
"maxOutputTokens": 32768,
|
||||
"maxOutputTokens": 16384,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -83,40 +32,15 @@
|
||||
],
|
||||
"inputPrice": 4,
|
||||
"outputPrice": 21,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"thinking": {
|
||||
"default": "enabled",
|
||||
"disabledTemperature": 0.6
|
||||
},
|
||||
"cacheHitPrice": 0.7,
|
||||
"supportedImageFormats": [
|
||||
"png",
|
||||
"jpeg",
|
||||
"webp",
|
||||
"gif"
|
||||
],
|
||||
"supportedVideoFormats": [
|
||||
"mp4",
|
||||
"mpeg",
|
||||
"mov",
|
||||
"avi",
|
||||
"x-flv",
|
||||
"mpg",
|
||||
"webm",
|
||||
"wmv",
|
||||
"3gpp"
|
||||
]
|
||||
}
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.9,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "kimi-k2",
|
||||
"displayName": "Kimi K2",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "月之暗面Kimi K2，万亿参数MoE模型(32B激活)，256K上下文，专为智能体设计",
|
||||
"serviceType": ["chat"],
|
||||
"description": "月之暗面Kimi K2，万亿参数MoE模型(320B激活)，256K上下文，专为智能体设计",
|
||||
"contextWindow": 256000,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
@@ -125,22 +49,19 @@
|
||||
"code",
|
||||
"tool_use",
|
||||
"agent",
|
||||
"long_context"
|
||||
"long_context",
|
||||
"vision"
|
||||
],
|
||||
"inputPrice": 4,
|
||||
"outputPrice": 16,
|
||||
"defaultTemperature": 0.6,
|
||||
"defaultTopP": 1,
|
||||
"extra": {
|
||||
"cacheHitPrice": 1
|
||||
}
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.9,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "kimi-k2-thinking",
|
||||
"displayName": "Kimi K2 思考版",
|
||||
"serviceType": [
|
||||
"reasoning"
|
||||
],
|
||||
"serviceType": ["reasoning"],
|
||||
"description": "月之暗面Kimi K2思考版，256K上下文，深度推理能力",
|
||||
"contextWindow": 256000,
|
||||
"maxOutputTokens": 16384,
|
||||
@@ -153,18 +74,14 @@
|
||||
],
|
||||
"inputPrice": 4,
|
||||
"outputPrice": 16,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {
|
||||
"cacheHitPrice": 1
|
||||
}
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.9,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "moonshot-v1-8k",
|
||||
"displayName": "Moonshot V1 8K",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "月之暗面标准模型，8K上下文",
|
||||
"contextWindow": 8192,
|
||||
"maxOutputTokens": 4096,
|
||||
@@ -174,16 +91,14 @@
|
||||
],
|
||||
"inputPrice": 2,
|
||||
"outputPrice": 2,
|
||||
"defaultTemperature": 0,
|
||||
"defaultTopP": 1,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.9,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "moonshot-v1-32k",
|
||||
"displayName": "Moonshot V1 32K",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "月之暗面标准模型，32K上下文",
|
||||
"contextWindow": 32768,
|
||||
"maxOutputTokens": 4096,
|
||||
@@ -194,16 +109,14 @@
|
||||
],
|
||||
"inputPrice": 5,
|
||||
"outputPrice": 5,
|
||||
"defaultTemperature": 0,
|
||||
"defaultTopP": 1,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.9,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "moonshot-v1-128k",
|
||||
"displayName": "Moonshot V1 128K",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "月之暗面标准模型，128K上下文",
|
||||
"contextWindow": 131072,
|
||||
"maxOutputTokens": 4096,
|
||||
@@ -214,8 +127,8 @@
|
||||
],
|
||||
"inputPrice": 10,
|
||||
"outputPrice": 10,
|
||||
"defaultTemperature": 0,
|
||||
"defaultTopP": 1,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.9,
|
||||
"extra": {}
|
||||
}
|
||||
]
|
||||
|
||||
@@ -19,14 +19,11 @@
|
||||
"serviceType": ["chat"],
|
||||
"description": "本地运行的 Llama 3.1 70B",
|
||||
"contextWindow": 131072,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"code",
|
||||
"reasoning"
|
||||
],
|
||||
"defaultTemperature": 0.8,
|
||||
"defaultTopP": 0.9,
|
||||
"extra": {}
|
||||
}
|
||||
]
|
||||
|
||||
@@ -25,9 +25,7 @@
|
||||
{
|
||||
"modelName": "gpt-5.2",
|
||||
"displayName": "GPT-5.2",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "OpenAI 最新旗舰模型，400K 上下文，编码和智能体任务优化",
|
||||
"contextWindow": 400000,
|
||||
"maxOutputTokens": 128000,
|
||||
@@ -48,9 +46,7 @@
|
||||
{
|
||||
"modelName": "gpt-5.2-pro",
|
||||
"displayName": "GPT-5.2 Pro",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "OpenAI GPT-5.2 Pro 专业版，最高性能",
|
||||
"contextWindow": 400000,
|
||||
"maxOutputTokens": 128000,
|
||||
@@ -71,9 +67,7 @@
|
||||
{
|
||||
"modelName": "gpt-5.1",
|
||||
"displayName": "GPT-5.1",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "OpenAI GPT-5.1，400K 上下文，高性能旗舰",
|
||||
"contextWindow": 400000,
|
||||
"maxOutputTokens": 128000,
|
||||
@@ -94,9 +88,7 @@
|
||||
{
|
||||
"modelName": "gpt-5",
|
||||
"displayName": "GPT-5",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "OpenAI GPT-5 新一代旗舰模型，统一所有模型能力",
|
||||
"contextWindow": 400000,
|
||||
"maxOutputTokens": 128000,
|
||||
@@ -117,12 +109,10 @@
|
||||
{
|
||||
"modelName": "gpt-5-pro",
|
||||
"displayName": "GPT-5 Pro",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "OpenAI GPT-5 Pro 专业版高性能推理模型",
|
||||
"serviceType": ["chat"],
|
||||
"description": "OpenAI GPT-5 Pro 专业版高性能模型",
|
||||
"contextWindow": 400000,
|
||||
"maxOutputTokens": 272000,
|
||||
"maxOutputTokens": 128000,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -140,12 +130,10 @@
|
||||
{
|
||||
"modelName": "gpt-5-mini",
|
||||
"displayName": "GPT-5-mini",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "高性价比模型，适合日常对话，400K 上下文",
|
||||
"contextWindow": 400000,
|
||||
"maxOutputTokens": 128000,
|
||||
"serviceType": ["chat"],
|
||||
"description": "高性价比模型，适合日常对话",
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 32768,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"fast",
|
||||
@@ -162,19 +150,17 @@
|
||||
{
|
||||
"modelName": "gpt-5-nano",
|
||||
"displayName": "GPT-5-nano",
|
||||
"serviceType": [
|
||||
"fast"
|
||||
],
|
||||
"description": "极速响应模型，适合简单任务，400K 上下文",
|
||||
"contextWindow": 400000,
|
||||
"maxOutputTokens": 128000,
|
||||
"serviceType": ["fast"],
|
||||
"description": "极速响应模型，适合简单任务",
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 16384,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"code",
|
||||
"fast"
|
||||
],
|
||||
"inputPrice": 0.05,
|
||||
"outputPrice": 0.4,
|
||||
"inputPrice": 0.02,
|
||||
"outputPrice": 0.08,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
@@ -182,11 +168,9 @@
|
||||
{
|
||||
"modelName": "gpt-4.1",
|
||||
"displayName": "GPT-4.1",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "OpenAI GPT-4.1，支持 1M 上下文，编码和指令遵循能力大幅提升",
|
||||
"contextWindow": 1047576,
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 32768,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
@@ -196,8 +180,8 @@
|
||||
"ultra_long_context",
|
||||
"tool_use"
|
||||
],
|
||||
"inputPrice": 2,
|
||||
"outputPrice": 8,
|
||||
"inputPrice": 2.00,
|
||||
"outputPrice": 8.00,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
@@ -205,11 +189,9 @@
|
||||
{
|
||||
"modelName": "gpt-4.1-mini",
|
||||
"displayName": "GPT-4.1 mini",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "OpenAI GPT-4.1 mini，1M 上下文，高性价比",
|
||||
"contextWindow": 1047576,
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 32768,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
@@ -218,8 +200,8 @@
|
||||
"ultra_long_context",
|
||||
"tool_use"
|
||||
],
|
||||
"inputPrice": 0.4,
|
||||
"outputPrice": 1.6,
|
||||
"inputPrice": 0.40,
|
||||
"outputPrice": 1.60,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
@@ -227,11 +209,9 @@
|
||||
{
|
||||
"modelName": "gpt-4.1-nano",
|
||||
"displayName": "GPT-4.1 nano",
|
||||
"serviceType": [
|
||||
"fast"
|
||||
],
|
||||
"serviceType": ["fast"],
|
||||
"description": "OpenAI GPT-4.1 nano，1M 上下文，极致性价比",
|
||||
"contextWindow": 1047576,
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 32768,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
@@ -239,8 +219,8 @@
|
||||
"ultra_long_context",
|
||||
"fast"
|
||||
],
|
||||
"inputPrice": 0.1,
|
||||
"outputPrice": 0.4,
|
||||
"inputPrice": 0.10,
|
||||
"outputPrice": 0.40,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
@@ -248,9 +228,7 @@
|
||||
{
|
||||
"modelName": "gpt-4o",
|
||||
"displayName": "GPT-4o",
|
||||
"serviceType": [
|
||||
"vision"
|
||||
],
|
||||
"serviceType": ["vision"],
|
||||
"description": "多模态模型，支持图像理解",
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 16384,
|
||||
@@ -260,8 +238,8 @@
|
||||
"image_understanding",
|
||||
"tool_use"
|
||||
],
|
||||
"inputPrice": 2.5,
|
||||
"outputPrice": 10,
|
||||
"inputPrice": 2.50,
|
||||
"outputPrice": 10.00,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
@@ -269,9 +247,7 @@
|
||||
{
|
||||
"modelName": "gpt-4o-mini",
|
||||
"displayName": "GPT-4o mini",
|
||||
"serviceType": [
|
||||
"vision"
|
||||
],
|
||||
"serviceType": ["vision"],
|
||||
"description": "OpenAI GPT-4o mini，高性价比多模态模型",
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 16384,
|
||||
@@ -282,7 +258,7 @@
|
||||
"tool_use"
|
||||
],
|
||||
"inputPrice": 0.15,
|
||||
"outputPrice": 0.6,
|
||||
"outputPrice": 0.60,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
@@ -290,50 +266,35 @@
|
||||
{
|
||||
"modelName": "text-embedding-3-small",
|
||||
"displayName": "text-embedding-3-small",
|
||||
"serviceType": [
|
||||
"embedding"
|
||||
],
|
||||
"serviceType": ["embedding"],
|
||||
"description": "轻量文本向量化模型，1536 维",
|
||||
"contextWindow": 8192,
|
||||
"capabilities": [
|
||||
"text_embedding",
|
||||
"semantic_search"
|
||||
],
|
||||
"inputPrice": 0.02,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "text-embedding-3-large",
|
||||
"displayName": "text-embedding-3-large",
|
||||
"serviceType": [
|
||||
"embedding"
|
||||
],
|
||||
"serviceType": ["embedding"],
|
||||
"description": "高精度文本向量化模型，3072 维",
|
||||
"contextWindow": 8192,
|
||||
"capabilities": [
|
||||
"text_embedding",
|
||||
"semantic_search"
|
||||
],
|
||||
"inputPrice": 0.13,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "tts-1",
|
||||
"displayName": "TTS-1",
|
||||
"serviceType": [
|
||||
"tts"
|
||||
],
|
||||
"serviceType": ["tts"],
|
||||
"description": "标准语音合成",
|
||||
"capabilities": [
|
||||
"tts"
|
||||
],
|
||||
"inputPrice": 15,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"voices": [
|
||||
"alloy",
|
||||
@@ -354,16 +315,11 @@
|
||||
{
|
||||
"modelName": "tts-1-hd",
|
||||
"displayName": "TTS-1-HD",
|
||||
"serviceType": [
|
||||
"tts"
|
||||
],
|
||||
"serviceType": ["tts"],
|
||||
"description": "高清语音合成",
|
||||
"capabilities": [
|
||||
"tts"
|
||||
],
|
||||
"inputPrice": 30,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"voices": [
|
||||
"alloy",
|
||||
@@ -384,17 +340,12 @@
|
||||
{
|
||||
"modelName": "whisper-1",
|
||||
"displayName": "Whisper",
|
||||
"serviceType": [
|
||||
"asr"
|
||||
],
|
||||
"serviceType": ["asr"],
|
||||
"description": "通用语音识别",
|
||||
"capabilities": [
|
||||
"asr",
|
||||
"multilingual"
|
||||
],
|
||||
"inputPrice": 0.006,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"maxAudioLength": 600,
|
||||
"supportedInputFormats": [
|
||||
@@ -412,9 +363,7 @@
|
||||
{
|
||||
"modelName": "o3",
|
||||
"displayName": "o3",
|
||||
"serviceType": [
|
||||
"responses"
|
||||
],
|
||||
"serviceType": ["responses"],
|
||||
"description": "OpenAI o3 推理模型，200K 上下文，支持工具调用",
|
||||
"contextWindow": 200000,
|
||||
"maxOutputTokens": 100000,
|
||||
@@ -426,8 +375,8 @@
|
||||
"science",
|
||||
"tool_use"
|
||||
],
|
||||
"inputPrice": 2,
|
||||
"outputPrice": 8,
|
||||
"inputPrice": 2.00,
|
||||
"outputPrice": 8.00,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
@@ -435,9 +384,7 @@
|
||||
{
|
||||
"modelName": "o3-pro",
|
||||
"displayName": "o3-pro",
|
||||
"serviceType": [
|
||||
"responses"
|
||||
],
|
||||
"serviceType": ["responses"],
|
||||
"description": "OpenAI o3-pro 高级推理模型，200K 上下文",
|
||||
"contextWindow": 200000,
|
||||
"maxOutputTokens": 100000,
|
||||
@@ -448,8 +395,8 @@
|
||||
"math",
|
||||
"science"
|
||||
],
|
||||
"inputPrice": 20,
|
||||
"outputPrice": 80,
|
||||
"inputPrice": 20.00,
|
||||
"outputPrice": 80.00,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
@@ -457,11 +404,9 @@
|
||||
{
|
||||
"modelName": "o3-mini",
|
||||
"displayName": "o3-mini",
|
||||
"serviceType": [
|
||||
"responses"
|
||||
],
|
||||
"description": "OpenAI o3-mini 推理模型，200K 上下文",
|
||||
"contextWindow": 200000,
|
||||
"serviceType": ["responses"],
|
||||
"description": "OpenAI o3-mini 推理模型，128K 上下文",
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 100000,
|
||||
"capabilities": [
|
||||
"reasoning",
|
||||
@@ -469,8 +414,8 @@
|
||||
"code",
|
||||
"fast"
|
||||
],
|
||||
"inputPrice": 1.1,
|
||||
"outputPrice": 4.4,
|
||||
"inputPrice": 1.10,
|
||||
"outputPrice": 4.40,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
@@ -478,9 +423,7 @@
|
||||
{
|
||||
"modelName": "o4-mini",
|
||||
"displayName": "o4-mini",
|
||||
"serviceType": [
|
||||
"responses"
|
||||
],
|
||||
"serviceType": ["responses"],
|
||||
"description": "OpenAI o4-mini 推理模型，200K 上下文，支持工具调用",
|
||||
"contextWindow": 200000,
|
||||
"maxOutputTokens": 100000,
|
||||
@@ -491,8 +434,8 @@
|
||||
"tool_use",
|
||||
"vision"
|
||||
],
|
||||
"inputPrice": 1.1,
|
||||
"outputPrice": 4.4,
|
||||
"inputPrice": 1.10,
|
||||
"outputPrice": 4.40,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
@@ -500,16 +443,12 @@
|
||||
{
|
||||
"modelName": "dall-e-3",
|
||||
"displayName": "DALL-E 3",
|
||||
"serviceType": [
|
||||
"image_gen"
|
||||
],
|
||||
"serviceType": ["image_gen"],
|
||||
"description": "高质量文生图模型",
|
||||
"capabilities": [
|
||||
"image_generation",
|
||||
"text_rendering"
|
||||
],
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"supportedImageSizes": [
|
||||
"1024x1024",
|
||||
@@ -525,12 +464,9 @@
|
||||
{
|
||||
"modelName": "gpt-4o-realtime",
|
||||
"displayName": "GPT-4o Realtime",
|
||||
"serviceType": [
|
||||
"omni"
|
||||
],
|
||||
"serviceType": ["omni"],
|
||||
"description": "全能实时模型，支持语音 + 文本 + 视觉",
|
||||
"contextWindow": 32000,
|
||||
"maxOutputTokens": 4096,
|
||||
"contextWindow": 128000,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"vision",
|
||||
@@ -538,10 +474,6 @@
|
||||
"asr",
|
||||
"realtime"
|
||||
],
|
||||
"inputPrice": 4,
|
||||
"outputPrice": 16,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"supportedModes": [
|
||||
"speech-to-speech",
|
||||
@@ -553,21 +485,13 @@
|
||||
{
|
||||
"modelName": "gpt-4o-realtime-preview",
|
||||
"displayName": "GPT-4o Realtime Preview",
|
||||
"serviceType": [
|
||||
"realtime_voice"
|
||||
],
|
||||
"serviceType": ["realtime_voice"],
|
||||
"description": "实时语音交互模型",
|
||||
"contextWindow": 32000,
|
||||
"maxOutputTokens": 4096,
|
||||
"capabilities": [
|
||||
"realtime",
|
||||
"speech_to_speech",
|
||||
"low_latency"
|
||||
],
|
||||
"inputPrice": 5,
|
||||
"outputPrice": 20,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"supportedModes": [
|
||||
"speech-to-speech",
|
||||
|
||||
@@ -16,7 +16,7 @@
|
||||
"displayName": "OpenRouter Auto",
|
||||
"serviceType": ["chat"],
|
||||
"description": "OpenRouter 自动路由，智能选择最优模型",
|
||||
"contextWindow": 2000000,
|
||||
"contextWindow": 200000,
|
||||
"maxOutputTokens": 16384,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
@@ -29,16 +29,19 @@
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "openai/gpt-oss-120b:free",
|
||||
"displayName": "GPT-OSS 120B (免费)",
|
||||
"modelName": "google/gemini-2.5-flash-exp:free",
|
||||
"displayName": "Gemini 2.5 Flash (免费)",
|
||||
"serviceType": ["chat"],
|
||||
"description": "通过 OpenRouter 免费使用的 OpenAI GPT-OSS 120B",
|
||||
"contextWindow": 131072,
|
||||
"maxOutputTokens": 131072,
|
||||
"description": "通过 OpenRouter 免费使用的 Gemini 2.5 Flash，1M 上下文",
|
||||
"contextWindow": 1048576,
|
||||
"maxOutputTokens": 65535,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code"
|
||||
"vision",
|
||||
"tool_use",
|
||||
"fast",
|
||||
"long_context"
|
||||
],
|
||||
"inputPrice": 0.00,
|
||||
"outputPrice": 0.00,
|
||||
@@ -51,8 +54,8 @@
|
||||
"displayName": "Qwen3 Coder 480B (免费)",
|
||||
"serviceType": ["chat"],
|
||||
"description": "通过 OpenRouter 免费使用的 Qwen3 Coder 480B",
|
||||
"contextWindow": 262000,
|
||||
"maxOutputTokens": 262000,
|
||||
"contextWindow": 262144,
|
||||
"maxOutputTokens": 32768,
|
||||
"capabilities": [
|
||||
"code",
|
||||
"reasoning",
|
||||
|
||||
@@ -26,16 +26,9 @@
|
||||
],
|
||||
"inputPrice": 3.00,
|
||||
"outputPrice": 15.00,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"requestPricingPer1k": {
|
||||
"low": 6,
|
||||
"medium": 10,
|
||||
"high": 14
|
||||
},
|
||||
"pricingNotes": "Total Sonar API cost includes token costs plus a request fee based on search context size."
|
||||
}
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "sonar-reasoning-pro",
|
||||
@@ -52,16 +45,9 @@
|
||||
],
|
||||
"inputPrice": 2.00,
|
||||
"outputPrice": 8.00,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"requestPricingPer1k": {
|
||||
"low": 6,
|
||||
"medium": 10,
|
||||
"high": 14
|
||||
},
|
||||
"pricingNotes": "Total Sonar API cost includes token costs plus a request fee based on search context size."
|
||||
}
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "sonar",
|
||||
@@ -78,16 +64,9 @@
|
||||
],
|
||||
"inputPrice": 1.00,
|
||||
"outputPrice": 1.00,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"requestPricingPer1k": {
|
||||
"low": 5,
|
||||
"medium": 8,
|
||||
"high": 12
|
||||
},
|
||||
"pricingNotes": "Total Sonar API cost includes token costs plus a request fee based on search context size."
|
||||
}
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -15,41 +15,41 @@
|
||||
"modelName": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
||||
"displayName": "Qwen3 Coder 480B (硅基)",
|
||||
"serviceType": ["chat"],
|
||||
"description": "Qwen3-Coder-480B-A35B-Instruct，480B MoE（35B 激活），原生 256K 上下文，可通过外推扩展至 1M，面向 Agentic Coding",
|
||||
"description": "开源最强代码模型，480B MoE 架构，擅长代码生成和 Agent 场景",
|
||||
"contextWindow": 262144,
|
||||
"maxOutputTokens": 262144,
|
||||
"maxOutputTokens": 32768,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"code",
|
||||
"long_context",
|
||||
"reasoning",
|
||||
"agent",
|
||||
"tool_use"
|
||||
],
|
||||
"inputPrice": 8,
|
||||
"outputPrice": 16,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": 0.7,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "Qwen/Qwen3-235B-A22B-Instruct-2507",
|
||||
"modelName": "Qwen/Qwen3-235B-A22B-Instruct",
|
||||
"displayName": "Qwen3 235B (硅基)",
|
||||
"serviceType": ["chat"],
|
||||
"description": "Qwen3-235B-A22B-Instruct-2507，235B MoE（22B 激活）通用指令模型，262K 上下文",
|
||||
"description": "Qwen3 旗舰通用模型，235B MoE 架构，多语言能力突出",
|
||||
"contextWindow": 262144,
|
||||
"maxOutputTokens": 262144,
|
||||
"maxOutputTokens": 38912,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"multilingual",
|
||||
"tool_use",
|
||||
"agent",
|
||||
"long_context"
|
||||
"vision"
|
||||
],
|
||||
"inputPrice": 2.5,
|
||||
"outputPrice": 10,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": 0.7,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
@@ -65,8 +65,6 @@
|
||||
],
|
||||
"inputPrice": 0,
|
||||
"outputPrice": 0,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {}
|
||||
}
|
||||
]
|
||||
|
||||
@@ -9,19 +9,14 @@
|
||||
"enabled": false,
|
||||
"status": "unconfigured",
|
||||
"priceCurrency": "CNY",
|
||||
"services": [
|
||||
"chat",
|
||||
"reasoning"
|
||||
],
|
||||
"services": ["chat", "reasoning"],
|
||||
"models": [
|
||||
{
|
||||
"modelName": "hunyuan-2.0-thinking-20251109",
|
||||
"displayName": "混元 2.0 Think",
|
||||
"serviceType": [
|
||||
"reasoning"
|
||||
],
|
||||
"serviceType": ["reasoning"],
|
||||
"description": "腾讯混元最新推理模型，128K输入/64K输出，MoE架构406B总参数",
|
||||
"contextWindow": 196608,
|
||||
"contextWindow": 131072,
|
||||
"maxOutputTokens": 65536,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
@@ -31,65 +26,16 @@
|
||||
],
|
||||
"inputPrice": 3.975,
|
||||
"outputPrice": 15.9,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"pricingTiers": [
|
||||
{
|
||||
"maxInputTokens": 32768,
|
||||
"inputPrice": 3.975,
|
||||
"outputPrice": 15.9
|
||||
},
|
||||
{
|
||||
"maxInputTokens": 131072,
|
||||
"inputPrice": 5.3,
|
||||
"outputPrice": 21.2
|
||||
}
|
||||
]
|
||||
}
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "hunyuan-2.0-instruct-20251111",
|
||||
"displayName": "混元 2.0 Instruct",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "腾讯混元 2.0 指令模型，最大输入128K/最大输出16K，支持联网搜索和 Function Calling",
|
||||
"contextWindow": 147456,
|
||||
"maxOutputTokens": 16384,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"code",
|
||||
"long_context",
|
||||
"tool_use"
|
||||
],
|
||||
"inputPrice": 3.18,
|
||||
"outputPrice": 7.95,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"pricingTiers": [
|
||||
{
|
||||
"maxInputTokens": 32768,
|
||||
"inputPrice": 3.18,
|
||||
"outputPrice": 7.95
|
||||
},
|
||||
{
|
||||
"maxInputTokens": 131072,
|
||||
"inputPrice": 4.505,
|
||||
"outputPrice": 11.13
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "hunyuan-turbos-latest",
|
||||
"modelName": "hunyuan-turbo-s",
|
||||
"displayName": "混元 Turbo S",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "腾讯混元高速模型，32K输入/16K输出，支持推理和工具调用",
|
||||
"contextWindow": 32768,
|
||||
"serviceType": ["chat"],
|
||||
"description": "腾讯混元高速模型，262K 上下文，支持推理和工具调用",
|
||||
"contextWindow": 262144,
|
||||
"maxOutputTokens": 16384,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
@@ -101,8 +47,8 @@
|
||||
],
|
||||
"inputPrice": 0.8,
|
||||
"outputPrice": 2,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
}
|
||||
]
|
||||
|
||||
@@ -23,12 +23,10 @@
|
||||
{
|
||||
"modelName": "doubao-2.0-pro",
|
||||
"displayName": "豆包 2.0 Pro",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "火山引擎豆包2.0旗舰模型，256K上下文，相比Gemini 3 Pro和GPT 5.2有较大成本优势",
|
||||
"contextWindow": 256000,
|
||||
"maxOutputTokens": 128000,
|
||||
"maxOutputTokens": 16384,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -39,19 +37,17 @@
|
||||
],
|
||||
"inputPrice": 3.2,
|
||||
"outputPrice": 16,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.7,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.9,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "doubao-seed-1.8",
|
||||
"displayName": "豆包 Seed-1.8",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "火山引擎豆包1.8旗舰模型，256K上下文，支持深度思考和多模态",
|
||||
"contextWindow": 256000,
|
||||
"maxOutputTokens": 16000,
|
||||
"maxOutputTokens": 16384,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -62,19 +58,17 @@
|
||||
],
|
||||
"inputPrice": 0.8,
|
||||
"outputPrice": 2,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.7,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.9,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "doubao-seed-1.6",
|
||||
"displayName": "豆包 Seed-1.6",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "火山引擎豆包1.6旗舰模型，256K上下文",
|
||||
"contextWindow": 256000,
|
||||
"maxOutputTokens": 32000,
|
||||
"maxOutputTokens": 16384,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -85,19 +79,17 @@
|
||||
],
|
||||
"inputPrice": 0.8,
|
||||
"outputPrice": 8,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.7,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.9,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "doubao-seed-1.6-thinking",
|
||||
"displayName": "豆包 Seed-1.6 思考版",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "火山引擎豆包1.6深度思考模型，256K上下文",
|
||||
"contextWindow": 256000,
|
||||
"maxOutputTokens": 16000,
|
||||
"maxOutputTokens": 32768,
|
||||
"capabilities": [
|
||||
"reasoning",
|
||||
"math",
|
||||
@@ -107,19 +99,16 @@
|
||||
],
|
||||
"inputPrice": 0.8,
|
||||
"outputPrice": 8,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.7,
|
||||
"defaultTemperature": 0.3,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "doubao-seed-1.6-flash",
|
||||
"displayName": "豆包 Seed-1.6 Flash",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "火山引擎豆包1.6快速版，成本较前代下降63%",
|
||||
"contextWindow": 256000,
|
||||
"maxOutputTokens": 16000,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"code",
|
||||
@@ -128,19 +117,17 @@
|
||||
],
|
||||
"inputPrice": 0.15,
|
||||
"outputPrice": 1.5,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.7,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.9,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "doubao-seed-1.6-lite",
|
||||
"displayName": "豆包 Seed-1.6 Lite",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "火山引擎豆包1.6轻量版，极致性价比",
|
||||
"contextWindow": 256000,
|
||||
"maxOutputTokens": 32000,
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 4096,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"code",
|
||||
@@ -148,19 +135,17 @@
|
||||
],
|
||||
"inputPrice": 0.3,
|
||||
"outputPrice": 0.6,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.7,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.9,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "doubao-seed-1.6-vision",
|
||||
"displayName": "豆包 Seed-1.6 视觉版",
|
||||
"serviceType": [
|
||||
"vision"
|
||||
],
|
||||
"serviceType": ["vision"],
|
||||
"description": "火山引擎豆包1.6视觉模型，256K上下文，支持视频理解",
|
||||
"contextWindow": 256000,
|
||||
"maxOutputTokens": 32000,
|
||||
"maxOutputTokens": 16384,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"vision",
|
||||
@@ -170,16 +155,14 @@
|
||||
],
|
||||
"inputPrice": 0.8,
|
||||
"outputPrice": 8,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.7,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.9,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "doubao-seed-code",
|
||||
"displayName": "豆包 Seed-Code",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "火山引擎豆包编程专用模型，256K上下文",
|
||||
"contextWindow": 256000,
|
||||
"maxOutputTokens": 32768,
|
||||
@@ -191,19 +174,16 @@
|
||||
],
|
||||
"inputPrice": 1.2,
|
||||
"outputPrice": 8,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.7,
|
||||
"defaultTemperature": 0.3,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "deepseek-v3.2",
|
||||
"displayName": "DeepSeek V3.2 (火山引擎)",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "火山引擎托管的DeepSeek V3.2，128K上下文",
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 32000,
|
||||
"maxOutputTokens": 8000,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -219,12 +199,10 @@
|
||||
{
|
||||
"modelName": "deepseek-r1",
|
||||
"displayName": "DeepSeek R1 (火山引擎)",
|
||||
"serviceType": [
|
||||
"reasoning"
|
||||
],
|
||||
"description": "火山引擎托管的DeepSeek R1推理模型，128K上下文",
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 65536,
|
||||
"serviceType": ["reasoning"],
|
||||
"description": "火山引擎托管的DeepSeek R1推理模型，64K上下文",
|
||||
"contextWindow": 64000,
|
||||
"maxOutputTokens": 32768,
|
||||
"capabilities": [
|
||||
"reasoning",
|
||||
"math",
|
||||
@@ -234,18 +212,16 @@
|
||||
],
|
||||
"inputPrice": 4,
|
||||
"outputPrice": 16,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "kimi-k2-volcengine",
|
||||
"displayName": "Kimi K2 (火山引擎)",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "火山引擎托管的Kimi K2，万亿参数MoE模型，128K上下文",
|
||||
"contextWindow": 256000,
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
@@ -257,19 +233,17 @@
|
||||
],
|
||||
"inputPrice": 4,
|
||||
"outputPrice": 16,
|
||||
"defaultTemperature": 0.6,
|
||||
"defaultTopP": 1,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.9,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "glm-4-7",
|
||||
"displayName": "GLM-4.7 (火山引擎)",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "火山引擎托管的智谱GLM-4.7，200K上下文",
|
||||
"contextWindow": 200000,
|
||||
"maxOutputTokens": 128000,
|
||||
"maxOutputTokens": 200000,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -280,16 +254,14 @@
|
||||
],
|
||||
"inputPrice": 4,
|
||||
"outputPrice": 16,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"defaultTemperature": 0.7,
|
||||
"defaultTopP": 0.9,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "doubao-embedding",
|
||||
"displayName": "豆包 Embedding",
|
||||
"serviceType": [
|
||||
"embedding"
|
||||
],
|
||||
"serviceType": ["embedding"],
|
||||
"description": "火山引擎豆包标准向量模型，2560维度",
|
||||
"contextWindow": 4096,
|
||||
"capabilities": [
|
||||
@@ -299,24 +271,18 @@
|
||||
"chinese_optimized"
|
||||
],
|
||||
"inputPrice": 0.5,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "volc-mega-tts-clone",
|
||||
"displayName": "火山声音复刻",
|
||||
"serviceType": [
|
||||
"voice_clone"
|
||||
],
|
||||
"serviceType": ["voice_clone"],
|
||||
"description": "火山引擎声音复刻，支持极少样本",
|
||||
"capabilities": [
|
||||
"voice_clone",
|
||||
"chinese_optimized",
|
||||
"few_shot"
|
||||
],
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"maxCloneSamples": 3,
|
||||
"minCloneDuration": 5
|
||||
@@ -325,9 +291,7 @@
|
||||
{
|
||||
"modelName": "volc-realtime-voice",
|
||||
"displayName": "火山实时语音",
|
||||
"serviceType": [
|
||||
"realtime_voice"
|
||||
],
|
||||
"serviceType": ["realtime_voice"],
|
||||
"description": "火山引擎实时语音交互",
|
||||
"capabilities": [
|
||||
"realtime",
|
||||
@@ -335,8 +299,6 @@
|
||||
"low_latency",
|
||||
"chinese_optimized"
|
||||
],
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"supportedModes": [
|
||||
"speech-to-speech"
|
||||
@@ -347,17 +309,13 @@
|
||||
{
|
||||
"modelName": "volc-simultaneous",
|
||||
"displayName": "火山同声传译",
|
||||
"serviceType": [
|
||||
"simultaneous_interpret"
|
||||
],
|
||||
"serviceType": ["simultaneous_interpret"],
|
||||
"description": "火山引擎同声传译，支持中英双向",
|
||||
"capabilities": [
|
||||
"simultaneous_interpretation",
|
||||
"chinese_optimized",
|
||||
"low_latency"
|
||||
],
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"streamingSupported": true
|
||||
}
|
||||
@@ -365,17 +323,13 @@
|
||||
{
|
||||
"modelName": "volc-translation",
|
||||
"displayName": "火山翻译",
|
||||
"serviceType": [
|
||||
"translation"
|
||||
],
|
||||
"serviceType": ["translation"],
|
||||
"description": "火山引擎机器翻译，支持多语种互译",
|
||||
"capabilities": [
|
||||
"translation",
|
||||
"multilingual",
|
||||
"chinese_optimized"
|
||||
],
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {}
|
||||
}
|
||||
]
|
||||
|
||||
@@ -12,12 +12,12 @@
|
||||
"services": ["chat", "reasoning"],
|
||||
"models": [
|
||||
{
|
||||
"modelName": "grok-4.20-0309-reasoning",
|
||||
"displayName": "Grok 4.20 Reasoning",
|
||||
"modelName": "grok-4-0709",
|
||||
"displayName": "Grok 4",
|
||||
"serviceType": ["chat", "reasoning"],
|
||||
"description": "xAI 旗舰推理模型，支持函数调用与结构化输出",
|
||||
"contextWindow": 2000000,
|
||||
"maxOutputTokens": 16384,
|
||||
"description": "xAI 最新旗舰推理模型，262K 上下文，支持工具调用",
|
||||
"contextWindow": 262144,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -25,17 +25,17 @@
|
||||
"vision",
|
||||
"tool_use"
|
||||
],
|
||||
"inputPrice": 2.00,
|
||||
"outputPrice": 6.00,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"inputPrice": 3.00,
|
||||
"outputPrice": 15.00,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "grok-4-1-fast-reasoning",
|
||||
"displayName": "Grok 4.1 Fast Reasoning",
|
||||
"serviceType": ["chat", "reasoning"],
|
||||
"description": "xAI 高速推理模型，2M 上下文窗口",
|
||||
"modelName": "grok-4-1-fast",
|
||||
"displayName": "Grok 4.1 Fast",
|
||||
"serviceType": ["chat"],
|
||||
"description": "xAI 超长上下文高速模型，2M token 窗口",
|
||||
"contextWindow": 2000000,
|
||||
"maxOutputTokens": 16384,
|
||||
"capabilities": [
|
||||
@@ -49,8 +49,8 @@
|
||||
],
|
||||
"inputPrice": 0.20,
|
||||
"outputPrice": 0.50,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {}
|
||||
}
|
||||
]
|
||||
|
||||
@@ -12,12 +12,12 @@
|
||||
"services": ["chat", "reasoning"],
|
||||
"models": [
|
||||
{
|
||||
"modelName": "spark-x",
|
||||
"modelName": "x1",
|
||||
"displayName": "讯飞星火 X1",
|
||||
"serviceType": ["reasoning"],
|
||||
"description": "讯飞深度推理模型（X2），输入64K/输出128K，支持思考模式与函数调用",
|
||||
"contextWindow": 65536,
|
||||
"maxOutputTokens": 128000,
|
||||
"description": "讯飞最新推理模型，基于全国产算力训练，擅长数学和代码推理",
|
||||
"contextWindow": 32768,
|
||||
"maxOutputTokens": 16384,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -25,10 +25,12 @@
|
||||
"math",
|
||||
"code"
|
||||
],
|
||||
"defaultTemperature": 1.2,
|
||||
"defaultTopP": 0.95,
|
||||
"inputPrice": 11,
|
||||
"outputPrice": 11,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {
|
||||
"pricingNote": "官方公开文档说明模型价格以控制台及实际购买页为准，未公开固定 token 单价"
|
||||
"pricingNote": "讯飞按token包计费，不区分输入输出"
|
||||
}
|
||||
},
|
||||
{
|
||||
@@ -44,10 +46,12 @@
|
||||
"code",
|
||||
"tool_use"
|
||||
],
|
||||
"inputPrice": 60,
|
||||
"outputPrice": 60,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 1,
|
||||
"extra": {
|
||||
"pricingNote": "官方公开文档说明模型价格以控制台及实际购买页为准，未公开固定 token 单价"
|
||||
"pricingNote": "讯飞按token包计费，不区分输入输出"
|
||||
}
|
||||
}
|
||||
]
|
||||
|
||||
@@ -18,22 +18,15 @@
|
||||
"modelName": "embedding-3",
|
||||
"displayName": "智谱 embedding-3",
|
||||
"serviceType": ["embedding"],
|
||||
"description": "智谱嵌入模型v3，支持自定义维度；模型上下文窗口 8K，单条输入最多 3072 tokens。走 OpenAI 兼容 /embeddings 端点（Anthropic 协议不提供 embeddings）",
|
||||
"contextWindow": 8192,
|
||||
"description": "智谱嵌入模型v3，支持自定义维度，单条最大3072 tokens。走 OpenAI 兼容 /embeddings 端点（Anthropic 协议不提供 embeddings）",
|
||||
"contextWindow": 3072,
|
||||
"capabilities": [
|
||||
"text_embedding",
|
||||
"semantic_search",
|
||||
"rag",
|
||||
"custom_dimensions"
|
||||
"rag"
|
||||
],
|
||||
"inputPrice": 0.5,
|
||||
"defaultTemperature": null,
|
||||
"defaultTopP": null,
|
||||
"extra": {
|
||||
"maxInputTokensPerItem": 3072,
|
||||
"maxBatchItems": 64,
|
||||
"vectorDimensions": "256-2048"
|
||||
}
|
||||
"extra": {}
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -18,72 +18,10 @@
|
||||
"embedding-3"
|
||||
],
|
||||
"models": [
|
||||
{
|
||||
"modelName": "glm-5.1",
|
||||
"displayName": "GLM-5.1",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "智谱 GLM-5.1 最新旗舰模型，面向长程 Agentic Coding 与 Autonomous Agent 场景，200K 上下文，128K 最大输出",
|
||||
"contextWindow": 200000,
|
||||
"maxOutputTokens": 128000,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"multilingual",
|
||||
"deep_thinking",
|
||||
"long_context",
|
||||
"math",
|
||||
"tool_use",
|
||||
"agent"
|
||||
],
|
||||
"inputPrice": 6,
|
||||
"outputPrice": 24,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"cacheHitPrice": 1.2,
|
||||
"thinking": {
|
||||
"default": "enabled"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "glm-5-turbo",
|
||||
"displayName": "GLM-5-Turbo",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "智谱 GLM-5-Turbo，面向 OpenClaw 等长链路任务优化，200K 上下文，128K 最大输出",
|
||||
"contextWindow": 200000,
|
||||
"maxOutputTokens": 128000,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"deep_thinking",
|
||||
"long_context",
|
||||
"tool_use",
|
||||
"agent"
|
||||
],
|
||||
"inputPrice": 5,
|
||||
"outputPrice": 22,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"cacheHitPrice": 1,
|
||||
"thinking": {
|
||||
"default": "enabled"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "glm-5",
|
||||
"displayName": "GLM-5",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "智谱GLM-5，744B参数旗舰基座模型，2026年2月发布，面向Agentic Engineering，编程能力接近Claude Opus",
|
||||
"contextWindow": 200000,
|
||||
"maxOutputTokens": 128000,
|
||||
@@ -100,18 +38,14 @@
|
||||
],
|
||||
"inputPrice": 4,
|
||||
"outputPrice": 18,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"cacheHitPrice": 0.8
|
||||
}
|
||||
"defaultTemperature": 0.95,
|
||||
"defaultTopP": 0.7,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "glm-4.7",
|
||||
"displayName": "GLM-4.7",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"serviceType": ["chat"],
|
||||
"description": "智谱GLM-4.7，355B参数MoE架构旗舰模型，200K上下文，编程能力对齐Claude Sonnet",
|
||||
"contextWindow": 200000,
|
||||
"maxOutputTokens": 128000,
|
||||
@@ -124,20 +58,16 @@
|
||||
"long_context",
|
||||
"tool_use"
|
||||
],
|
||||
"inputPrice": 2,
|
||||
"outputPrice": 8,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"cacheHitPrice": 0.5
|
||||
}
|
||||
"inputPrice": 4,
|
||||
"outputPrice": 16,
|
||||
"defaultTemperature": 0.95,
|
||||
"defaultTopP": 0.7,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "glm-4.7-thinking",
|
||||
"displayName": "GLM-4.7 Thinking",
|
||||
"serviceType": [
|
||||
"reasoning"
|
||||
],
|
||||
"serviceType": ["reasoning"],
|
||||
"description": "智谱GLM-4.7深度思考模式，200K上下文，交错式/保留式/轮级思考",
|
||||
"contextWindow": 200000,
|
||||
"maxOutputTokens": 128000,
|
||||
@@ -148,57 +78,19 @@
|
||||
"deep_thinking",
|
||||
"long_context"
|
||||
],
|
||||
"inputPrice": 2,
|
||||
"outputPrice": 8,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"cacheHitPrice": 0.5,
|
||||
"aliasOf": "glm-4.7"
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "glm-5v-turbo",
|
||||
"displayName": "GLM-5V-Turbo",
|
||||
"serviceType": [
|
||||
"vision"
|
||||
],
|
||||
"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，200K 上下文，128K 最大输出",
|
||||
"contextWindow": 200000,
|
||||
"maxOutputTokens": 128000,
|
||||
"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,
|
||||
"thinking": {
|
||||
"default": "enabled"
|
||||
}
|
||||
}
|
||||
"inputPrice": 8,
|
||||
"outputPrice": 32,
|
||||
"defaultTemperature": 0.95,
|
||||
"defaultTopP": 0.7,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "glm-4.6v",
|
||||
"displayName": "GLM-4.6V",
|
||||
"serviceType": [
|
||||
"vision"
|
||||
],
|
||||
"serviceType": ["vision"],
|
||||
"description": "智谱GLM-4.6V多模态版，106B/12B MoE，支持图像视频理解与工具调用，128K上下文",
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 32768,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"vision",
|
||||
@@ -207,37 +99,28 @@
|
||||
"long_context",
|
||||
"tool_use"
|
||||
],
|
||||
"inputPrice": 1,
|
||||
"outputPrice": 4,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"cacheHitPrice": 0.2
|
||||
}
|
||||
"inputPrice": 8,
|
||||
"outputPrice": 32,
|
||||
"extra": {}
|
||||
},
|
||||
{
|
||||
"modelName": "glm-4.6",
|
||||
"displayName": "GLM-4.6",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "智谱GLM-4.6，增强推理能力，200K上下文",
|
||||
"contextWindow": 200000,
|
||||
"maxOutputTokens": 128000,
|
||||
"serviceType": ["chat"],
|
||||
"description": "智谱GLM-4.6，增强推理能力，128K上下文",
|
||||
"contextWindow": 128000,
|
||||
"maxOutputTokens": 8192,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"multilingual",
|
||||
"deep_thinking"
|
||||
"deep_thinking",
|
||||
"vision"
|
||||
],
|
||||
"inputPrice": 2,
|
||||
"outputPrice": 8,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"cacheHitPrice": 0.5
|
||||
}
|
||||
"inputPrice": 5,
|
||||
"outputPrice": 5,
|
||||
"extra": {}
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"version": "1.0.0",
|
||||
"presetDataVersion": 29,
|
||||
"updatedAt": "2026-04-24",
|
||||
"presetDataVersion": 24,
|
||||
"updatedAt": "2026-04-20",
|
||||
"description": "DesireCore 官方配置中心"
|
||||
}
|
||||
|
||||
@@ -1,17 +0,0 @@
|
||||
# 未确认字段报告 - compute/providers/anthropic.json
|
||||
|
||||
- provider: `anthropic`
|
||||
- generatedAt: `2026-04-24T00:00:00+08:00`
|
||||
- 本轮范围: `defaultTemperature` / `defaultTopP`
|
||||
|
||||
## claude-opus-4-7
|
||||
|
||||
- `defaultTopP`: 已查 https://docs.anthropic.com/en/api/messages 。官方页面给出了 `top_p` 参数说明和范围，但没有给“省略参数时默认值”，因此只能保留为 `null`。
|
||||
|
||||
## claude-sonnet-4-6
|
||||
|
||||
- `defaultTopP`: 已查 https://docs.anthropic.com/en/api/messages 。官方页面给出了 `top_p` 参数说明和范围，但没有给“省略参数时默认值”，因此只能保留为 `null`。
|
||||
|
||||
## claude-haiku-4-5
|
||||
|
||||
- `defaultTopP`: 已查 https://docs.anthropic.com/en/api/messages 。官方页面给出了 `top_p` 参数说明和范围，但没有给“省略参数时默认值”，因此只能保留为 `null`。
|
||||
@@ -1,30 +0,0 @@
|
||||
# 详细字段取值表 - compute/providers/anthropic.json
|
||||
|
||||
- provider: `anthropic`
|
||||
- generatedAt: `2026-04-24T00:00:00+08:00`
|
||||
- 本轮复核字段: `defaultTemperature` / `defaultTopP`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://docs.anthropic.com/en/api/messages
|
||||
|
||||
## claude-opus-4-7
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | Anthropic Messages API 文档明确写明 `temperature` `Defaults to 1.0`。 |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | Anthropic Messages API 文档描述了 `top_p` 的含义和范围，但未给省略时默认值；JSON 不应伪装成官方默认值。 |
|
||||
|
||||
## claude-sonnet-4-6
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | Anthropic Messages API 文档明确写明 `temperature` `Defaults to 1.0`。 |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | Anthropic Messages API 文档描述了 `top_p` 的含义和范围，但未给省略时默认值；JSON 不应伪装成官方默认值。 |
|
||||
|
||||
## claude-haiku-4-5
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | Anthropic Messages API 文档明确写明 `temperature` `Defaults to 1.0`。 |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | Anthropic Messages API 文档描述了 `top_p` 的含义和范围，但未给省略时默认值；JSON 不应伪装成官方默认值。 |
|
||||
@@ -1,17 +0,0 @@
|
||||
# anthropic ambiguous/similar 逐条处置记录（2026-04-23）
|
||||
|
||||
依据：
|
||||
- Anthropic Models: https://docs.anthropic.com/en/docs/about-claude/models
|
||||
- Anthropic Pricing: https://www.anthropic.com/pricing
|
||||
- ZenMux: https://zenmux.ai/models
|
||||
- ZenMux API: https://zenmux.ai/api/v1/models
|
||||
|
||||
## 已处置条目
|
||||
|
||||
1. `claude-sonnet-4-5-computer`（ambiguous）
|
||||
处置：不修改。
|
||||
原因：ZenMux 候选覆盖 `sonnet/opus/haiku` 多分支；本地条目为 `computer_use` 专用路由，不能按通用 chat 候选直接覆盖。
|
||||
|
||||
## 本轮 anthropic 落库结果
|
||||
|
||||
- JSON 变更：0
|
||||
@@ -1,36 +0,0 @@
|
||||
# 未确认字段报告 - compute/providers/baichuan.json
|
||||
|
||||
- provider: `baichuan`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## Baichuan-M3-Plus
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `maxOutputTokens`: 已复核 https://platform.baichuan-ai.com/docs/api 及其官方正文源 `https://platform.baichuan-ai.com/api/gitlab/file` 返回的 `mainDocument.md`；当前通用对话 API 文档确有 `max_tokens` 参数，取值范围为 `[1,2048]`、默认 `2048`，但正文支持模型仅列 `Baichuan4-Turbo` / `Baichuan4-Air` / `Baichuan4` / `Baichuan3-Turbo` / `Baichuan3-Turbo-128k` / `Baichuan2-Turbo`，未覆盖 `Baichuan-M3-Plus`
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## Baichuan-M3
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `maxOutputTokens`: 已复核 https://platform.baichuan-ai.com/docs/api 及其官方正文源 `https://platform.baichuan-ai.com/api/gitlab/file` 返回的 `mainDocument.md`；当前通用对话 API 文档确有 `max_tokens` 参数，取值范围为 `[1,2048]`、默认 `2048`，但正文支持模型仅列 `Baichuan4-Turbo` / `Baichuan4-Air` / `Baichuan4` / `Baichuan3-Turbo` / `Baichuan3-Turbo-128k` / `Baichuan2-Turbo`，未覆盖 `Baichuan-M3`
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## Baichuan-M2-Plus
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `maxOutputTokens`: 已复核 https://platform.baichuan-ai.com/docs/api 及其官方正文源 `https://platform.baichuan-ai.com/api/gitlab/file` 返回的 `mainDocument.md`；当前通用对话 API 文档确有 `max_tokens` 参数，取值范围为 `[1,2048]`、默认 `2048`，但正文支持模型仅列 `Baichuan4-Turbo` / `Baichuan4-Air` / `Baichuan4` / `Baichuan3-Turbo` / `Baichuan3-Turbo-128k` / `Baichuan2-Turbo`，未覆盖 `Baichuan-M2-Plus`
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## Baichuan-M2
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `maxOutputTokens`: 已复核 https://platform.baichuan-ai.com/docs/api 及其官方正文源 `https://platform.baichuan-ai.com/api/gitlab/file` 返回的 `mainDocument.md`；当前通用对话 API 文档确有 `max_tokens` 参数，取值范围为 `[1,2048]`、默认 `2048`，但正文支持模型仅列 `Baichuan4-Turbo` / `Baichuan4-Air` / `Baichuan4` / `Baichuan3-Turbo` / `Baichuan3-Turbo-128k` / `Baichuan2-Turbo`，未覆盖 `Baichuan-M2`
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
@@ -1,90 +0,0 @@
|
||||
# 详细字段取值表 - compute/providers/baichuan.json
|
||||
|
||||
- provider: `baichuan`
|
||||
- priceCurrency: `CNY`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://platform.baichuan-ai.com/prices
|
||||
- https://platform.baichuan-ai.com/docs/api
|
||||
- https://platform.baichuan-ai.com/api/gitlab/file
|
||||
- https://platform.baichuan-ai.com/docs/knowledgeBase
|
||||
- https://zenmux.ai/models
|
||||
- https://zenmux.ai/api/v1/models
|
||||
|
||||
## Baichuan-M3-Plus
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"Baichuan-M3-Plus"` | `"Baichuan-M3-Plus"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"百川 M3-Plus"` | `"百川 M3-Plus"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `32000` | `32000` | 保持 | 百川价格页 https://platform.baichuan-ai.com/prices 将 `Baichuan-M3-Plus` / `Baichuan-M3` / `Baichuan-M2-Plus` / `Baichuan-M2` 的上下文长度均列为 `32k` |
|
||||
| `maxOutputTokens` | `32000` | `32000` | 待确认 | 已复核 https://platform.baichuan-ai.com/docs/api 及其官方正文源 `https://platform.baichuan-ai.com/api/gitlab/file` 返回的 `mainDocument.md`；当前通用对话 API 文档确有 `max_tokens` 参数，取值范围为 `[1,2048]`、默认 `2048`，但正文支持模型仅列 `Baichuan4-Turbo` / `Baichuan4-Air` / `Baichuan4` / `Baichuan3-Turbo` / `Baichuan3-Turbo-128k` / `Baichuan2-Turbo`，未覆盖本地 `Baichuan-M3-Plus`，因此不能直接据此回填 |
|
||||
| `inputPrice` | `5` | `5` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `9` | `9` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","multilingual","vision","long_context","medical"]` | `["chat","reasoning","code","multilingual","vision","long_context","medical"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 百川官方通用对话 API 文档 https://platform.baichuan-ai.com/docs/api 及其正文源 `https://platform.baichuan-ai.com/api/gitlab/file` 仅为 `Baichuan4/3/2-Turbo` 系列声明 `temperature` 默认值 `0.3`；未覆盖 `Baichuan-M3-Plus`，按“官网未定义该型号默认值”记为 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 百川官方通用对话 API 文档 https://platform.baichuan-ai.com/docs/api 及其正文源 `https://platform.baichuan-ai.com/api/gitlab/file` 仅为 `Baichuan4/3/2-Turbo` 系列声明 `top_p` 默认值 `0.85`；未覆盖 `Baichuan-M3-Plus`，按“官网未定义该型号默认值”记为 `null` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## Baichuan-M3
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"Baichuan-M3"` | `"Baichuan-M3"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"百川 M3"` | `"百川 M3"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `32000` | `32000` | 保持 | 百川价格页 https://platform.baichuan-ai.com/prices 将 `Baichuan-M3-Plus` / `Baichuan-M3` / `Baichuan-M2-Plus` / `Baichuan-M2` 的上下文长度均列为 `32k` |
|
||||
| `maxOutputTokens` | `32000` | `32000` | 待确认 | 已复核 https://platform.baichuan-ai.com/docs/api 及其官方正文源 `https://platform.baichuan-ai.com/api/gitlab/file` 返回的 `mainDocument.md`；当前通用对话 API 文档确有 `max_tokens` 参数，取值范围为 `[1,2048]`、默认 `2048`，但正文支持模型仅列 `Baichuan4-Turbo` / `Baichuan4-Air` / `Baichuan4` / `Baichuan3-Turbo` / `Baichuan3-Turbo-128k` / `Baichuan2-Turbo`，未覆盖本地 `Baichuan-M3`，因此不能直接据此回填 |
|
||||
| `inputPrice` | `10` | `10` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `30` | `30` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","multilingual","vision","medical"]` | `["chat","reasoning","code","multilingual","vision","medical"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 百川官方通用对话 API 文档 https://platform.baichuan-ai.com/docs/api 及其正文源 `https://platform.baichuan-ai.com/api/gitlab/file` 仅为 `Baichuan4/3/2-Turbo` 系列声明 `temperature` 默认值 `0.3`；未覆盖 `Baichuan-M3`，按“官网未定义该型号默认值”记为 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 百川官方通用对话 API 文档 https://platform.baichuan-ai.com/docs/api 及其正文源 `https://platform.baichuan-ai.com/api/gitlab/file` 仅为 `Baichuan4/3/2-Turbo` 系列声明 `top_p` 默认值 `0.85`；未覆盖 `Baichuan-M3`，按“官网未定义该型号默认值”记为 `null` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## Baichuan-M2-Plus
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"Baichuan-M2-Plus"` | `"Baichuan-M2-Plus"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"百川 M2-Plus"` | `"百川 M2-Plus"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `32000` | `32000` | 保持 | 百川价格页 https://platform.baichuan-ai.com/prices 将 `Baichuan-M3-Plus` / `Baichuan-M3` / `Baichuan-M2-Plus` / `Baichuan-M2` 的上下文长度均列为 `32k` |
|
||||
| `maxOutputTokens` | `32000` | `32000` | 待确认 | 已复核 https://platform.baichuan-ai.com/docs/api 及其官方正文源 `https://platform.baichuan-ai.com/api/gitlab/file` 返回的 `mainDocument.md`；当前通用对话 API 文档确有 `max_tokens` 参数，取值范围为 `[1,2048]`、默认 `2048`，但正文支持模型仅列 `Baichuan4-Turbo` / `Baichuan4-Air` / `Baichuan4` / `Baichuan3-Turbo` / `Baichuan3-Turbo-128k` / `Baichuan2-Turbo`，未覆盖本地 `Baichuan-M2-Plus`，因此不能直接据此回填 |
|
||||
| `inputPrice` | `10` | `10` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `30` | `30` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","multilingual","long_context"]` | `["chat","reasoning","code","multilingual","long_context"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 百川官方通用对话 API 文档 https://platform.baichuan-ai.com/docs/api 及其正文源 `https://platform.baichuan-ai.com/api/gitlab/file` 仅为 `Baichuan4/3/2-Turbo` 系列声明 `temperature` 默认值 `0.3`；未覆盖 `Baichuan-M2-Plus`，按“官网未定义该型号默认值”记为 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 百川官方通用对话 API 文档 https://platform.baichuan-ai.com/docs/api 及其正文源 `https://platform.baichuan-ai.com/api/gitlab/file` 仅为 `Baichuan4/3/2-Turbo` 系列声明 `top_p` 默认值 `0.85`；未覆盖 `Baichuan-M2-Plus`，按“官网未定义该型号默认值”记为 `null` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## Baichuan-M2
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"Baichuan-M2"` | `"Baichuan-M2"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"百川 M2"` | `"百川 M2"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `32000` | `32000` | 保持 | 百川价格页 https://platform.baichuan-ai.com/prices 将 `Baichuan-M3-Plus` / `Baichuan-M3` / `Baichuan-M2-Plus` / `Baichuan-M2` 的上下文长度均列为 `32k` |
|
||||
| `maxOutputTokens` | `32000` | `32000` | 待确认 | 已复核 https://platform.baichuan-ai.com/docs/api 及其官方正文源 `https://platform.baichuan-ai.com/api/gitlab/file` 返回的 `mainDocument.md`；当前通用对话 API 文档确有 `max_tokens` 参数，取值范围为 `[1,2048]`、默认 `2048`，但正文支持模型仅列 `Baichuan4-Turbo` / `Baichuan4-Air` / `Baichuan4` / `Baichuan3-Turbo` / `Baichuan3-Turbo-128k` / `Baichuan2-Turbo`，未覆盖本地 `Baichuan-M2`，因此不能直接据此回填 |
|
||||
| `inputPrice` | `2` | `2` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `20` | `20` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","multilingual"]` | `["chat","reasoning","code","multilingual"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 百川官方通用对话 API 文档 https://platform.baichuan-ai.com/docs/api 及其正文源 `https://platform.baichuan-ai.com/api/gitlab/file` 仅为 `Baichuan4/3/2-Turbo` 系列声明 `temperature` 默认值 `0.3`；未覆盖 `Baichuan-M2`，按“官网未定义该型号默认值”记为 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 百川官方通用对话 API 文档 https://platform.baichuan-ai.com/docs/api 及其正文源 `https://platform.baichuan-ai.com/api/gitlab/file` 仅为 `Baichuan4/3/2-Turbo` 系列声明 `top_p` 默认值 `0.85`；未覆盖 `Baichuan-M2`，按“官网未定义该型号默认值”记为 `null` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
@@ -1,18 +0,0 @@
|
||||
# 未确认字段报告 - compute/providers/baidu.json
|
||||
|
||||
- provider: `baidu`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## ernie-5.0-thinking-latest
|
||||
|
||||
- `inputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `outputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `capabilities`: ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## ernie-4.5-turbo-128k-latest
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
@@ -1,90 +0,0 @@
|
||||
# 详细字段取值表 - compute/providers/baidu.json
|
||||
|
||||
- provider: `baidu`
|
||||
- priceCurrency: `CNY`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://cloud.baidu.com/doc/qianfan/
|
||||
- https://cloud.baidu.com/doc/qianfan/s/rmh4stp0j
|
||||
- https://cloud.baidu.com/doc/qianfan/s/6mh4stoyf
|
||||
- https://zenmux.ai/models
|
||||
- https://zenmux.ai/api/v1/models
|
||||
|
||||
## ernie-5.0-thinking-latest
|
||||
|
||||
- ZenMux匹配级别: `stripped`
|
||||
- ZenMux命中: `baidu/ernie-5.0-thinking-preview`
|
||||
- ZenMux候选: `baidu/ernie-5.0-thinking-preview`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"ernie-5.0-thinking-latest"` | `"ernie-5.0-thinking-latest"` | 保持 | 百度千帆模型列表 https://cloud.baidu.com/doc/qianfan/s/rmh4stp0j 直接列出 `ernie-5.0-thinking-latest` |
|
||||
| `displayName` | `"文心 ERNIE 5.0"` | `"文心 ERNIE 5.0"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat","reasoning"]` | `["chat","reasoning"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `128000` | `128000` | 保持 | 百度千帆模型列表 https://cloud.baidu.com/doc/qianfan/s/rmh4stp0j 标注 `ernie-5.0-thinking-latest` 上下文长度为 `128k` |
|
||||
| `maxOutputTokens` | `65536` | `65536` | 保持 | 百度千帆模型列表 https://cloud.baidu.com/doc/qianfan/s/rmh4stp0j 标注 `ernie-5.0-thinking-latest` 最大输出为 `[1，65536]` |
|
||||
| `inputPrice` | `8` | `8` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `outputPrice` | `32` | `32` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","vision","multimodal","tool_use"]` | `["chat","reasoning","vision","multimodal","tool_use"]` | 待确认 | ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 百度千帆官方“模型默认参数说明” https://cloud.baidu.com/doc/qianfan/s/6mh4stoyf 明确 `ernie-5.0` 系列属于“ERNIE 深度思考模型”，`temperature` 不支持、传入后忽略不报错，因此本地字段应为 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 百度千帆官方“模型默认参数说明” https://cloud.baidu.com/doc/qianfan/s/6mh4stoyf 明确 `ernie-5.0` 系列 `top_p` 不支持、传入后忽略不报错，因此本地字段应为 `null` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## ernie-4.5-turbo-128k-latest
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"ernie-4.5-turbo-128k-latest"` | `"ernie-4.5-turbo-128k-latest"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"文心 ERNIE 4.5 Turbo"` | `"文心 ERNIE 4.5 Turbo"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `131072` | `131072` | 保持 | 百度千帆模型列表 https://cloud.baidu.com/doc/qianfan/s/rmh4stp0j 标注 `ernie-4.5-turbo-128k` 上下文长度为 `128k`；当前值 `131072` 为按 `128 * 1024` 换算 |
|
||||
| `maxOutputTokens` | `12288` | `12288` | 保持 | 百度千帆模型列表 https://cloud.baidu.com/doc/qianfan/s/rmh4stp0j 标注 `ernie-4.5-turbo-128k` 最大输出为 `[2，12288]` |
|
||||
| `inputPrice` | `0.8` | `0.8` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `3.2` | `3.2` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","code","vision","long_context","fast"]` | `["chat","code","vision","long_context","fast"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `0.8` | `0.8` | 保持 | 百度千帆官方“模型默认参数说明” https://cloud.baidu.com/doc/qianfan/s/6mh4stoyf 明确 `ernie-4.5-turbo` 系列 `temperature` 默认值为 `0.8` |
|
||||
| `defaultTopP` | `1` | `1` | 保持 | 百度千帆官方“模型默认参数说明” https://cloud.baidu.com/doc/qianfan/s/6mh4stoyf 明确 `ernie-4.5-turbo` 系列 `top_p` 默认值为 `1.0` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## ernie-5.0
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"ernie-5.0"` | `"ernie-5.0"` | 保持 | 百度千帆默认模型与深度思考文档均直接使用该模型名 |
|
||||
| `displayName` | `"文心 ERNIE 5.0 非思考"` | `"文心 ERNIE 5.0 非思考"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `131072` | `131072` | 保持 | 百度千帆模型列表 https://cloud.baidu.com/doc/qianfan/s/rmh4stp0j 标注 `ernie-5.0` 上下文长度为 `128k`；当前值 `131072` 为按 `128 * 1024` 换算 |
|
||||
| `maxOutputTokens` | `65536` | `65536` | 保持 | 百度千帆模型列表 https://cloud.baidu.com/doc/qianfan/s/rmh4stp0j 标注 `ernie-5.0` 最大输出为 `[1，65536]` |
|
||||
| `inputPrice` | `6` | `6` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `outputPrice` | `24` | `24` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","vision","multimodal","tool_use"]` | `["chat","vision","multimodal","tool_use"]` | 待确认 | 能力字段为项目语义字段，需官方能力说明复核 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 百度千帆官方“模型默认参数说明” https://cloud.baidu.com/doc/qianfan/s/6mh4stoyf 明确 `ernie-5.0` 系列属于“ERNIE 深度思考模型”，`temperature` 不支持、传入后忽略不报错 |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 百度千帆官方“模型默认参数说明” https://cloud.baidu.com/doc/qianfan/s/6mh4stoyf 明确 `ernie-5.0` 系列 `top_p` 不支持、传入后忽略不报错 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## ernie-x1.1
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"ernie-x1.1"` | `"ernie-x1.1"` | 保持 | 百度千帆模型列表直接使用该模型名 |
|
||||
| `displayName` | `"文心 ERNIE X1.1"` | `"文心 ERNIE X1.1"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["reasoning"]` | `["reasoning"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `65536` | `65536` | 保持 | 百度千帆模型列表 https://cloud.baidu.com/doc/qianfan/s/rmh4stp0j 标注 `ernie-x1.1` 上下文长度为 `64k`；当前值 `65536` 为按 `64 * 1024` 换算 |
|
||||
| `maxOutputTokens` | `65536` | `65536` | 保持 | 百度千帆模型列表 https://cloud.baidu.com/doc/qianfan/s/rmh4stp0j 标注 `ernie-x1.1` 最大输出为 `[1，65536]` |
|
||||
| `inputPrice` | `1` | `1` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `outputPrice` | `4` | `4` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","deep_thinking","math","code"]` | `["chat","reasoning","deep_thinking","math","code"]` | 待确认 | 能力字段为项目语义字段，需官方能力说明复核 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 百度千帆官方“模型默认参数说明” https://cloud.baidu.com/doc/qianfan/s/6mh4stoyf 明确 `ernie-x1.1` 系列属于“ERNIE 深度思考模型”，`temperature` 不支持、传入后忽略不报错 |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 百度千帆官方“模型默认参数说明” https://cloud.baidu.com/doc/qianfan/s/6mh4stoyf 明确 `ernie-x1.1` 系列 `top_p` 不支持、传入后忽略不报错 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
@@ -1,7 +0,0 @@
|
||||
# 未确认字段报告 - compute/providers/cohere.json
|
||||
|
||||
- provider: `cohere`
|
||||
- generatedAt: `2026-04-24T00:00:00+08:00`
|
||||
- 本轮范围: `defaultTemperature` / `defaultTopP`
|
||||
|
||||
本轮范围内无剩余未确认项。
|
||||
@@ -1,39 +0,0 @@
|
||||
# 详细字段取值表 - compute/providers/cohere.json
|
||||
|
||||
- provider: `cohere`
|
||||
- generatedAt: `2026-04-24T00:00:00+08:00`
|
||||
- 本轮复核字段: `defaultTemperature` / `defaultTopP`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://docs.cohere.com/reference/chat
|
||||
- https://docs.cohere.com/docs/cohere-embed
|
||||
- https://docs.cohere.com/v2/docs/rerank
|
||||
|
||||
## command-a-03-2025
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `0.3` | `0.3` | 保持 | Cohere Chat API 参考文档明确写明 `temperature` `Defaults to 0.3`。 |
|
||||
| `defaultTopP` | `0.75` | `0.75` | 保持 | Cohere Chat API 参考文档使用参数名 `p`，并明确写明 `Defaults to 0.75`；本项目字段 `defaultTopP` 对应此 nucleus sampling 参数。 |
|
||||
|
||||
## command-r7b-12-2024
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `0.3` | `0.3` | 保持 | Cohere Chat API 参考文档明确写明 `temperature` `Defaults to 0.3`。 |
|
||||
| `defaultTopP` | `0.75` | `0.75` | 保持 | Cohere Chat API 参考文档使用参数名 `p`，并明确写明 `Defaults to 0.75`；本项目字段 `defaultTopP` 对应此 nucleus sampling 参数。 |
|
||||
|
||||
## embed-v4.0
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | Cohere Embed 文档未定义聊天采样参数默认值；embedding 模型不按聊天采样参数工作。 |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | Cohere Embed 文档未定义聊天采样参数默认值；embedding 模型不按聊天采样参数工作。 |
|
||||
|
||||
## rerank-v3.5
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | Cohere Rerank 文档未定义聊天采样参数默认值；rerank 模型不按聊天采样参数工作。 |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | Cohere Rerank 文档未定义聊天采样参数默认值；rerank 模型不按聊天采样参数工作。 |
|
||||
@@ -1,16 +0,0 @@
|
||||
# 未确认字段报告 - compute/coding-plans/dashscope-coding.json
|
||||
|
||||
- provider: `dashscope`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## qwen3-coder-plus
|
||||
|
||||
- `capabilities`: ZenMux给出reasoning=false，但capabilities是项目语义字段，需官方能力说明复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## qwen3-max-2026-01-23
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
@@ -1,51 +0,0 @@
|
||||
# 详细字段取值表 - compute/coding-plans/dashscope-coding.json
|
||||
|
||||
- provider: `dashscope`
|
||||
- priceCurrency: `USD`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://help.aliyun.com/zh/model-studio/getting-started/models
|
||||
- https://help.aliyun.com/zh/model-studio/pricing
|
||||
- https://zenmux.ai/models
|
||||
- https://zenmux.ai/api/v1/models
|
||||
|
||||
## qwen3-coder-plus
|
||||
|
||||
- ZenMux匹配级别: `exact`
|
||||
- ZenMux命中: `qwen/qwen3-coder-plus`
|
||||
- ZenMux候选: `qwen/qwen3-coder-plus`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"qwen3-coder-plus"` | `"qwen3-coder-plus"` | 保持 | ZenMux匹配(exact): qwen/qwen3-coder-plus |
|
||||
| `displayName` | `"Qwen3 Coder Plus (Coding)"` | `"Qwen3 Coder Plus (Coding)"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `1000000` | `1000000` | 保持 | 阿里云百炼模型列表列明 `qwen3-coder-plus` 上下文长度为 `1,000,000` |
|
||||
| `maxOutputTokens` | `65536` | `65536` | 保持 | 阿里云百炼模型列表列明 `qwen3-coder-plus` 最大输出为 `65,536` |
|
||||
| `inputPrice` | `1` | `1` | 保持 | ZenMux(qwen/qwen3-coder-plus) prompt=1 USD/MTokens |
|
||||
| `outputPrice` | `5` | `5` | 保持 | ZenMux(qwen/qwen3-coder-plus) completion=5 USD/MTokens |
|
||||
| `capabilities` | `["chat","reasoning","code","tool_use"]` | `["chat","reasoning","code","tool_use"]` | 待确认 | ZenMux给出reasoning=false，但capabilities是项目语义字段，需官方能力说明复核 |
|
||||
| `defaultTemperature` | `0.7` | `0.7` | 保持 | 已复核阿里云官方 OpenAI Chat / DashScope API 文档，`Qwen3-Coder` 系列默认 `temperature=0.7` |
|
||||
| `defaultTopP` | `0.8` | `0.8` | 保持 | 已复核阿里云官方 OpenAI Chat / DashScope API 文档，`Qwen3-Coder` 系列默认 `top_p=0.8` |
|
||||
| `extra` | (缺省) | (缺省) | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## qwen3-max-2026-01-23
|
||||
|
||||
- ZenMux匹配级别: `ambiguous`
|
||||
- ZenMux候选: `qwen/qwen3-max`、`qwen/qwen3-max-preview`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"qwen3-max-2026-01-23"` | `"qwen3-max-2026-01-23"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"Qwen3 Max (Coding)"` | `"Qwen3 Max (Coding)"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `262144` | `262144` | 保持 | 阿里云百炼模型列表写明稳定版 `qwen3-max` 当前与 `qwen3-max-2026-01-23` 能力相同，且上下文长度为 `262,144` |
|
||||
| `maxOutputTokens` | `65536` | `65536` | 保持 | 同一官方模型列表写明 `qwen3-max` 最大输出为 `65,536`，并注明其当前与 `qwen3-max-2026-01-23` 能力相同 |
|
||||
| `inputPrice` | `1.2` | `1.2` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `6` | `6` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","multilingual","tool_use","long_context","vision"]` | `["chat","reasoning","code","multilingual","tool_use","long_context","vision"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `0.7` | `0.7` | 保持 | 已复核阿里云官方 OpenAI Chat / DashScope API 文档，`qwen-max` 系列默认 `temperature=0.7` |
|
||||
| `defaultTopP` | `0.8` | `0.8` | 保持 | 已复核阿里云官方 OpenAI Chat / DashScope API 文档，`qwen-max` 系列默认 `top_p=0.8` |
|
||||
| `extra` | (缺省) | (缺省) | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
@@ -1,17 +0,0 @@
|
||||
# dashscope-coding ambiguous/similar 逐条处置记录（2026-04-23）
|
||||
|
||||
## 范围
|
||||
|
||||
- 文件：`compute/coding-plans/dashscope-coding.json`
|
||||
- 目标条目：`qwen3-max-2026-01-23`
|
||||
- 依据：阿里云百炼官方模型/计费页 + `https://zenmux.ai/models` + `https://zenmux.ai/api/v1/models`
|
||||
|
||||
## 逐条结论
|
||||
|
||||
| 条目 | ZenMux候选 | 处置 | 是否改JSON | 理由 |
|
||||
|---|---|---|---|---|
|
||||
| `qwen3-max-2026-01-23` | `qwen/qwen3-max`、`qwen/qwen3-max-preview` | 保持现状（确认） | 否 | 本地 `contextWindow=262144` 与 `qwen/qwen3-max-preview` 精确一致；`inputPrice=1.2`、`outputPrice=6` 与该候选阶梯首档一致。当前值已对齐，无需改动。 |
|
||||
|
||||
## 备注
|
||||
|
||||
- 此项由“ambiguous”提升为“可解释匹配（通过上下文长度和命名语义）”，但因字段已一致，所以仅记录处置，不产生 JSON 差异。
|
||||
@@ -1,134 +0,0 @@
|
||||
# 未确认字段报告 - compute/providers/dashscope.json
|
||||
|
||||
- provider: `dashscope`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## qwen3.5-plus
|
||||
|
||||
- `inputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `outputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `capabilities`: ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## qwen-max
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## qwen-plus
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## qwen-turbo
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## qwen-long
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## qwen3-max
|
||||
|
||||
- `inputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `outputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `capabilities`: ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## qwen3-vl-plus
|
||||
|
||||
- `inputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `outputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `capabilities`: ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## qwen3-vl-flash
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## text-embedding-v3
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## text-embedding-v4
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## qwen3-rerank
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## cosyvoice-v2
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## paraformer-v2
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## wanx-v2
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## wanx-video
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## cosyvoice-clone
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## qwen-omni-turbo
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## qwen3-max-trans
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `contextWindow`: 已复核 https://help.aliyun.com/zh/model-studio/machine-translation 、https://help.aliyun.com/zh/model-studio/user-guide/machine-translation 与 https://help.aliyun.com/zh/model-studio/model ，官方当前机器翻译产品线公开的是 `qwen-mt-plus` / `qwen-mt-flash` / `qwen-mt-turbo` / `qwen-mt-lite`；用户指南还明确 `qwen-mt-plus`、`qwen-mt-turbo` 属于 `Qwen3-MT`，但没有任何页面使用 `qwen3-max-trans` 这个模型名，也没有给出本地别名到官方型号的一一映射，因此无法确认本地 `qwen3-max-trans` 的固定上下文窗口
|
||||
- `maxOutputTokens`: 已复核 https://help.aliyun.com/zh/model-studio/machine-translation 、https://help.aliyun.com/zh/model-studio/user-guide/machine-translation 与 https://help.aliyun.com/zh/model-studio/model ，官方机器翻译页确实公开了 `qwen-mt-plus` / `qwen-mt-flash` / `qwen-mt-turbo` / `qwen-mt-lite` 的最大输出规格，但没有任何页面使用 `qwen3-max-trans` 这个模型名，也没有给出别名映射，因此不能把任一 `Qwen-MT` 规格直接回填到本地 `qwen3-max-trans`
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `defaultTemperature`: 已复核 https://help.aliyun.com/zh/model-studio/user-guide/machine-translation 与 https://help.aliyun.com/zh/model-studio/machine-translation ，官方只对 `qwen-mt` 系列给出 `temperature=0.65` 的默认值，但没有提供本地别名 `qwen3-max-trans` 到 `qwen-mt-*` 的官方映射，因此不能把该数字确认为本地模型的官方默认值
|
||||
- `defaultTopP`: 已复核 https://help.aliyun.com/zh/model-studio/user-guide/machine-translation 与 https://help.aliyun.com/zh/model-studio/machine-translation ，官方只对 `qwen-mt` 系列给出 `top_p=0.8` 的默认值，但没有提供本地别名 `qwen3-max-trans` 到 `qwen-mt-*` 的官方映射，因此不能把该数字确认为本地模型的官方默认值
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
@@ -1,365 +0,0 @@
|
||||
# 详细字段取值表 - compute/providers/dashscope.json
|
||||
|
||||
- provider: `dashscope`
|
||||
- priceCurrency: `CNY`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://help.aliyun.com/zh/model-studio/model
|
||||
- https://help.aliyun.com/zh/model-studio/models
|
||||
- https://help.aliyun.com/zh/model-studio/qwen-api-via-openai-chat-completions
|
||||
- https://help.aliyun.com/zh/model-studio/deep-thinking
|
||||
- https://help.aliyun.com/zh/model-studio/vision
|
||||
- https://help.aliyun.com/zh/model-studio/rerank
|
||||
- https://help.aliyun.com/zh/model-studio/text-embedding-synchronous-api
|
||||
- https://help.aliyun.com/zh/model-studio/user-guide/qwen-omni
|
||||
- https://help.aliyun.com/zh/model-studio/machine-translation
|
||||
- https://help.aliyun.com/zh/model-studio/user-guide/machine-translation
|
||||
- https://zenmux.ai/models
|
||||
- https://zenmux.ai/api/v1/models
|
||||
|
||||
## qwen3.5-plus
|
||||
|
||||
- ZenMux匹配级别: `exact`
|
||||
- ZenMux命中: `qwen/qwen3.5-plus`
|
||||
- ZenMux候选: `qwen/qwen3.5-plus`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"qwen3.5-plus"` | `"qwen3.5-plus"` | 保持 | ZenMux匹配(exact): qwen/qwen3.5-plus |
|
||||
| `displayName` | `"阿里云 Qwen3.5-Plus"` | `"阿里云 Qwen3.5-Plus"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `1000000` | `1000000` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/model 标注 `qwen3.5-plus` 稳定版上下文长度为 `1,000,000` |
|
||||
| `maxOutputTokens` | `65536` | `65536` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/model 标注 `qwen3.5-plus` 稳定版最大输出为 `65,536` |
|
||||
| `inputPrice` | `0.8` | `0.8` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `outputPrice` | `4.8` | `4.8` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","multilingual","long_context","tool_use","agent","vision"]` | `["chat","reasoning","code","multilingual","long_context","tool_use","agent","vision"]` | 待确认 | ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核 |
|
||||
| `defaultTemperature` | `0.6` | `0.6` | 保持 | 阿里云 OpenAI Chat API 文档 https://help.aliyun.com/zh/model-studio/qwen-api-via-openai-chat-completions 给出 Qwen3.5 思考模式默认 `temperature=0.6`；视觉理解文档 https://help.aliyun.com/zh/model-studio/vision 明确 `qwen3.5` 系列 `enable_thinking` 默认为 `true` |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | 阿里云 OpenAI Chat API 文档 https://help.aliyun.com/zh/model-studio/qwen-api-via-openai-chat-completions 给出 Qwen3.5 思考模式默认 `top_p=0.95`；视觉理解文档确认 `qwen3.5` 系列默认开启思考 |
|
||||
| `extra` | `{"pricingTiers":[{"maxInputTokens":128000,"inputPrice":0.8,"outputPrice":4.8},{"maxInputTokens":256000,"inputPrice":2,"outputPrice":12},{"maxInputTokens":1000000,"inputPrice":4,"outputPrice":24}],"thinkingMaxTokens":81920}` | `{"pricingTiers":[{"maxInputTokens":128000,"inputPrice":0.8,"outputPrice":4.8},{"maxInputTokens":256000,"inputPrice":2,"outputPrice":12},{"maxInputTokens":1000000,"inputPrice":4,"outputPrice":24}],"thinkingMaxTokens":81920}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## qwen-max
|
||||
|
||||
- ZenMux匹配级别: `ambiguous`
|
||||
- ZenMux候选: `qwen/qwen3-max`、`qwen/qwen3-max-preview`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"qwen-max"` | `"qwen-max"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"阿里云 qwen-max"` | `"阿里云 qwen-max"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `32768` | `32768` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/models 标注 `qwen-max` 稳定版当前与 `qwen-max-2025-01-25` 能力相同，上下文长度为 `32,768` |
|
||||
| `maxOutputTokens` | `8192` | `8192` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/models 标注 `qwen-max` 稳定版最大输出为 `8,192` |
|
||||
| `inputPrice` | `2.4` | `2.4` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `9.6` | `9.6` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","multilingual","long_context"]` | `["chat","reasoning","code","multilingual","long_context"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `0.7` | `0.7` | 保持 | 阿里云 OpenAI Chat API 文档 https://help.aliyun.com/zh/model-studio/qwen-api-via-openai-chat-completions 将 `qwen-max` 系列默认 `temperature` 标注为 `0.7` |
|
||||
| `defaultTopP` | `0.8` | `0.8` | 保持 | 阿里云 OpenAI Chat API 文档 https://help.aliyun.com/zh/model-studio/qwen-api-via-openai-chat-completions 将 `qwen-max` 系列默认 `top_p` 标注为 `0.8` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## qwen-plus
|
||||
|
||||
- ZenMux匹配级别: `ambiguous`
|
||||
- ZenMux候选: `qwen/qwen3.6-plus`、`qwen/qwen3.5-plus`、`qwen/qwen3-vl-plus`、`qwen/qwen3-coder-plus`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"qwen-plus"` | `"qwen-plus"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"阿里云 qwen-plus"` | `"阿里云 qwen-plus"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `1000000` | `1000000` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/model 标注 `qwen-plus` 稳定版非思考模式上下文为 `1,000,000`，思考模式为 `995,904`；当前字段按稳定版上限保留 `1,000,000` |
|
||||
| `maxOutputTokens` | `32768` | `32768` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/model 标注 `qwen-plus` 稳定版最大输出为 `32,768` |
|
||||
| `inputPrice` | `0.8` | `0.8` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `2` | `2` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","thinking_mode"]` | `["chat","reasoning","code","thinking_mode"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 阿里云 OpenAI Chat API 文档 https://help.aliyun.com/zh/model-studio/qwen-api-via-openai-chat-completions 只区分 `qwen-plus` 系列思考/非思考两套参数；深度思考文档 https://help.aliyun.com/zh/model-studio/deep-thinking 说明该模型支持 `enable_thinking` 切换，但官网没有给“省略 `enable_thinking` 时”的单一默认值，因此本地字段应为 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 官网仅给出模式相关参数口径，未给 `qwen-plus` 稳定版在省略 `enable_thinking` 时的单一 `top_p` 默认值，因此本地字段应为 `null` |
|
||||
| `extra` | `{"pricingTiers":[{"maxInputTokens":128000,"inputPrice":0.8,"outputPrice":2,"thinkingOutputPrice":8},{"maxInputTokens":256000,"inputPrice":2.4,"outputPrice":20,"thinkingOutputPrice":24},{"maxInputTokens":1000000,"inputPrice":4.8,"outputPrice":48,"thinkingOutputPrice":64}],"thinkingMaxTokens":81920}` | `{"pricingTiers":[{"maxInputTokens":128000,"inputPrice":0.8,"outputPrice":2,"thinkingOutputPrice":8},{"maxInputTokens":256000,"inputPrice":2.4,"outputPrice":20,"thinkingOutputPrice":24},{"maxInputTokens":1000000,"inputPrice":4.8,"outputPrice":48,"thinkingOutputPrice":64}],"thinkingMaxTokens":81920}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## qwen-turbo
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"qwen-turbo"` | `"qwen-turbo"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"阿里云 qwen-turbo"` | `"阿里云 qwen-turbo"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `1000000` | `1000000` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/model 标注 `qwen-turbo` 稳定版非思考模式上下文为 `1,000,000`，思考模式为 `131,072`；当前字段按非思考模式上限保留 `1,000,000` |
|
||||
| `maxOutputTokens` | `16384` | `16384` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/model 标注 `qwen-turbo` 稳定版最大输出为 `16,384` |
|
||||
| `inputPrice` | `0.367` | `0.367` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `1.468` | `1.468` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","code","long_context","fast"]` | `["chat","code","long_context","fast"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 阿里云 OpenAI Chat API 文档 https://help.aliyun.com/zh/model-studio/qwen-api-via-openai-chat-completions 只给出 `qwen-turbo` 非思考模式默认值；官网未说明稳定版省略 `enable_thinking` 时是否默认进入思考模式，因此本地字段应为 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 官网未公开 `qwen-turbo` 在省略 `enable_thinking` 时的单一模型级 `top_p` 默认值，因此本地字段应为 `null` |
|
||||
| `extra` | `{"thinkingContextWindow":131072,"thinkingOutputPrice":3.67,"thinkingMaxTokens":38912}` | `{"thinkingContextWindow":131072,"thinkingOutputPrice":3.67,"thinkingMaxTokens":38912}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## qwen-long
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"qwen-long"` | `"qwen-long"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"阿里云 qwen-long"` | `"阿里云 qwen-long"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `10000000` | `10000000` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/models 标注 `qwen-long` 稳定版上下文长度为 `10,000,000` |
|
||||
| `maxOutputTokens` | `32768` | `32768` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/models 标注 `qwen-long` 稳定版最大输出为 `32,768` |
|
||||
| `inputPrice` | `0.5` | `0.5` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `2` | `2` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","ultra_long_context","document_processing"]` | `["chat","ultra_long_context","document_processing"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | 阿里云 OpenAI Chat API 文档 https://help.aliyun.com/zh/model-studio/qwen-api-via-openai-chat-completions 将 `qwen-long` 系列默认 `temperature` 标注为 `1.0` |
|
||||
| `defaultTopP` | `0.8` | `0.8` | 保持 | 阿里云 OpenAI Chat API 文档 https://help.aliyun.com/zh/model-studio/qwen-api-via-openai-chat-completions 将 `qwen-long` 系列默认 `top_p` 标注为 `0.8` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## qwen3-max
|
||||
|
||||
- ZenMux匹配级别: `exact`
|
||||
- ZenMux命中: `qwen/qwen3-max`
|
||||
- ZenMux候选: `qwen/qwen3-max`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"qwen3-max"` | `"qwen3-max"` | 保持 | ZenMux匹配(exact): qwen/qwen3-max |
|
||||
| `displayName` | `"阿里云 Qwen3-Max"` | `"阿里云 Qwen3-Max"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `256000` | `262144` | 建议修改 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/model 标注 `qwen3-max` 稳定版上下文长度为 `262,144` |
|
||||
| `maxOutputTokens` | `65536` | `65536` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/model 标注 `qwen3-max` 非思考模式最大输出为 `65,536`，思考模式为 `32,768`；当前字段按单模型绝对最大输出保留 `65,536` |
|
||||
| `inputPrice` | `2.5` | `2.5` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `outputPrice` | `10` | `10` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","multilingual","long_context","tool_use","agent","vision"]` | `["chat","reasoning","code","multilingual","long_context","tool_use","agent","vision"]` | 待确认 | ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 阿里云 OpenAI Chat API 文档 https://help.aliyun.com/zh/model-studio/qwen-api-via-openai-chat-completions 对 `Qwen3` 仅区分思考/非思考两套默认参数；官网没有给 `qwen3-max` 稳定版省略思考开关时的单一默认值，因此本地字段应为 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 官网未公开 `qwen3-max` 稳定版在省略思考开关时的单一模型级 `top_p` 默认值，因此本地字段应为 `null` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## qwen3-vl-plus
|
||||
|
||||
- ZenMux匹配级别: `exact`
|
||||
- ZenMux命中: `qwen/qwen3-vl-plus`
|
||||
- ZenMux候选: `qwen/qwen3-vl-plus`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"qwen3-vl-plus"` | `"qwen3-vl-plus"` | 保持 | ZenMux匹配(exact): qwen/qwen3-vl-plus |
|
||||
| `displayName` | `"阿里云 Qwen3-VL-Plus"` | `"阿里云 Qwen3-VL-Plus"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["vision"]` | `["vision"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `262144` | `262144` | 保持 | ZenMux(qwen/qwen3-vl-plus)口径近似（≤3%） |
|
||||
| `maxOutputTokens` | `8192` | `32768` | 建议修改 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/models 标注 `qwen3-vl-plus` 稳定版最大输出为 `32,768` |
|
||||
| `inputPrice` | `1.5` | `1.5` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `outputPrice` | `6` | `6` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","vision","image_understanding","ocr","chart_analysis"]` | `["chat","vision","image_understanding","ocr","chart_analysis"]` | 待确认 | ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核 |
|
||||
| `defaultTemperature` | `0.7` | `0.7` | 保持 | 阿里云 OpenAI Chat API 文档 https://help.aliyun.com/zh/model-studio/qwen-api-via-openai-chat-completions 给出 `Qwen3-VL` 非思考模式默认 `temperature=0.7`；视觉理解文档 https://help.aliyun.com/zh/model-studio/vision 明确 `qwen3-vl-plus` 默认 `enable_thinking=false` |
|
||||
| `defaultTopP` | `0.8` | `0.8` | 保持 | 阿里云 OpenAI Chat API 文档给出 `Qwen3-VL` 非思考模式默认 `top_p=0.8`；视觉理解文档确认 `qwen3-vl-plus` 默认关闭思考 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## qwen3-vl-flash
|
||||
|
||||
- ZenMux匹配级别: `ambiguous`
|
||||
- ZenMux候选: `qwen/qwen3.5-flash`、`qwen/qwen3-vl-plus`、`qwen/qwen3-max`、`qwen/qwen3-coder`、`qwen/qwen3-14b`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"qwen3-vl-flash"` | `"qwen3-vl-flash"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"阿里云 Qwen3-VL-Flash"` | `"阿里云 Qwen3-VL-Flash"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["vision"]` | `["vision"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `131072` | `262144` | 建议修改 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/models 标注 `qwen3-vl-flash` 稳定版上下文长度为 `262,144` |
|
||||
| `maxOutputTokens` | `8192` | `32768` | 建议修改 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/models 标注 `qwen3-vl-flash` 稳定版最大输出为 `32,768` |
|
||||
| `inputPrice` | `0.8` | `0.8` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `3` | `3` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","vision","image_understanding","fast"]` | `["chat","vision","image_understanding","fast"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `0.7` | `0.7` | 保持 | 阿里云 OpenAI Chat API 文档 https://help.aliyun.com/zh/model-studio/qwen-api-via-openai-chat-completions 给出 `Qwen3-VL` 非思考模式默认 `temperature=0.7`；视觉理解文档 https://help.aliyun.com/zh/model-studio/vision 明确 `qwen3-vl-flash` 默认 `enable_thinking=false` |
|
||||
| `defaultTopP` | `0.8` | `0.8` | 保持 | 阿里云 OpenAI Chat API 文档给出 `Qwen3-VL` 非思考模式默认 `top_p=0.8`；视觉理解文档确认 `qwen3-vl-flash` 默认关闭思考 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## text-embedding-v3
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"text-embedding-v3"` | `"text-embedding-v3"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"text-embedding-v3"` | `"text-embedding-v3"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["embedding"]` | `["embedding"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `8192` | `8192` | 保持 | 阿里云 Embedding 同步接口文档 https://help.aliyun.com/zh/model-studio/text-embedding-synchronous-api 标注 `text-embedding-v3` 单行最大 Token 数为 `8,192` |
|
||||
| `maxOutputTokens` | `0` | `0` | 保持 | 阿里云 Embedding 同步接口文档 https://help.aliyun.com/zh/model-studio/text-embedding-synchronous-api 说明 `text-embedding-v3` 输出为向量维度，不定义 max output tokens |
|
||||
| `inputPrice` | `0.7` | `0.7` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["text_embedding","semantic_search","chinese_optimized"]` | `["text_embedding","semantic_search","chinese_optimized"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 阿里云 Embedding 同步接口文档 https://help.aliyun.com/zh/model-studio/text-embedding-synchronous-api 仅定义输入文本、向量维度等参数，不支持采样参数；`defaultTemperature` 应为 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 阿里云 Embedding 同步接口文档未定义 `top_p`；Embedding 模型不支持采样参数，因此字段应为 `null` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## text-embedding-v4
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"text-embedding-v4"` | `"text-embedding-v4"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"阿里云 text-embedding-v4"` | `"阿里云 text-embedding-v4"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["embedding"]` | `["embedding"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `8192` | `8192` | 保持 | 阿里云 Embedding 同步接口文档 https://help.aliyun.com/zh/model-studio/text-embedding-synchronous-api 标注 `text-embedding-v4` 单行最大 Token 数为 `8,192` |
|
||||
| `maxOutputTokens` | `0` | `0` | 保持 | 阿里云 Embedding 同步接口文档 https://help.aliyun.com/zh/model-studio/text-embedding-synchronous-api 说明 `text-embedding-v4` 输出为向量维度，不定义 max output tokens |
|
||||
| `inputPrice` | `0.5` | `0.5` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["text_embedding","semantic_search","rag"]` | `["text_embedding","semantic_search","rag"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 阿里云 Embedding 同步接口文档 https://help.aliyun.com/zh/model-studio/text-embedding-synchronous-api 仅定义输入文本、向量维度等参数，不支持采样参数；`defaultTemperature` 应为 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 阿里云 Embedding 同步接口文档未定义 `top_p`；Embedding 模型不支持采样参数，因此字段应为 `null` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## qwen3-rerank
|
||||
|
||||
- ZenMux匹配级别: `ambiguous`
|
||||
- ZenMux候选: `qwen/qwen3-max`、`qwen/qwen3-coder`、`qwen/qwen3-14b`、`qwen/qwen3.6-plus`、`qwen/qwen3.5-flash`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"qwen3-rerank"` | `"qwen3-rerank"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"Qwen3-Rerank"` | `"Qwen3-Rerank"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["rerank"]` | `["rerank"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `30000` | `120000` | 建议修改 | 阿里云 Rerank 文档 https://help.aliyun.com/zh/model-studio/rerank 标注 `qwen3-rerank` 单次请求最大 Token 数为 `120,000` |
|
||||
| `maxOutputTokens` | `0` | `0` | 保持 | 阿里云 Rerank 文档 https://help.aliyun.com/zh/model-studio/rerank 说明 `qwen3-rerank` 输出为排序分数与文档顺序，不定义 max output tokens |
|
||||
| `inputPrice` | `1` | `1` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["rerank","semantic_reranking","multilingual"]` | `["rerank","semantic_reranking","multilingual"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 阿里云 Rerank 文档 https://help.aliyun.com/zh/model-studio/rerank 仅定义检索文本、文档列表等重排序参数，不支持采样参数；字段应为 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 阿里云 Rerank 文档未定义 `top_p`；重排序模型不支持采样参数，因此字段应为 `null` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## cosyvoice-v2
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"cosyvoice-v2"` | `"cosyvoice-v2"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"CosyVoice V2"` | `"CosyVoice V2"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["tts"]` | `["tts"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `0` | `0` | 保持 | 阿里云语音合成文档 https://help.aliyun.com/model-studio/developer-reference/quick-start-cosyvoice 对 `cosyvoice-v2` 描述为 TTS 模型，`contextWindow` 不适用 |
|
||||
| `maxOutputTokens` | `0` | `0` | 保持 | 阿里云语音合成文档 https://help.aliyun.com/model-studio/developer-reference/quick-start-cosyvoice 对 `cosyvoice-v2` 描述为 TTS 模型，`maxOutputTokens` 不适用 |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["tts","multilingual","chinese_optimized"]` | `["tts","multilingual","chinese_optimized"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 阿里云语音合成文档 https://help.aliyun.com/model-studio/developer-reference/quick-start-cosyvoice 仅定义语音、音色、格式等参数，不支持采样参数；字段应为 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 阿里云语音合成文档未定义 `top_p`；TTS 模型不支持采样参数，因此字段应为 `null` |
|
||||
| `extra` | `{"voices":["longxiaochun","longxiaoxia","longlaotie","longshu"],"supportedAudioFormats":["mp3","wav","pcm"]}` | `{"voices":["longxiaochun","longxiaoxia","longlaotie","longshu"],"supportedAudioFormats":["mp3","wav","pcm"]}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## paraformer-v2
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"paraformer-v2"` | `"paraformer-v2"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"Paraformer V2"` | `"Paraformer V2"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["asr"]` | `["asr"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `0` | `0` | 保持 | 阿里云 ASR 文档 https://help.aliyun.com/document_detail/2840914.html 对 `paraformer-v2` 描述为语音识别模型，`contextWindow` 不适用 |
|
||||
| `maxOutputTokens` | `0` | `0` | 保持 | 阿里云 ASR 文档 https://help.aliyun.com/document_detail/2840914.html 对 `paraformer-v2` 描述为语音识别模型，`maxOutputTokens` 不适用 |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["asr","chinese_optimized"]` | `["asr","chinese_optimized"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 阿里云 ASR 文档 https://help.aliyun.com/document_detail/2840914.html 仅定义音频识别参数，不支持采样参数；字段应为 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 阿里云 ASR 文档未定义 `top_p`；ASR 模型不支持采样参数，因此字段应为 `null` |
|
||||
| `extra` | `{"maxAudioLength":3600,"supportedInputFormats":["wav","mp3","pcm","ogg"],"streamingSupported":true}` | `{"maxAudioLength":3600,"supportedInputFormats":["wav","mp3","pcm","ogg"],"streamingSupported":true}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## wanx-v2
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"wanx-v2"` | `"wanx-v2"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"通义万相 V2"` | `"通义万相 V2"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["image_gen"]` | `["image_gen"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `0` | `0` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/models 将 `wanx-v2` 归为图像生成模型，`contextWindow` 不适用 |
|
||||
| `maxOutputTokens` | `0` | `0` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/models 将 `wanx-v2` 归为图像生成模型，`maxOutputTokens` 不适用 |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["image_generation","chinese_optimized"]` | `["image_generation","chinese_optimized"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/models 将 `wanx-v2` 归为图像生成模型，官方接口未定义 `temperature` 默认值；本地字段应为 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 阿里云图像生成相关文档未定义 `top_p`；图像生成模型不支持该采样字段时应记为 `null` |
|
||||
| `extra` | `{"supportedImageSizes":["1024x1024","720x1280","1280x720"],"supportedStyles":["auto","photography","anime","3d_cartoon"]}` | `{"supportedImageSizes":["1024x1024","720x1280","1280x720"],"supportedStyles":["auto","photography","anime","3d_cartoon"]}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## wanx-video
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"wanx-video"` | `"wanx-video"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"通义万相视频"` | `"通义万相视频"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["video_gen"]` | `["video_gen"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `0` | `0` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/models 将 `wanx-video` 归为视频生成模型，`contextWindow` 不适用 |
|
||||
| `maxOutputTokens` | `0` | `0` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/models 将 `wanx-video` 归为视频生成模型，`maxOutputTokens` 不适用 |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["video_generation","chinese_optimized"]` | `["video_generation","chinese_optimized"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/models 将 `wanx-video` 归为视频生成模型，官方接口未定义 `temperature` 默认值；本地字段应为 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 阿里云视频生成相关文档未定义 `top_p`；视频生成模型不支持该采样字段时应记为 `null` |
|
||||
| `extra` | `{"maxVideoDuration":10,"supportedResolutions":["720p","1080p"]}` | `{"maxVideoDuration":10,"supportedResolutions":["720p","1080p"]}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## cosyvoice-clone
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"cosyvoice-clone"` | `"cosyvoice-clone"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"CosyVoice 声音复刻"` | `"CosyVoice 声音复刻"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["voice_clone"]` | `["voice_clone"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `0` | `0` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/models 将该能力归为语音/声音定制类服务，`contextWindow` 不适用 |
|
||||
| `maxOutputTokens` | `0` | `0` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/models 将该能力归为语音/声音定制类服务，`maxOutputTokens` 不适用 |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["voice_clone","chinese_optimized","few_shot"]` | `["voice_clone","chinese_optimized","few_shot"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/models 将该能力归为声音定制类服务，官方接口未定义采样参数；字段应为 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 声音复刻能力未定义 `top_p`；该字段不适用，应为 `null` |
|
||||
| `extra` | `{"maxCloneSamples":5,"minCloneDuration":3}` | `{"maxCloneSamples":5,"minCloneDuration":3}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## qwen-omni-turbo
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"qwen-omni-turbo"` | `"qwen-omni-turbo"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"Qwen-Omni-Turbo"` | `"Qwen-Omni-Turbo"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["omni"]` | `["omni"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `32768` | `32768` | 保持 | 阿里云 Qwen-Omni 文档 https://help.aliyun.com/zh/model-studio/user-guide/qwen-omni 标注 `qwen-omni-turbo` 上下文长度为 `32,768` |
|
||||
| `maxOutputTokens` | `2048` | `2048` | 保持 | 阿里云 Qwen-Omni 文档 https://help.aliyun.com/zh/model-studio/user-guide/qwen-omni 标注 `qwen-omni-turbo` 最大输出为 `2,048` |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","vision","tts","asr","multimodal","tool_use"]` | `["chat","vision","tts","asr","multimodal","tool_use"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 阿里云 OpenAI Chat API 文档 https://help.aliyun.com/zh/model-studio/qwen-api-via-openai-chat-completions 给出了 `qwen-omni-turbo` 系列 `top_p` 默认值，但未给非实时 Qwen-Omni 的 `temperature` 默认值；因此本地 `defaultTemperature` 应为 `null` |
|
||||
| `defaultTopP` | `0.01` | `0.01` | 保持 | 阿里云 OpenAI Chat API 文档 https://help.aliyun.com/zh/model-studio/qwen-api-via-openai-chat-completions 明确 `qwen-omni-turbo` 系列默认 `top_p=0.01` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## qwen3-max-trans
|
||||
|
||||
- ZenMux匹配级别: `ambiguous`
|
||||
- ZenMux候选: `qwen/qwen3-max`、`qwen/qwen3-max-preview`、`qwen/qwen3-coder`、`qwen/qwen3-14b`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"qwen3-max-trans"` | `"qwen3-max-trans"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"Qwen3-Max（翻译）"` | `"Qwen3-Max（翻译）"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["translation"]` | `["translation"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `131072` | `131072` | 待确认 | 已复核 https://help.aliyun.com/zh/model-studio/machine-translation 、https://help.aliyun.com/zh/model-studio/user-guide/machine-translation 与 https://help.aliyun.com/zh/model-studio/model ，官方当前机器翻译产品线公开的是 `qwen-mt-plus` / `qwen-mt-flash` / `qwen-mt-turbo` / `qwen-mt-lite`；用户指南还明确 `qwen-mt-plus`、`qwen-mt-turbo` 属于 `Qwen3-MT`，但没有任何页面使用 `qwen3-max-trans` 这个模型名，也没有给出本地别名到官方型号的一一映射，因此无法确认本地 `qwen3-max-trans` 的固定上下文窗口 |
|
||||
| `maxOutputTokens` | `8192` | `8192` | 待确认 | 已复核 https://help.aliyun.com/zh/model-studio/machine-translation 、https://help.aliyun.com/zh/model-studio/user-guide/machine-translation 与 https://help.aliyun.com/zh/model-studio/model ，官方机器翻译页确实公开了 `qwen-mt-plus` / `qwen-mt-flash` / `qwen-mt-turbo` / `qwen-mt-lite` 的最大输出规格，但没有任何页面使用 `qwen3-max-trans` 这个模型名，也没有给出别名映射，因此不能把任一 `Qwen-MT` 规格直接回填到本地 `qwen3-max-trans` |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["translation","multilingual","chinese_optimized"]` | `["translation","multilingual","chinese_optimized"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 阿里云机器翻译文档 https://help.aliyun.com/zh/model-studio/user-guide/machine-translation 为 `qwen-mt` 系列给出 `temperature=0.65`、`top_p=0.8` 的参考默认值，但官方没有给出本地别名 `qwen3-max-trans` 到 `qwen-mt-*` 的一一映射，因此本地字段不能伪装成官方默认值，应为 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 机器翻译文档中的 `0.8` 仅能作为 `qwen-mt` 系列参考值；在没有官方别名映射前，`qwen3-max-trans` 的 `defaultTopP` 不能确认为官方默认值，应为 `null` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
@@ -1,38 +0,0 @@
|
||||
# dashscope ambiguous/similar 逐条处置记录（2026-04-23）
|
||||
|
||||
## 范围
|
||||
|
||||
- 文件：`compute/providers/dashscope.json`
|
||||
- 目标条目：`qwen-max`、`qwen-plus`、`qwen3-vl-flash`、`qwen3-rerank`、`qwen3-max-trans`
|
||||
- 依据：阿里云百炼官方模型/计费页 + `https://zenmux.ai/models` + `https://zenmux.ai/api/v1/models`
|
||||
|
||||
## 逐条结论
|
||||
|
||||
| 条目 | ZenMux候选 | 处置 | 是否改JSON | 理由 |
|
||||
|---|---|---|---|---|
|
||||
| `qwen-max` | `qwen/qwen3-max`、`qwen/qwen3-max-preview` | 不修改 | 否 | 本地为 legacy 命名（`qwen-max`，32K）；ZenMux 候选是 Qwen3 Max 系列，规格口径不一致，不能直接覆盖。 |
|
||||
| `qwen-plus` | `qwen/qwen3.6-plus`、`qwen/qwen3.5-plus`、`qwen/qwen3-vl-plus`、`qwen/qwen3-coder-plus` | 不修改 | 否 | 候选跨模型族（chat/vl/coder），且价格阶梯与本地 `qwen-plus` 不可唯一对齐，拒绝强匹配。 |
|
||||
| `qwen3-vl-flash` | `qwen/qwen3.5-flash`、`qwen/qwen3-vl-plus`、`qwen/qwen3-max`、`qwen/qwen3-coder`、`qwen/qwen3-14b` | 不修改 | 否 | ZenMux 未给出 `qwen3-vl-flash` 同名条目；候选包含非视觉模型，无法唯一映射。 |
|
||||
| `qwen3-rerank` | `qwen/qwen3-max`、`qwen/qwen3-coder`、`qwen/qwen3-14b`、`qwen/qwen3.6-plus`、`qwen/qwen3.5-flash` | 不修改 | 否 | 本地是 `rerank` 服务类型，ZenMux 候选均为生成模型，服务类型不一致。 |
|
||||
| `qwen3-max-trans` | `qwen/qwen3-max`、`qwen/qwen3-max-preview`、`qwen/qwen3-coder`、`qwen/qwen3-14b` | 不修改 | 否 | 本地是翻译专用路由（`translation`），ZenMux 候选为通用生成模型，无法安全映射。 |
|
||||
|
||||
## 备注
|
||||
|
||||
- 本批次没有可“唯一确认且与本地值不同”的字段，因此 `compute/providers/dashscope.json` 无变更。
|
||||
|
||||
## none 条目补齐（第2轮）
|
||||
|
||||
依据（官方）：
|
||||
- 阿里云百炼模型概览：`https://help.aliyun.com/zh/model-studio/models`
|
||||
- 文本向量模型 v3/v4 文档：`https://help.aliyun.com/zh/model-studio/developer-reference/text-embedding-v3`
|
||||
- 文本排序（Rerank）文档：`https://help.aliyun.com/zh/model-studio/developer-reference/text-rerank-api`
|
||||
|
||||
已执行：
|
||||
1. `text-embedding-v3`：新增 `contextWindow: 8192`
|
||||
2. `text-embedding-v4`：新增 `contextWindow: 8192`
|
||||
3. `qwen3-rerank`：新增 `contextWindow: 30000`（按官方“单次请求最大 Token”）
|
||||
|
||||
未改项（说明）：
|
||||
- `text-embedding-v3/v4` 的 `maxOutputTokens` 与 `outputPrice` 保持缺省：Embedding 为输入向量化，不走 completion token 口径。
|
||||
- `qwen3-rerank` 的 `maxOutputTokens` 保持缺省：Rerank 返回排序结果，不是文本生成输出。
|
||||
- 语音/图像/视频模型（`cosyvoice`/`paraformer`/`wanx`）的 token 上下文与输出上限口径不统一，继续待官方明确 token 语义映射。
|
||||
@@ -1,18 +0,0 @@
|
||||
# 未确认字段报告 - compute/providers/deepseek.json
|
||||
|
||||
- provider: `deepseek`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## deepseek-chat
|
||||
|
||||
- `inputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `outputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `capabilities`: ZenMux给出reasoning=false，但capabilities是项目语义字段，需官方能力说明复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## deepseek-reasoner
|
||||
|
||||
- `inputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `outputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `capabilities`: ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
@@ -1,54 +0,0 @@
|
||||
# 详细字段取值表 - compute/providers/deepseek.json
|
||||
|
||||
- provider: `deepseek`
|
||||
- priceCurrency: `CNY`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://api-docs.deepseek.com/quick_start/pricing
|
||||
- https://api-docs.deepseek.com/api/create-chat-completion
|
||||
- https://api-docs.deepseek.com/guides/reasoning_model
|
||||
- https://api-docs.deepseek.com/quick_start/parameter_settings
|
||||
- https://zenmux.ai/models
|
||||
- https://zenmux.ai/api/v1/models
|
||||
|
||||
## deepseek-chat
|
||||
|
||||
- ZenMux匹配级别: `exact`
|
||||
- ZenMux命中: `deepseek/deepseek-chat`
|
||||
- ZenMux候选: `deepseek/deepseek-chat`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"deepseek-chat"` | `"deepseek-chat"` | 保持 | ZenMux匹配(exact): deepseek/deepseek-chat |
|
||||
| `displayName` | `"DeepSeek V3.2"` | `"DeepSeek V3.2"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `128000` | `128000` | 保持 | ZenMux(deepseek/deepseek-chat)口径近似（≤3%） |
|
||||
| `maxOutputTokens` | `8192` | `8192` | 保持 | DeepSeek 官方模型与价格页 https://api-docs.deepseek.com/quick_start/pricing/ 标注 `deepseek-chat` 最大输出为 8K |
|
||||
| `inputPrice` | `2` | `2` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `outputPrice` | `8` | `8` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","code","reasoning","multilingual"]` | `["chat","code","reasoning","multilingual"]` | 待确认 | ZenMux给出reasoning=false，但capabilities是项目语义字段，需官方能力说明复核 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | DeepSeek 官方 Chat Completions API https://api-docs.deepseek.com/api/create-chat-completion 将 `temperature` schema 默认值标注为 `1`；参数设置页 https://api-docs.deepseek.com/quick_start/parameter_settings 也写明默认值为 `1.0` |
|
||||
| `defaultTopP` | `1` | `1` | 保持 | DeepSeek 官方 Chat Completions API https://api-docs.deepseek.com/api/create-chat-completion 将 `top_p` schema 默认值标注为 `1` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## deepseek-reasoner
|
||||
|
||||
- ZenMux匹配级别: `exact`
|
||||
- ZenMux命中: `deepseek/deepseek-reasoner`
|
||||
- ZenMux候选: `deepseek/deepseek-reasoner`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"deepseek-reasoner"` | `"deepseek-reasoner"` | 保持 | ZenMux匹配(exact): deepseek/deepseek-reasoner |
|
||||
| `displayName` | `"DeepSeek R1"` | `"DeepSeek R1"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["reasoning"]` | `["reasoning"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `128000` | `128000` | 保持 | ZenMux(deepseek/deepseek-reasoner)口径近似（≤3%） |
|
||||
| `maxOutputTokens` | `65536` | `65536` | 保持 | DeepSeek 官方模型与价格页 https://api-docs.deepseek.com/quick_start/pricing/ 与推理模型文档 https://api-docs.deepseek.com/guides/reasoning_model 均标注 `deepseek-reasoner` 最大输出为 64K |
|
||||
| `inputPrice` | `4` | `4` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `outputPrice` | `16` | `16` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","deep_thinking","code","math"]` | `["chat","reasoning","deep_thinking","code","math"]` | 待确认 | ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | DeepSeek 官方推理模型文档 https://api-docs.deepseek.com/guides/reasoning_model 明确 `deepseek-reasoner` 不支持参数 `temperature`，因此本地字段应为 `null` 而不是伪装成默认值 |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | DeepSeek 官方推理模型文档 https://api-docs.deepseek.com/guides/reasoning_model 明确 `deepseek-reasoner` 不支持参数 `top_p`，因此本地字段应为 `null` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
@@ -1,13 +0,0 @@
|
||||
# 未确认字段报告 - compute/providers/google.json
|
||||
|
||||
- provider: `google`
|
||||
- generatedAt: `2026-04-24T00:00:00+08:00`
|
||||
- 本轮范围: `defaultTemperature` / `defaultTopP`
|
||||
|
||||
## gemini-2.5-pro
|
||||
|
||||
- `defaultTemperature`: 已查 https://ai.google.dev/api/models 、https://ai.google.dev/gemini-api/docs/text-generation 。官方明确说明模型元数据里存在 backend 默认值，但公共文档没有直接给出 Gemini 2.5 的默认温度数字；本地原值 `1` 只能视为参考值，不能作为官方默认值写入 JSON。
|
||||
|
||||
## gemini-2.5-flash
|
||||
|
||||
- `defaultTemperature`: 已查 https://ai.google.dev/api/models 、https://ai.google.dev/gemini-api/docs/text-generation 。官方明确说明模型元数据里存在 backend 默认值，但公共文档没有直接给出 Gemini 2.5 的默认温度数字；本地原值 `1` 只能视为参考值，不能作为官方默认值写入 JSON。
|
||||
@@ -1,55 +0,0 @@
|
||||
# 详细字段取值表 - compute/providers/google.json
|
||||
|
||||
- provider: `google`
|
||||
- generatedAt: `2026-04-24T00:00:00+08:00`
|
||||
- 本轮复核字段: `defaultTemperature` / `defaultTopP`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://ai.google.dev/api/models
|
||||
- https://ai.google.dev/gemini-api/docs/text-generation
|
||||
- https://ai.google.dev/gemini-api/docs/gemini-3
|
||||
- https://ai.google.dev/gemini-api/docs/prompting-strategies
|
||||
- https://cloud.google.com/vertex-ai/generative-ai/docs/embeddings/get-text-embeddings
|
||||
|
||||
## gemini-3.1-pro-preview
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | Gemini 3 文档明确写明 `temperature` 的默认值为 `1.0`。 |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | Prompting strategies 文档明确写明 `topP` 的默认值为 `0.95`；Models API 文档说明该值是 backend 默认值。 |
|
||||
|
||||
## gemini-3-flash-preview
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | Gemini 3 文档明确写明 `temperature` 的默认值为 `1.0`。 |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | Prompting strategies 文档明确写明 `topP` 的默认值为 `0.95`；Models API 文档说明该值是 backend 默认值。 |
|
||||
|
||||
## gemini-3.1-flash-lite-preview
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | Gemini 3 文档明确写明 `temperature` 的默认值为 `1.0`。 |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | Prompting strategies 文档明确写明 `topP` 的默认值为 `0.95`；Models API 文档说明该值是 backend 默认值。 |
|
||||
|
||||
## gemini-2.5-pro
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | Google 公共文档未直接给出 Gemini 2.5 的 API 默认 `temperature` 数字；`models.get` 文档只说明模型元数据会返回 backend 默认值，因此 JSON 不保留为伪官方默认值。参考值可记为 `1.0`，但只作参考。 |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | Prompting strategies 文档明确写明 `topP` 的默认值为 `0.95`。 |
|
||||
|
||||
## gemini-2.5-flash
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | Google 公共文档未直接给出 Gemini 2.5 的 API 默认 `temperature` 数字；`models.get` 文档只说明模型元数据会返回 backend 默认值，因此 JSON 不保留为伪官方默认值。参考值可记为 `1.0`，但只作参考。 |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | Prompting strategies 文档明确写明 `topP` 的默认值为 `0.95`。 |
|
||||
|
||||
## text-embedding-005
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | Vertex AI embeddings 文档仅定义嵌入输入长度、维度等规格，不定义采样默认值；embedding 模型不按聊天采样参数使用。 |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | Vertex AI embeddings 文档仅定义嵌入输入长度、维度等规格，不定义采样默认值；embedding 模型不按聊天采样参数使用。 |
|
||||
@@ -1,15 +0,0 @@
|
||||
# google none 条目处置记录（2026-04-23，第2轮）
|
||||
|
||||
依据：
|
||||
- Google 官方模型文档（Gemini API / Vertex AI）中 `text-embedding-005` 最大输入长度为 `2048` tokens。
|
||||
- https://cloud.google.com/vertex-ai/generative-ai/docs/embeddings/get-text-embeddings
|
||||
|
||||
已执行：
|
||||
1. `text-embedding-005`：新增 `contextWindow: 2048`
|
||||
|
||||
未改项（说明）：
|
||||
- `maxOutputTokens` / `outputPrice` 保持缺省：Embedding 仅输入计费，无生成输出 token 口径。
|
||||
|
||||
## 本轮 google 落库结果
|
||||
|
||||
- JSON 变更：1 模型 / 1 字段
|
||||
@@ -1,13 +0,0 @@
|
||||
# 未确认字段报告 - compute/coding-plans/infini-coding.json
|
||||
|
||||
- provider: `infini`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## deepseek-v3
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `contextWindow`: 已复核 https://docs.infini-ai.com/gen-studio-coding-plan/supported-models.html ，当前 Coding Plan 支持模型页仅列 `deepseek-v3.2` / `deepseek-v3.2-thinking`，并注明模型列表接口本身不返回 metadata；已复核 https://docs.infini-ai.com/shared/gen-studio/coding-tools/cp-use-openclaw.html ，其中 OpenClaw 示例把 `deepseek-v3.2` 写为 `contextWindow: 128000`、`maxTokens: 128000`，但页面同时声明该 JSON 示例“可能与实际值不一致”；官方没有把本地别名 `deepseek-v3` 与 `deepseek-v3.2` 做一一映射，因此不能据此确认本地 `deepseek-v3`
|
||||
- `maxOutputTokens`: 已复核 https://docs.infini-ai.com/gen-studio-coding-plan/supported-models.html 与 https://docs.infini-ai.com/shared/gen-studio/coding-tools/cp-use-openclaw.html ，官方当前只对 `deepseek-v3.2` 的 OpenClaw 示例展示 `maxTokens: 128000`，且示例页明确声明示例值可能与实际值不一致；本地配置使用的 `deepseek-v3` 未出现在官方当前 Coding Plan 模型列表中，无法确认其固定最大输出值
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
@@ -1,33 +0,0 @@
|
||||
# 详细字段取值表 - compute/coding-plans/infini-coding.json
|
||||
|
||||
- provider: `infini`
|
||||
- priceCurrency: `USD`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://docs.infini-ai.com/gen-studio-coding-plan/supported-models.html
|
||||
- https://docs.infini-ai.com/shared/gen-studio/coding-tools/cp-use-openclaw.html
|
||||
- https://docs.infini-ai.com/public/models/deepseek-v3.html
|
||||
- https://api-docs.deepseek.com/quick_start/pricing
|
||||
- https://zenmux.ai/models
|
||||
- https://zenmux.ai/api/v1/models
|
||||
|
||||
## deepseek-v3
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"deepseek-v3"` | `"deepseek-v3"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"DeepSeek V3 (芯穹 Coding)"` | `"DeepSeek V3 (芯穹 Coding)"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `128000` | `128000` | 待确认 | 已复核 https://docs.infini-ai.com/gen-studio-coding-plan/supported-models.html ，当前 Coding Plan 支持模型页仅列 `deepseek-v3.2` / `deepseek-v3.2-thinking`，并注明模型列表接口本身不返回 metadata；已复核 https://docs.infini-ai.com/shared/gen-studio/coding-tools/cp-use-openclaw.html ，其中 OpenClaw 示例把 `deepseek-v3.2` 写为 `contextWindow: 128000`、`maxTokens: 128000`，但页面同时声明该 JSON 示例“可能与实际值不一致”；官方没有把本地别名 `deepseek-v3` 与 `deepseek-v3.2` 做一一映射，因此不能据此确认本地 `deepseek-v3` |
|
||||
| `maxOutputTokens` | `8192` | `8192` | 待确认 | 已复核 https://docs.infini-ai.com/gen-studio-coding-plan/supported-models.html 与 https://docs.infini-ai.com/shared/gen-studio/coding-tools/cp-use-openclaw.html ，官方当前只对 `deepseek-v3.2` 的 OpenClaw 示例展示 `maxTokens: 128000`，且示例页明确声明示例值可能与实际值不一致；本地配置使用的 `deepseek-v3` 未出现在官方当前 Coding Plan 模型列表中，无法确认其固定最大输出值 |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","multilingual"]` | `["chat","reasoning","code","multilingual"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 已复核 https://docs.infini-ai.com/gen-studio-coding-plan/supported-models.html 与 https://docs.infini-ai.com/shared/gen-studio/coding-tools/cp-use-openclaw.html ，官方当前公开的是 `deepseek-v3.2` / `deepseek-v3.2-thinking`，未把本地别名 `deepseek-v3` 与某个官方型号做 1:1 映射；按规则不应冒充官方默认值，当前保持 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 同上；官方当前没有为本地别名 `deepseek-v3` 公布可直接回填的默认 `top_p`，当前保持 `null` |
|
||||
| `extra` | (缺省) | (缺省) | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
@@ -1,104 +0,0 @@
|
||||
# 未确认字段报告 - compute/providers/internal-testing.json
|
||||
|
||||
- provider: `internal-testing`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## MiniMax-M2.7-highspeed
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `maxOutputTokens`: 已查 https://platform.minimax.io/docs/api-reference/text-chat-anthropic 与 https://platform.minimax.io/docs/api-reference/text-chat-openai ，当前兼容接口仅把 `max_tokens` / `max_completion_tokens` 写成接口参数上限 `2048`；另查 https://platform.minimax.io/docs/api-reference/text-post ，废弃 Text Generation 接口只给出 `MiniMax-M2` / `MiniMax-M1` / `MiniMax-Text-01` 的默认值 `10240` / `8192` / `2048`，未公布 `MiniMax-M2.7-highspeed` 的独立模型级最大输出，因此无法用官网确认当前 `8192`
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## glm-5.1
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## glm-5
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## glm-5-turbo
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## glm-4.7
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## kimi-k2.6-code-preview
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## kimi-k2.5
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## MiniMax-M2.5
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `maxOutputTokens`: 已查 https://platform.minimax.io/docs/api-reference/text-chat-anthropic 与 https://platform.minimax.io/docs/api-reference/text-chat-openai ，当前兼容接口仅把 `max_tokens` / `max_completion_tokens` 写成接口参数上限 `2048`；另查 https://platform.minimax.io/docs/api-reference/text-post ，废弃 Text Generation 接口只给出 `MiniMax-M2` / `MiniMax-M1` / `MiniMax-Text-01` 的默认值 `10240` / `8192` / `2048`，未公布 `MiniMax-M2.5` 的独立模型级最大输出，因此无法用官网确认当前 `8192`
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## qwen3.6-plus
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## qwen3.5-plus
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## qwen3.5-35b-a3b
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## qwen3.5-27b
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## qwen3-max-2026-01-23
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## doubao-seed-2-0-code-preview-260215
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
@@ -1,289 +0,0 @@
|
||||
# 详细字段取值表 - compute/providers/internal-testing.json
|
||||
|
||||
- provider: `internal-testing`
|
||||
- priceCurrency: `CNY`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://platform.minimax.io/docs/api-reference/api-overview
|
||||
- https://platform.minimax.io/docs/api-reference/text-chat-anthropic
|
||||
- https://platform.minimax.io/docs/api-reference/text-chat-openai
|
||||
- https://platform.minimax.io/docs/api-reference/text-post
|
||||
- https://platform.minimax.io/docs/guides/text-generation
|
||||
- https://docs.bigmodel.cn/cn/guide/models/text/glm-5.1
|
||||
- https://docs.bigmodel.cn/cn/guide/models/text/glm-5
|
||||
- https://docs.bigmodel.cn/cn/guide/models/text/glm-5-turbo
|
||||
- https://docs.bigmodel.cn/cn/guide/models/text/glm-4.7
|
||||
- https://platform.kimi.com/docs/guide/kimi-k2-6-quickstart
|
||||
- https://platform.kimi.com/docs/guide/kimi-k2-5-quickstart
|
||||
- https://help.aliyun.com/zh/model-studio/model
|
||||
- https://developer.volcengine.com/articles/7615528054736945158
|
||||
- https://zenmux.ai/models
|
||||
- https://zenmux.ai/api/v1/models
|
||||
|
||||
## MiniMax-M2.7-highspeed
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"MiniMax-M2.7-highspeed"` | `"MiniMax-M2.7-highspeed"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"MiniMax-M2.7 高速版"` | `"MiniMax-M2.7 高速版"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `204800` | `204800` | 保持 | MiniMax API Overview https://platform.minimax.io/docs/api-reference/api-overview 与 Text Generation 文档 https://platform.minimax.io/docs/guides/text-generation 均标注 `MiniMax-M2.7-highspeed` context window 为 `204,800` |
|
||||
| `maxOutputTokens` | `8192` | `8192` | 待确认 | 已查 https://platform.minimax.io/docs/api-reference/text-chat-anthropic 与 https://platform.minimax.io/docs/api-reference/text-chat-openai ，当前兼容接口仅把 `max_tokens` / `max_completion_tokens` 写成接口参数上限 `2048`；另查 https://platform.minimax.io/docs/api-reference/text-post ，废弃 Text Generation 接口只给出 `MiniMax-M2` / `MiniMax-M1` / `MiniMax-Text-01` 的默认值 `10240` / `8192` / `2048`，未公布 `MiniMax-M2.7-highspeed` 的独立模型级最大输出；当前值暂保留待确认 |
|
||||
| `inputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code"]` | `["chat","reasoning","code"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | MiniMax OpenAI 兼容文本对话文档 https://platform.minimaxi.com/docs/api-reference/text-chat-openai 明确 `temperature` 默认值为 `1`；本地 `MiniMax-M2.7-highspeed` 与官方模型名一致 |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | MiniMax OpenAI 兼容文本对话文档 https://platform.minimaxi.com/docs/api-reference/text-chat-openai 明确 `top_p` 默认值为 `0.95`；本地 `MiniMax-M2.7-highspeed` 与官方模型名一致 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## glm-5.1
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"glm-5.1"` | `"glm-5.1"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"GLM-5.1"` | `"GLM-5.1"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `200000` | `200000` | 保持 | 智谱官方 GLM-5.1 模型页 https://docs.bigmodel.cn/cn/guide/models/text/glm-5.1 列明上下文窗口为 `200K` |
|
||||
| `maxOutputTokens` | `128000` | `128000` | 保持 | 智谱官方 GLM-5.1 模型页 https://docs.bigmodel.cn/cn/guide/models/text/glm-5.1 列明最大输出 Tokens 为 `128K` |
|
||||
| `inputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","deep_thinking","tool_use","agent"]` | `["chat","reasoning","code","deep_thinking","tool_use","agent"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | 智谱对话补全文档 https://docs.bigmodel.cn/api-reference 明确 `temperature` 默认值为 `1`；本地 `glm-5.1` 与官方模型名一致 |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | 智谱对话补全文档 https://docs.bigmodel.cn/api-reference 明确 `top_p` 默认值为 `0.95`；本地 `glm-5.1` 与官方模型名一致 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## glm-5
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"glm-5"` | `"glm-5"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"GLM-5"` | `"GLM-5"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `200000` | `200000` | 保持 | 智谱官方 GLM-5 模型页 https://docs.bigmodel.cn/cn/guide/models/text/glm-5 列明上下文窗口为 `200K` |
|
||||
| `maxOutputTokens` | `128000` | `128000` | 保持 | 智谱官方 GLM-5 模型页 https://docs.bigmodel.cn/cn/guide/models/text/glm-5 列明最大输出 Tokens 为 `128K` |
|
||||
| `inputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code"]` | `["chat","reasoning","code"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | 智谱对话补全文档 https://docs.bigmodel.cn/api-reference 明确 `temperature` 默认值为 `1`；本地 `glm-5` 与官方模型名一致 |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | 智谱对话补全文档 https://docs.bigmodel.cn/api-reference 明确 `top_p` 默认值为 `0.95`；本地 `glm-5` 与官方模型名一致 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## glm-5-turbo
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"glm-5-turbo"` | `"glm-5-turbo"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"GLM-5-Turbo"` | `"GLM-5-Turbo"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `128000` | `200000` | 建议修改 | 智谱官方 GLM-5-Turbo 模型页 https://docs.bigmodel.cn/cn/guide/models/text/glm-5-turbo 列明上下文窗口为 `200K` |
|
||||
| `maxOutputTokens` | `8192` | `128000` | 建议修改 | 智谱官方 GLM-5-Turbo 模型页 https://docs.bigmodel.cn/cn/guide/models/text/glm-5-turbo 列明最大输出 Tokens 为 `128K` |
|
||||
| `inputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code"]` | `["chat","reasoning","code"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | 智谱对话补全文档 https://docs.bigmodel.cn/api-reference 明确 `temperature` 默认值为 `1`；本地 `glm-5-turbo` 与官方模型名一致 |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | 智谱对话补全文档 https://docs.bigmodel.cn/api-reference 明确 `top_p` 默认值为 `0.95`；本地 `glm-5-turbo` 与官方模型名一致 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## glm-4.7
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"glm-4.7"` | `"glm-4.7"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"GLM-4.7"` | `"GLM-4.7"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `200000` | `200000` | 保持 | 智谱官方 GLM-4.7 模型页 https://docs.bigmodel.cn/cn/guide/models/text/glm-4.7 列明上下文窗口为 `200K` |
|
||||
| `maxOutputTokens` | `128000` | `128000` | 保持 | 智谱官方 GLM-4.7 模型页 https://docs.bigmodel.cn/cn/guide/models/text/glm-4.7 列明最大输出 Tokens 为 `128K` |
|
||||
| `inputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code"]` | `["chat","reasoning","code"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | 智谱对话补全文档 https://docs.bigmodel.cn/api-reference 明确 `temperature` 默认值为 `1`；本地 `glm-4.7` 与官方模型名一致 |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | 智谱对话补全文档 https://docs.bigmodel.cn/api-reference 明确 `top_p` 默认值为 `0.95`；本地 `glm-4.7` 与官方模型名一致 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## kimi-k2.6-code-preview
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"kimi-k2.6-code-preview"` | `"kimi-k2.6-code-preview"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"Kimi K2.6 Code Preview"` | `"Kimi K2.6 Code Preview"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `256000` | `256000` | 保持 | Moonshot 官方 Kimi K2.6 文档 https://platform.kimi.com/docs/guide/kimi-k2-6-quickstart 说明 `kimi-k2.6` 提供 `256K` 上下文窗口；本地别名 `kimi-k2.6-code-preview` 可按同规格理解 |
|
||||
| `maxOutputTokens` | `16384` | `32768` | 建议修改 | Moonshot 官方 Kimi K2.6 文档 https://platform.kimi.com/docs/guide/kimi-k2-6-quickstart “参数变动说明”列明 `max_tokens` 默认值为 `32k`，即 `32768` |
|
||||
| `inputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","tool_use","agent","vision","long_context"]` | `["chat","reasoning","code","tool_use","agent","vision","long_context"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | Moonshot K2.6 文档 https://platform.kimi.com/docs/guide/kimi-k2-6-quickstart 明确 K2.6/K2.5 系列默认开启思考，`temperature` 使用确定值 `1.0`；本地 `kimi-k2.6-code-preview` 按同系列理解 |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | Moonshot K2.6 文档 https://platform.kimi.com/docs/guide/kimi-k2-6-quickstart 明确 K2.6/K2.5 系列 `top_p` 使用确定值 `0.95`；本地 `kimi-k2.6-code-preview` 按同系列理解 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## kimi-k2.5
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"kimi-k2.5"` | `"kimi-k2.5"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"Kimi-2.5"` | `"Kimi-2.5"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `128000` | `256000` | 建议修改 | Moonshot 官方 Kimi K2.5 文档 https://platform.kimi.com/docs/guide/kimi-k2-5-quickstart 标注模型上下文长度为 `256k` |
|
||||
| `maxOutputTokens` | `8192` | `32768` | 建议修改 | Moonshot 官方 Kimi K2.5 文档 https://platform.kimi.com/docs/guide/kimi-k2-5-quickstart “参数变动说明”列明 `max_tokens` 默认值为 `32k`，即 `32768` |
|
||||
| `inputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","tool_use","agent","vision","long_context"]` | `["chat","reasoning","code","tool_use","agent","vision","long_context"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | Moonshot K2.5 文档 https://platform.kimi.com/docs/guide/kimi-k2-5-quickstart 明确 K2.5 系列默认开启思考，`temperature` 使用确定值 `1.0` |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | Moonshot K2.5 文档 https://platform.kimi.com/docs/guide/kimi-k2-5-quickstart 明确 K2.5 系列 `top_p` 使用确定值 `0.95` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## MiniMax-M2.5
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"MiniMax-M2.5"` | `"MiniMax-M2.5"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"MiniMax-M2.5"` | `"MiniMax-M2.5"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `204800` | `204800` | 保持 | MiniMax API Overview https://platform.minimax.io/docs/api-reference/api-overview 与 Text Generation 文档 https://platform.minimax.io/docs/guides/text-generation 均标注 `MiniMax-M2.5` context window 为 `204,800` |
|
||||
| `maxOutputTokens` | `8192` | `8192` | 待确认 | 已查 https://platform.minimax.io/docs/api-reference/text-chat-anthropic 与 https://platform.minimax.io/docs/api-reference/text-chat-openai ，当前兼容接口仅把 `max_tokens` / `max_completion_tokens` 写成接口参数上限 `2048`；另查 https://platform.minimax.io/docs/api-reference/text-post ，废弃 Text Generation 接口只给出 `MiniMax-M2` / `MiniMax-M1` / `MiniMax-Text-01` 的默认值 `10240` / `8192` / `2048`，未公布 `MiniMax-M2.5` 的独立模型级最大输出；当前值暂保留待确认 |
|
||||
| `inputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","tool_use","long_context"]` | `["chat","reasoning","code","tool_use","long_context"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | MiniMax OpenAI 兼容文本对话文档 https://platform.minimaxi.com/docs/api-reference/text-chat-openai 明确 `temperature` 默认值为 `1`；本地 `MiniMax-M2.5` 与官方模型名一致 |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | MiniMax OpenAI 兼容文本对话文档 https://platform.minimaxi.com/docs/api-reference/text-chat-openai 明确 `top_p` 默认值为 `0.95`；本地 `MiniMax-M2.5` 与官方模型名一致 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## qwen3.6-plus
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"qwen3.6-plus"` | `"qwen3.6-plus"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"Qwen3.6 Plus"` | `"Qwen3.6 Plus"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `1000000` | `1000000` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/model 标注 `qwen3.6-plus` 稳定版上下文长度为 `1,000,000` |
|
||||
| `maxOutputTokens` | `65536` | `65536` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/model 标注 `qwen3.6-plus` 稳定版最大输出为 `65,536` |
|
||||
| `inputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","vision","tool_use","agent","deep_thinking"]` | `["chat","reasoning","code","vision","tool_use","agent","deep_thinking"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `0.7` | `0.7` | 保持 | 通义千问 API 参考 https://help.aliyun.com/zh/model-studio/use-qwen-by-calling-api 明确 `qwen-plus` / `Qwen3（非思考模式）` 默认 `temperature=0.7`；本地 `qwen3.6-plus` 按 `qwen-plus` 系列处理 |
|
||||
| `defaultTopP` | `0.8` | `0.8` | 保持 | 通义千问 API 参考 https://help.aliyun.com/zh/model-studio/use-qwen-by-calling-api 明确 `qwen-plus` / `Qwen3（非思考模式）` 默认 `top_p=0.8`；本地 `qwen3.6-plus` 按 `qwen-plus` 系列处理 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## qwen3.5-plus
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"qwen3.5-plus"` | `"qwen3.5-plus"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"Qwen3.5 Plus"` | `"Qwen3.5 Plus"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `128000` | `1000000` | 建议修改 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/model 标注 `qwen3.5-plus` 稳定版上下文长度为 `1,000,000` |
|
||||
| `maxOutputTokens` | `8192` | `65536` | 建议修改 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/model 标注 `qwen3.5-plus` 稳定版最大输出为 `65,536` |
|
||||
| `inputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","tool_use","agent","vision","long_context"]` | `["chat","reasoning","code","tool_use","agent","vision","long_context"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `0.7` | `0.7` | 保持 | 通义千问 API 参考 https://help.aliyun.com/zh/model-studio/use-qwen-by-calling-api 明确 `qwen-plus` / `Qwen3（非思考模式）` 默认 `temperature=0.7`；本地 `qwen3.5-plus` 按 `qwen-plus` 系列处理 |
|
||||
| `defaultTopP` | `0.8` | `0.8` | 保持 | 通义千问 API 参考 https://help.aliyun.com/zh/model-studio/use-qwen-by-calling-api 明确 `qwen-plus` / `Qwen3（非思考模式）` 默认 `top_p=0.8`；本地 `qwen3.5-plus` 按 `qwen-plus` 系列处理 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## qwen3.5-35b-a3b
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"qwen3.5-35b-a3b"` | `"qwen3.5-35b-a3b"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"Qwen3.5 35B-A3B"` | `"Qwen3.5 35B-A3B"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `262144` | `262144` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/model 将 `qwen3.5-35b-a3b` 标注为 `262,144` 上下文 |
|
||||
| `maxOutputTokens` | `65536` | `65536` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/model 将 `qwen3.5-35b-a3b` 标注为最大回复长度 `65,536` |
|
||||
| `inputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","vision","tool_use"]` | `["chat","reasoning","code","vision","tool_use"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `0.7` | `0.7` | 保持 | 通义千问 API 参考 https://help.aliyun.com/zh/model-studio/use-qwen-by-calling-api 明确 `qwen开源系列` 默认 `temperature=0.7`；本地 `qwen3.5-35b-a3b` 按 qwen 开源系列处理 |
|
||||
| `defaultTopP` | `0.8` | `0.8` | 保持 | 通义千问 API 参考 https://help.aliyun.com/zh/model-studio/use-qwen-by-calling-api 明确 `qwen开源系列` 默认 `top_p=0.8`；本地 `qwen3.5-35b-a3b` 按 qwen 开源系列处理 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## qwen3.5-27b
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"qwen3.5-27b"` | `"qwen3.5-27b"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"Qwen3.5 27B"` | `"Qwen3.5 27B"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `262144` | `262144` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/model 将 `qwen3.5-27b` 标注为 `262,144` 上下文 |
|
||||
| `maxOutputTokens` | `65536` | `65536` | 保持 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/model 将 `qwen3.5-27b` 标注为最大回复长度 `65,536` |
|
||||
| `inputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","vision","tool_use"]` | `["chat","reasoning","code","vision","tool_use"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `0.7` | `0.7` | 保持 | 通义千问 API 参考 https://help.aliyun.com/zh/model-studio/use-qwen-by-calling-api 明确 `qwen开源系列` 默认 `temperature=0.7`；本地 `qwen3.5-27b` 按 qwen 开源系列处理 |
|
||||
| `defaultTopP` | `0.8` | `0.8` | 保持 | 通义千问 API 参考 https://help.aliyun.com/zh/model-studio/use-qwen-by-calling-api 明确 `qwen开源系列` 默认 `top_p=0.8`；本地 `qwen3.5-27b` 按 qwen 开源系列处理 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## qwen3-max-2026-01-23
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"qwen3-max-2026-01-23"` | `"qwen3-max-2026-01-23"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"Qwen3 Max"` | `"Qwen3 Max"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `128000` | `262144` | 建议修改 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/model 标注 `qwen3-max-2026-01-23` 对应的 `qwen3-max` 上下文长度为 `262,144` |
|
||||
| `maxOutputTokens` | `8192` | `32768` | 建议修改 | 阿里云模型总表 https://help.aliyun.com/zh/model-studio/model 标注 `qwen3-max-2026-01-23` 思考模式最大输出为 `32,768` |
|
||||
| `inputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","tool_use","agent","vision","long_context"]` | `["chat","reasoning","code","tool_use","agent","vision","long_context"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `0.7` | `0.7` | 保持 | 通义千问 API 参考 https://help.aliyun.com/zh/model-studio/use-qwen-by-calling-api 明确 `qwen-max` 系列默认 `temperature=0.7`；本地 `qwen3-max-2026-01-23` 可按官方 dated `qwen3-max` 同系列理解 |
|
||||
| `defaultTopP` | `0.8` | `0.8` | 保持 | 通义千问 API 参考 https://help.aliyun.com/zh/model-studio/use-qwen-by-calling-api 明确 `qwen-max` 系列默认 `top_p=0.8`；本地 `qwen3-max-2026-01-23` 可按官方 dated `qwen3-max` 同系列理解 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## doubao-seed-2-0-code-preview-260215
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"doubao-seed-2-0-code-preview-260215"` | `"doubao-seed-2-0-code-preview-260215"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"豆包 Seed 2.0 Code Preview"` | `"豆包 Seed 2.0 Code Preview"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `128000` | `256000` | 建议修改 | 火山引擎开发者社区实践文档 https://developer.volcengine.com/articles/7615528054736945158 列明 `doubao-seed-2.0-code` contextWindow 为 `256000`；本地快照别名 `doubao-seed-2-0-code-preview-260215` 可按同规格理解 |
|
||||
| `maxOutputTokens` | `8192` | `128000` | 建议修改 | 火山引擎开发者社区实践文档 https://developer.volcengine.com/articles/7615528054736945158 列明 `doubao-seed-2.0-code` maxTokens 为 `128000`；本地快照别名 `doubao-seed-2-0-code-preview-260215` 可按同规格理解 |
|
||||
| `inputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code"]` | `["chat","reasoning","code"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | 火山引擎 AI 数据湖文本生成文档 https://www.volcengine.com/docs/6492/2165102?lang=zh 明确豆包/DeepSeek 文本生成接口 `temperature` 默认值为 `1`；本地 `doubao-seed-2-0-code-preview-260215` 按官方 `doubao-seed-2.0-code` 快照别名同规格理解 |
|
||||
| `defaultTopP` | `0.7` | `0.7` | 保持 | 火山引擎 AI 数据湖文本生成文档 https://www.volcengine.com/docs/6492/2165102?lang=zh 明确豆包/DeepSeek 文本生成接口 `top_p` 默认值为 `0.7`；本地 `doubao-seed-2-0-code-preview-260215` 按官方 `doubao-seed-2.0-code` 快照别名同规格理解 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
@@ -1,32 +0,0 @@
|
||||
# 未确认字段报告 - compute/providers/kling.json
|
||||
|
||||
- provider: `kling`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## kling-v2-5-turbo
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## kling-v2-5-turbo-pro
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## kling-v2
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## kling-v2-master
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
@@ -1,87 +0,0 @@
|
||||
# 详细字段取值表 - compute/providers/kling.json
|
||||
|
||||
- provider: `kling`
|
||||
- priceCurrency: `CNY`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://app.klingai.com/cn/quickstart/klingai-video-3-model-user-guide
|
||||
- https://zenmux.ai/models
|
||||
- https://zenmux.ai/api/v1/models
|
||||
|
||||
## kling-v2-5-turbo
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"kling-v2-5-turbo"` | `"kling-v2-5-turbo"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"可灵 V2.5 Turbo"` | `"可灵 V2.5 Turbo"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["video_gen"]` | `["video_gen"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `0` | `0` | 保持 | 已查 https://app.klingai.com/cn/quickstart/klingai-video-3-model-user-guide ，可灵视频模型按时长/分辨率生成视频，context window 字段不适用，当前以 `0` 记录 |
|
||||
| `maxOutputTokens` | `0` | `0` | 保持 | 已查 https://app.klingai.com/cn/quickstart/klingai-video-3-model-user-guide ，官网公开了输出时长与分辨率能力，但视频模型不以 token completion 计量，当前以 `0` 记录为不适用 |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["video_generation","chinese_optimized","high_quality","fast"]` | `["video_generation","chinese_optimized","high_quality","fast"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 已复核可灵官方模型使用指南；视频生成模型按时长/分辨率生成任务，不提供文本采样 `temperature`，当前保持 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 同上；视频生成模型不提供文本采样 `top_p`，当前保持 `null` |
|
||||
| `extra` | `{"maxVideoDuration":10,"supportedResolutions":["720p","1080p"],"pricePerGeneration":1.5}` | `{"maxVideoDuration":10,"supportedResolutions":["720p","1080p"],"pricePerGeneration":1.5}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## kling-v2-5-turbo-pro
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"kling-v2-5-turbo-pro"` | `"kling-v2-5-turbo-pro"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"可灵 V2.5 Turbo Pro"` | `"可灵 V2.5 Turbo Pro"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["video_gen"]` | `["video_gen"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `0` | `0` | 保持 | 已查 https://app.klingai.com/cn/quickstart/klingai-video-3-model-user-guide ，可灵视频模型按时长/分辨率生成视频，context window 字段不适用，当前以 `0` 记录 |
|
||||
| `maxOutputTokens` | `0` | `0` | 保持 | 已查 https://app.klingai.com/cn/quickstart/klingai-video-3-model-user-guide ，官网公开了输出时长与分辨率能力，但视频模型不以 token completion 计量，当前以 `0` 记录为不适用 |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["video_generation","chinese_optimized","ultra_quality"]` | `["video_generation","chinese_optimized","ultra_quality"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 已复核可灵官方模型使用指南；视频生成模型按时长/分辨率生成任务，不提供文本采样 `temperature`，当前保持 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 同上；视频生成模型不提供文本采样 `top_p`，当前保持 `null` |
|
||||
| `extra` | `{"maxVideoDuration":10,"supportedResolutions":["1080p","4k"],"pricePerGeneration":2.5}` | `{"maxVideoDuration":10,"supportedResolutions":["1080p","4k"],"pricePerGeneration":2.5}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## kling-v2
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"kling-v2"` | `"kling-v2"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"可灵 V2"` | `"可灵 V2"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["video_gen"]` | `["video_gen"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `0` | `0` | 保持 | 已查 https://app.klingai.com/cn/quickstart/klingai-video-3-model-user-guide ，可灵视频模型按时长/分辨率生成视频，context window 字段不适用，当前以 `0` 记录 |
|
||||
| `maxOutputTokens` | `0` | `0` | 保持 | 已查 https://app.klingai.com/cn/quickstart/klingai-video-3-model-user-guide ，官网公开了输出时长与分辨率能力，但视频模型不以 token completion 计量，当前以 `0` 记录为不适用 |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["video_generation","chinese_optimized","high_quality"]` | `["video_generation","chinese_optimized","high_quality"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 已复核可灵官方模型使用指南；视频生成模型按时长/分辨率生成任务，不提供文本采样 `temperature`，当前保持 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 同上；视频生成模型不提供文本采样 `top_p`，当前保持 `null` |
|
||||
| `extra` | `{"maxVideoDuration":10,"supportedResolutions":["720p","1080p"]}` | `{"maxVideoDuration":10,"supportedResolutions":["720p","1080p"]}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## kling-v2-master
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"kling-v2-master"` | `"kling-v2-master"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"可灵 V2 Master"` | `"可灵 V2 Master"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["video_gen"]` | `["video_gen"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `0` | `0` | 保持 | 已查 https://app.klingai.com/cn/quickstart/klingai-video-3-model-user-guide ，可灵视频模型按时长/分辨率生成视频，context window 字段不适用，当前以 `0` 记录 |
|
||||
| `maxOutputTokens` | `0` | `0` | 保持 | 已查 https://app.klingai.com/cn/quickstart/klingai-video-3-model-user-guide ，官网公开了输出时长与分辨率能力，但视频模型不以 token completion 计量，当前以 `0` 记录为不适用 |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["video_generation","chinese_optimized","ultra_quality"]` | `["video_generation","chinese_optimized","ultra_quality"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 已复核可灵官方模型使用指南；视频生成模型按时长/分辨率生成任务，不提供文本采样 `temperature`，当前保持 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 同上；视频生成模型不提供文本采样 `top_p`，当前保持 `null` |
|
||||
| `extra` | `{"maxVideoDuration":10,"supportedResolutions":["1080p","4k"]}` | `{"maxVideoDuration":10,"supportedResolutions":["1080p","4k"]}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
@@ -1,13 +0,0 @@
|
||||
# 未确认字段报告 - compute/coding-plans/kwai-coding.json
|
||||
|
||||
- provider: `kwai`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## kwai-coder
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `contextWindow`: 已复核产品页 https://www.streamlake.com/product/kat-coder 与官方接入指南 https://www.streamlake.com/document/WANQING/me6ymdjrqv8lp4iq0o9 ，Coding Plan 官方要求使用的模型名是 `kat-coder-pro-v2`，而本地配置使用的是别名 `kwai-coder`；已复核发布公告 https://www.streamlake.com/document/WANQING/mdptas54hptu5uvllco ，官方确认存在 `KAT-Coder-Pro-V2`，但当前公开文档没有上下文窗口字段，也没有说明 `kwai-coder` 与该官方型号的一一映射
|
||||
- `maxOutputTokens`: 已复核官方接入指南 https://www.streamlake.com/document/WANQING/me6ymdjrqv8lp4iq0o9 ，其中 Droid `customModels` 示例为 `kat-coder-pro-v2` 填写了 `maxOutputTokens: 128000`，但该值出现在客户端配置样例，不是正式模型规格页；结合产品页 https://www.streamlake.com/product/kat-coder 与发布公告 https://www.streamlake.com/document/WANQING/mdptas54hptu5uvllco ，官方仍未发布 `kwai-coder` / `kat-coder-pro-v2` 的固定最大输出说明，不能直接据此回填
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
@@ -1,33 +0,0 @@
|
||||
# 详细字段取值表 - compute/coding-plans/kwai-coding.json
|
||||
|
||||
- provider: `kwai`
|
||||
- priceCurrency: `USD`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://www.streamlake.com/product/kat-coder
|
||||
- https://www.streamlake.com/document/WANQING/me6ymdjrqv8lp4iq0o9
|
||||
- https://www.streamlake.com/document/WANQING/mdptas54hptu5uvllco
|
||||
- https://www.streamlake.com/document/WANQING/me6z3u08sjus2mzplbj
|
||||
- https://zenmux.ai/models
|
||||
- https://zenmux.ai/api/v1/models
|
||||
|
||||
## kwai-coder
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"kwai-coder"` | `"kwai-coder"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"KwaiKAT Coder (Coding)"` | `"KwaiKAT Coder (Coding)"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `128000` | `128000` | 待确认 | 已复核产品页 https://www.streamlake.com/product/kat-coder 与官方接入指南 https://www.streamlake.com/document/WANQING/me6ymdjrqv8lp4iq0o9 ，Coding Plan 官方要求使用的模型名是 `kat-coder-pro-v2`，而本地配置使用的是别名 `kwai-coder`；已复核发布公告 https://www.streamlake.com/document/WANQING/mdptas54hptu5uvllco ，官方确认存在 `KAT-Coder-Pro-V2`，但当前公开文档没有上下文窗口字段，也没有说明 `kwai-coder` 与该官方型号的一一映射 |
|
||||
| `maxOutputTokens` | `8192` | `8192` | 待确认 | 已复核官方接入指南 https://www.streamlake.com/document/WANQING/me6ymdjrqv8lp4iq0o9 ，其中 Droid `customModels` 示例为 `kat-coder-pro-v2` 填写了 `maxOutputTokens: 128000`，但该值出现在客户端配置样例，不是正式模型规格页；结合产品页 https://www.streamlake.com/product/kat-coder 与发布公告 https://www.streamlake.com/document/WANQING/mdptas54hptu5uvllco ，官方仍未发布 `kwai-coder` / `kat-coder-pro-v2` 的固定最大输出说明，不能直接据此回填 |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","code"]` | `["chat","code"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | 已复核 StreamLake 官方“文本生成”接口文档，在线推理点对话 API 的 `temperature` 默认值为 `1` |
|
||||
| `defaultTopP` | `1` | `1` | 保持 | 已复核 StreamLake 官方“文本生成”接口文档，在线推理点对话 API 的 `top_p` 默认值为 `1` |
|
||||
| `extra` | (缺省) | (缺省) | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
@@ -1,22 +0,0 @@
|
||||
# 未确认字段报告 - compute/providers/lingyiwanwu.json
|
||||
|
||||
- provider: `lingyiwanwu`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## yi-lightning
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `contextWindow`: 已复核 https://platform.lingyiwanwu.com/billing 与 https://platform.lingyiwanwu.com/playground ，公开可访问页面只展示平台导航、计费入口、Playground 与文档入口，未公开 `yi-lightning` / `yi-vision-v2` 的独立模型卡片或参数表；已复核 https://platform.lingyiwanwu.com/useragreement ，官方明确开放平台是“多模型聚合平台”，会按任务进行智能路由，因此不能从聚合平台入口反推这两个公开别名的固定上下文规格
|
||||
- `maxOutputTokens`: 已复核 https://platform.lingyiwanwu.com/billing 、https://platform.lingyiwanwu.com/playground 与 https://platform.lingyiwanwu.com/useragreement ，当前官方公开页面没有 `yi-lightning` / `yi-vision-v2` 的独立最大输出规格；且用户协议明确平台存在智能路由，不足以从聚合平台公开入口反推固定 `maxOutputTokens`
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## yi-vision-v2
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `contextWindow`: 已复核 https://platform.lingyiwanwu.com/billing 与 https://platform.lingyiwanwu.com/playground ，公开可访问页面只展示平台导航、计费入口、Playground 与文档入口，未公开 `yi-lightning` / `yi-vision-v2` 的独立模型卡片或参数表；已复核 https://platform.lingyiwanwu.com/useragreement ，官方明确开放平台是“多模型聚合平台”，会按任务进行智能路由，因此不能从聚合平台入口反推这两个公开别名的固定上下文规格
|
||||
- `maxOutputTokens`: 已复核 https://platform.lingyiwanwu.com/billing 、https://platform.lingyiwanwu.com/playground 与 https://platform.lingyiwanwu.com/useragreement ，当前官方公开页面没有 `yi-lightning` / `yi-vision-v2` 的独立最大输出规格；且用户协议明确平台存在智能路由，不足以从聚合平台公开入口反推固定 `maxOutputTokens`
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
@@ -1,52 +0,0 @@
|
||||
# 详细字段取值表 - compute/providers/lingyiwanwu.json
|
||||
|
||||
- provider: `lingyiwanwu`
|
||||
- priceCurrency: `CNY`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://platform.lingyiwanwu.com/billing
|
||||
- https://platform.lingyiwanwu.com/playground
|
||||
- https://platform.lingyiwanwu.com/docs/api-reference
|
||||
- https://platform.lingyiwanwu.com/useragreement
|
||||
- https://zenmux.ai/models
|
||||
- https://zenmux.ai/api/v1/models
|
||||
|
||||
## yi-lightning
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"yi-lightning"` | `"yi-lightning"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"Yi Lightning"` | `"Yi Lightning"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `16000` | `16000` | 待确认 | 已复核 https://platform.lingyiwanwu.com/billing 与 https://platform.lingyiwanwu.com/playground ，公开可访问页面只展示平台导航、计费入口、Playground 与文档入口，未公开 `yi-lightning` / `yi-vision-v2` 的独立模型卡片或参数表；已复核 https://platform.lingyiwanwu.com/useragreement ，官方明确开放平台是“多模型聚合平台”，会按任务进行智能路由，因此不能从聚合平台入口反推这两个公开别名的固定上下文规格 |
|
||||
| `maxOutputTokens` | `4096` | `4096` | 待确认 | 已复核 https://platform.lingyiwanwu.com/billing 、https://platform.lingyiwanwu.com/playground 与 https://platform.lingyiwanwu.com/useragreement ，当前官方公开页面没有 `yi-lightning` / `yi-vision-v2` 的独立最大输出规格；且用户协议明确平台存在智能路由，不足以从聚合平台公开入口反推固定 `maxOutputTokens` |
|
||||
| `inputPrice` | `0.99` | `0.99` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `0.99` | `0.99` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","fast","smart_routing"]` | `["chat","reasoning","code","fast","smart_routing"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 已复核官方 `playground`、`docs/api-reference` 与用户协议；公开页面未给 `yi-lightning` 的默认采样值，且平台官方明确为智能路由聚合平台，不应把本地参考值冒充官方默认，当前保持 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 同上；公开页面未给 `yi-lightning` 的默认 `top_p`，当前保持 `null` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## yi-vision-v2
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"yi-vision-v2"` | `"yi-vision-v2"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"Yi Vision V2"` | `"Yi Vision V2"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["vision"]` | `["vision"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `16000` | `16000` | 待确认 | 已复核 https://platform.lingyiwanwu.com/billing 与 https://platform.lingyiwanwu.com/playground ，公开可访问页面只展示平台导航、计费入口、Playground 与文档入口，未公开 `yi-lightning` / `yi-vision-v2` 的独立模型卡片或参数表；已复核 https://platform.lingyiwanwu.com/useragreement ，官方明确开放平台是“多模型聚合平台”，会按任务进行智能路由，因此不能从聚合平台入口反推这两个公开别名的固定上下文规格 |
|
||||
| `maxOutputTokens` | `4096` | `4096` | 待确认 | 已复核 https://platform.lingyiwanwu.com/billing 、https://platform.lingyiwanwu.com/playground 与 https://platform.lingyiwanwu.com/useragreement ，当前官方公开页面没有 `yi-lightning` / `yi-vision-v2` 的独立最大输出规格；且用户协议明确平台存在智能路由，不足以从聚合平台公开入口反推固定 `maxOutputTokens` |
|
||||
| `inputPrice` | `6` | `6` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `6` | `6` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","vision","image_understanding","ocr","chart_analysis","smart_routing"]` | `["chat","vision","image_understanding","ocr","chart_analysis","smart_routing"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 已复核官方 `playground`、`docs/api-reference` 与用户协议；公开页面未给 `yi-vision-v2` 的默认采样值，且平台官方明确为智能路由聚合平台，不应把本地参考值冒充官方默认，当前保持 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 同上；公开页面未给 `yi-vision-v2` 的默认 `top_p`，当前保持 `null` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
@@ -1,11 +0,0 @@
|
||||
# 未确认字段报告 - compute/providers/local-whisper.json
|
||||
|
||||
- provider: `local-whisper`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## whisper-large-v3
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
@@ -1,31 +0,0 @@
|
||||
# 详细字段取值表 - compute/providers/local-whisper.json
|
||||
|
||||
- provider: `local-whisper`
|
||||
- priceCurrency: `USD`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://huggingface.co/openai/whisper-large-v3
|
||||
- https://github.com/openai/whisper
|
||||
- https://zenmux.ai/models
|
||||
- https://zenmux.ai/api/v1/models
|
||||
|
||||
## whisper-large-v3
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"whisper-large-v3"` | `"whisper-large-v3"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"Whisper Large V3"` | `"Whisper Large V3"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["asr"]` | `["asr"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `0` | `0` | 保持 | 已查 https://huggingface.co/openai/whisper-large-v3 与 https://github.com/openai/whisper ，`whisper-large-v3` 为语音转文本模型，官方未定义与聊天模型同口径的 context window，当前以 `0` 记录为不适用 |
|
||||
| `maxOutputTokens` | `0` | `0` | 保持 | 已查 https://huggingface.co/openai/whisper-large-v3 与 https://github.com/openai/whisper ，官方未提供 transcription 模型的 max output tokens 规格，当前以 `0` 记录为不适用 |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["asr","multilingual"]` | `["asr","multilingual"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 已复核 Whisper 官方仓库与 `whisper-large-v3` 模型卡；Whisper 是 ASR/翻译模型，官方公开的是转录解码策略而非本地 OpenAI 兼容服务的固定模型级默认采样值，当前保持 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 已复核 Whisper 官方仓库与模型卡，未提供 ASR 模型的 `top_p` 采样默认值，当前保持 `null` |
|
||||
| `extra` | `{"maxAudioLength":7200,"supportedInputFormats":["wav","mp3","flac","ogg","webm"],"streamingSupported":true}` | `{"maxAudioLength":7200,"supportedInputFormats":["wav","mp3","flac","ogg","webm"],"streamingSupported":true}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
@@ -1,11 +0,0 @@
|
||||
# 未确认字段报告 - compute/coding-plans/minimax-coding.json
|
||||
|
||||
- provider: `minimax`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## MiniMax-M2.5
|
||||
|
||||
- `modelName`: ZenMux匹配(normalized): minimax/minimax-m2.5
|
||||
- `maxOutputTokens`: 已查 https://platform.minimax.io/docs/api-reference/text-chat-anthropic 与 https://platform.minimax.io/docs/api-reference/text-chat-openai ，当前兼容接口仅把 `max_tokens` / `max_completion_tokens` 写成接口参数上限 `2048`；另查 https://platform.minimax.io/docs/api-reference/text-post ，废弃 Text Generation 接口只给出 `MiniMax-M2` / `MiniMax-M1` / `MiniMax-Text-01` 的默认值 `10240` / `8192` / `2048`，未公布 `MiniMax-M2.5` 的独立模型级最大输出，因此无法用官网确认当前 `32768`
|
||||
- `capabilities`: ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
@@ -1,54 +0,0 @@
|
||||
# 详细字段取值表 - compute/coding-plans/minimax-coding.json
|
||||
|
||||
- provider: `minimax`
|
||||
- priceCurrency: `USD`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://platform.minimax.io/docs/api-reference/api-overview
|
||||
- https://platform.minimax.io/docs/api-reference/text-chat-anthropic
|
||||
- https://platform.minimax.io/docs/api-reference/text-chat-openai
|
||||
- https://platform.minimax.io/docs/api-reference/text-post
|
||||
- https://platform.minimax.io/docs/guides/text-generation
|
||||
- https://platform.minimax.io/docs/guides/pricing-paygo
|
||||
- https://zenmux.ai/models
|
||||
- https://zenmux.ai/api/v1/models
|
||||
|
||||
## MiniMax-M2.5
|
||||
|
||||
- ZenMux匹配级别: `normalized`
|
||||
- ZenMux命中: `minimax/minimax-m2.5`
|
||||
- ZenMux候选: `minimax/minimax-m2.5`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"MiniMax-M2.5"` | `"minimax-m2.5"` | 待确认 | ZenMux匹配(normalized): minimax/minimax-m2.5 |
|
||||
| `displayName` | `"MiniMax-M2.5 (Coding)"` | `"MiniMax-M2.5 (Coding)"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `204800` | `204800` | 保持 | MiniMax API Overview https://platform.minimax.io/docs/api-reference/api-overview 标注 `MiniMax-M2.5` context window 为 `204,800` |
|
||||
| `maxOutputTokens` | `32768` | `32768` | 待确认 | 已查 https://platform.minimax.io/docs/api-reference/text-chat-anthropic 与 https://platform.minimax.io/docs/api-reference/text-chat-openai ，当前兼容接口仅把 `max_tokens` / `max_completion_tokens` 写成接口参数上限 `2048`；另查 https://platform.minimax.io/docs/api-reference/text-post ，废弃 Text Generation 接口只给出 `MiniMax-M2` / `MiniMax-M1` / `MiniMax-Text-01` 的默认值 `10240` / `8192` / `2048`，未公布 `MiniMax-M2.5` 的独立模型级最大输出，因此无法用官网确认当前 `32768` |
|
||||
| `inputPrice` | `0.3` | `0.3` | 保持 | ZenMux(minimax/minimax-m2.5) prompt=0.3 USD/MTokens |
|
||||
| `outputPrice` | `1.2` | `1.2` | 保持 | ZenMux(minimax/minimax-m2.5) completion=1.2 USD/MTokens |
|
||||
| `capabilities` | `["chat","reasoning","code","long_context"]` | `["chat","reasoning","code","long_context"]` | 待确认 | ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | 已复核 MiniMax 官方 OpenAI / Anthropic 兼容接口文档，文本模型默认 `temperature=1.0` |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | 已复核 MiniMax 官方 OpenAI / Anthropic 兼容接口文档，文本模型默认 `top_p=0.95` |
|
||||
| `extra` | (缺省) | (缺省) | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## MiniMax-M2.7
|
||||
|
||||
- 本次补充 `defaultTemperature` / `defaultTopP` 复核结论
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | 已复核 MiniMax 官方 OpenAI / Anthropic 兼容接口文档，文本模型默认 `temperature=1.0` |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | 已复核 MiniMax 官方 OpenAI / Anthropic 兼容接口文档，文本模型默认 `top_p=0.95` |
|
||||
|
||||
## MiniMax-M2.7-highspeed
|
||||
|
||||
- 本次补充 `defaultTemperature` / `defaultTopP` 复核结论
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | 已复核 MiniMax 官方 OpenAI / Anthropic 兼容接口文档，文本模型默认 `temperature=1.0` |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | 已复核 MiniMax 官方 OpenAI / Anthropic 兼容接口文档，文本模型默认 `top_p=0.95` |
|
||||
@@ -1,66 +0,0 @@
|
||||
# 未确认字段报告 - compute/providers/minimax.json
|
||||
|
||||
- provider: `minimax`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## MiniMax-M2.7
|
||||
|
||||
- `modelName`: ZenMux匹配(normalized): minimax/minimax-m2.7
|
||||
- `maxOutputTokens`: 已查 https://platform.minimax.io/docs/api-reference/text-chat-anthropic 与 https://platform.minimax.io/docs/api-reference/text-chat-openai ，当前兼容接口仅把 `max_tokens` / `max_completion_tokens` 写成接口参数上限 `2048`；另查 https://platform.minimax.io/docs/api-reference/text-post ，废弃 Text Generation 接口只给出 `MiniMax-M2` / `MiniMax-M1` / `MiniMax-Text-01` 的默认值 `10240` / `8192` / `2048`，未公布 `MiniMax-M2.7` 的独立模型级最大输出，因此无法用官网确认当前 `131072`
|
||||
- `inputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `outputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `capabilities`: ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## MiniMax-M2.7-highspeed
|
||||
|
||||
- `modelName`: ZenMux匹配(normalized): minimax/minimax-m2.7-highspeed
|
||||
- `maxOutputTokens`: 已查 https://platform.minimax.io/docs/api-reference/text-chat-anthropic 与 https://platform.minimax.io/docs/api-reference/text-chat-openai ，当前兼容接口仅把 `max_tokens` / `max_completion_tokens` 写成接口参数上限 `2048`；另查 https://platform.minimax.io/docs/api-reference/text-post ，废弃 Text Generation 接口只给出 `MiniMax-M2` / `MiniMax-M1` / `MiniMax-Text-01` 的默认值 `10240` / `8192` / `2048`，未公布 `MiniMax-M2.7-highspeed` 的独立模型级最大输出，因此无法用官网确认当前 `131072`
|
||||
- `inputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `outputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `capabilities`: ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## MiniMax-M2.5
|
||||
|
||||
- `modelName`: ZenMux匹配(normalized): minimax/minimax-m2.5
|
||||
- `maxOutputTokens`: 已查 https://platform.minimax.io/docs/api-reference/text-chat-anthropic 与 https://platform.minimax.io/docs/api-reference/text-chat-openai ，当前兼容接口仅把 `max_tokens` / `max_completion_tokens` 写成接口参数上限 `2048`；另查 https://platform.minimax.io/docs/api-reference/text-post ，废弃 Text Generation 接口只给出 `MiniMax-M2` / `MiniMax-M1` / `MiniMax-Text-01` 的默认值 `10240` / `8192` / `2048`，未公布 `MiniMax-M2.5` 的独立模型级最大输出，因此无法用官网确认当前 `131072`
|
||||
- `inputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `outputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `capabilities`: ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## MiniMax-M2.5-highspeed
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `maxOutputTokens`: 已查 https://platform.minimax.io/docs/api-reference/text-chat-anthropic 与 https://platform.minimax.io/docs/api-reference/text-chat-openai ，当前兼容接口仅把 `max_tokens` / `max_completion_tokens` 写成接口参数上限 `2048`；另查 https://platform.minimax.io/docs/api-reference/text-post ，废弃 Text Generation 接口只给出 `MiniMax-M2` / `MiniMax-M1` / `MiniMax-Text-01` 的默认值 `10240` / `8192` / `2048`，未公布 `MiniMax-M2.5-highspeed` 的独立模型级最大输出，因此无法用官网确认当前 `131072`
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## MiniMax-M2.1
|
||||
|
||||
- `modelName`: ZenMux匹配(normalized): minimax/minimax-m2.1
|
||||
- `maxOutputTokens`: 已查 https://platform.minimax.io/docs/api-reference/text-chat-anthropic 与 https://platform.minimax.io/docs/api-reference/text-chat-openai ，当前兼容接口仅把 `max_tokens` / `max_completion_tokens` 写成接口参数上限 `2048`；另查 https://platform.minimax.io/docs/api-reference/text-post ，废弃 Text Generation 接口只给出 `MiniMax-M2` / `MiniMax-M1` / `MiniMax-Text-01` 的默认值 `10240` / `8192` / `2048`，未公布 `MiniMax-M2.1` 的独立模型级最大输出，因此无法用官网确认当前 `131072`
|
||||
- `inputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `outputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `capabilities`: ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## MiniMax-M2.1-highspeed
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `maxOutputTokens`: 已查 https://platform.minimax.io/docs/api-reference/text-chat-anthropic 与 https://platform.minimax.io/docs/api-reference/text-chat-openai ，当前兼容接口仅把 `max_tokens` / `max_completion_tokens` 写成接口参数上限 `2048`；另查 https://platform.minimax.io/docs/api-reference/text-post ，废弃 Text Generation 接口只给出 `MiniMax-M2` / `MiniMax-M1` / `MiniMax-Text-01` 的默认值 `10240` / `8192` / `2048`，未公布 `MiniMax-M2.1-highspeed` 的独立模型级最大输出，因此无法用官网确认当前 `131072`
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## MiniMax-Text-01
|
||||
|
||||
- `modelName`: ZenMux匹配(similar): minimax/minimax-m2
|
||||
- `contextWindow`: 已查 https://platform.minimax.io/docs/guides/text-vllm-deployment 与 https://huggingface.co/MiniMaxAI/MiniMax-Text-01 ，官方仅给开源/本地部署口径：vLLM 部署按硬件可支持 `2M` / `5M` context，官方模型卡写明训练上下文 `1M`、推理最高可到 `4M`；MiniMax 托管 API 文档未公布固定 hosted context window，因此无法用官网确认当前 `1000000`
|
||||
- `maxOutputTokens`: 已查 https://platform.minimax.io/docs/api-reference/text-post ，官方仅对 `MiniMax-Text-01` 给出废弃 Text Generation 接口的默认 `max_completion_tokens=2048`，未公布 `MiniMax-Text-01` 在托管 API 下的独立模型级最大输出；开源模型卡 https://huggingface.co/MiniMaxAI/MiniMax-Text-01 也未给固定 `max_new_tokens` 上限，因此无法用官网确认当前 `131072`
|
||||
- `inputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `outputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `capabilities`: ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
@@ -1,157 +0,0 @@
|
||||
# 详细字段取值表 - compute/providers/minimax.json
|
||||
|
||||
- provider: `minimax`
|
||||
- priceCurrency: `CNY`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://platform.minimax.io/docs/api-reference/api-overview
|
||||
- https://platform.minimax.io/docs/api-reference/text-chat-anthropic
|
||||
- https://platform.minimax.io/docs/api-reference/text-chat-openai
|
||||
- https://platform.minimax.io/docs/api-reference/text-post
|
||||
- https://platform.minimax.io/docs/guides/text-generation
|
||||
- https://platform.minimax.io/docs/guides/models-intro
|
||||
- https://platform.minimax.io/docs/guides/pricing-paygo
|
||||
- https://platform.minimax.io/docs/guides/text-vllm-deployment
|
||||
- https://huggingface.co/MiniMaxAI/MiniMax-Text-01
|
||||
- https://zenmux.ai/models
|
||||
- https://zenmux.ai/api/v1/models
|
||||
|
||||
## MiniMax-M2.7
|
||||
|
||||
- ZenMux匹配级别: `normalized`
|
||||
- ZenMux命中: `minimax/minimax-m2.7`
|
||||
- ZenMux候选: `minimax/minimax-m2.7`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"MiniMax-M2.7"` | `"minimax-m2.7"` | 待确认 | ZenMux匹配(normalized): minimax/minimax-m2.7 |
|
||||
| `displayName` | `"MiniMax M2.7"` | `"MiniMax M2.7"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat","reasoning"]` | `["chat","reasoning"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `204800` | `204800` | 保持 | MiniMax API Overview https://platform.minimax.io/docs/api-reference/api-overview 与 Text Generation 文档 https://platform.minimax.io/docs/guides/text-generation 均标注 `MiniMax-M2.7` context window 为 `204,800` |
|
||||
| `maxOutputTokens` | `131072` | `131072` | 待确认 | 已查 https://platform.minimax.io/docs/api-reference/text-chat-anthropic 与 https://platform.minimax.io/docs/api-reference/text-chat-openai ，当前兼容接口仅把 `max_tokens` / `max_completion_tokens` 写成接口参数上限 `2048`；另查 https://platform.minimax.io/docs/api-reference/text-post ，废弃 Text Generation 接口只给出 `MiniMax-M2` / `MiniMax-M1` / `MiniMax-Text-01` 的默认值 `10240` / `8192` / `2048`，未公布 `MiniMax-M2.7` 的独立模型级最大输出，因此无法用官网确认当前 `131072` |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","tool_use"]` | `["chat","reasoning","code","tool_use"]` | 待确认 | ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | MiniMax OpenAI 兼容文本对话文档 https://platform.minimaxi.com/docs/api-reference/text-chat-openai 明确 `temperature` 默认值为 `1` |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | MiniMax OpenAI 兼容文本对话文档 https://platform.minimaxi.com/docs/api-reference/text-chat-openai 明确 `top_p` 默认值为 `0.95` |
|
||||
| `extra` | `{"cacheReadPrice":0.42,"cacheWritePrice":2.625,"outputSpeedTps":60}` | `{"cacheReadPrice":0.42,"cacheWritePrice":2.625,"outputSpeedTps":60}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## MiniMax-M2.7-highspeed
|
||||
|
||||
- ZenMux匹配级别: `normalized`
|
||||
- ZenMux命中: `minimax/minimax-m2.7-highspeed`
|
||||
- ZenMux候选: `minimax/minimax-m2.7-highspeed`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"MiniMax-M2.7-highspeed"` | `"minimax-m2.7-highspeed"` | 待确认 | ZenMux匹配(normalized): minimax/minimax-m2.7-highspeed |
|
||||
| `displayName` | `"MiniMax M2.7 高速版"` | `"MiniMax M2.7 高速版"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["fast"]` | `["fast"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `204800` | `204800` | 保持 | MiniMax API Overview https://platform.minimax.io/docs/api-reference/api-overview 标注 `MiniMax-M2.7-highspeed` context window 为 `204,800` |
|
||||
| `maxOutputTokens` | `131072` | `131072` | 待确认 | 已查 https://platform.minimax.io/docs/api-reference/text-chat-anthropic 与 https://platform.minimax.io/docs/api-reference/text-chat-openai ，当前兼容接口仅把 `max_tokens` / `max_completion_tokens` 写成接口参数上限 `2048`；另查 https://platform.minimax.io/docs/api-reference/text-post ，废弃 Text Generation 接口只给出 `MiniMax-M2` / `MiniMax-M1` / `MiniMax-Text-01` 的默认值 `10240` / `8192` / `2048`，未公布 `MiniMax-M2.7-highspeed` 的独立模型级最大输出，因此无法用官网确认当前 `131072` |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","tool_use","fast"]` | `["chat","reasoning","code","tool_use","fast"]` | 待确认 | ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | MiniMax OpenAI 兼容文本对话文档 https://platform.minimaxi.com/docs/api-reference/text-chat-openai 明确 `temperature` 默认值为 `1` |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | MiniMax OpenAI 兼容文本对话文档 https://platform.minimaxi.com/docs/api-reference/text-chat-openai 明确 `top_p` 默认值为 `0.95` |
|
||||
| `extra` | `{"cacheReadPrice":0.42,"cacheWritePrice":2.625,"outputSpeedTps":100}` | `{"cacheReadPrice":0.42,"cacheWritePrice":2.625,"outputSpeedTps":100}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## MiniMax-M2.5
|
||||
|
||||
- ZenMux匹配级别: `normalized`
|
||||
- ZenMux命中: `minimax/minimax-m2.5`
|
||||
- ZenMux候选: `minimax/minimax-m2.5`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"MiniMax-M2.5"` | `"minimax-m2.5"` | 待确认 | ZenMux匹配(normalized): minimax/minimax-m2.5 |
|
||||
| `displayName` | `"MiniMax M2.5"` | `"MiniMax M2.5"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat","reasoning"]` | `["chat","reasoning"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `204800` | `204800` | 保持 | MiniMax API Overview https://platform.minimax.io/docs/api-reference/api-overview 标注 `MiniMax-M2.5` context window 为 `204,800` |
|
||||
| `maxOutputTokens` | `131072` | `131072` | 待确认 | 已查 https://platform.minimax.io/docs/api-reference/text-chat-anthropic 与 https://platform.minimax.io/docs/api-reference/text-chat-openai ，当前兼容接口仅把 `max_tokens` / `max_completion_tokens` 写成接口参数上限 `2048`；另查 https://platform.minimax.io/docs/api-reference/text-post ，废弃 Text Generation 接口只给出 `MiniMax-M2` / `MiniMax-M1` / `MiniMax-Text-01` 的默认值 `10240` / `8192` / `2048`，未公布 `MiniMax-M2.5` 的独立模型级最大输出，因此无法用官网确认当前 `131072` |
|
||||
| `inputPrice` | `2.1` | `2.1` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `outputPrice` | `8.4` | `8.4` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","tool_use","long_context"]` | `["chat","reasoning","code","tool_use","long_context"]` | 待确认 | ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | MiniMax OpenAI 兼容文本对话文档 https://platform.minimaxi.com/docs/api-reference/text-chat-openai 明确 `temperature` 默认值为 `1` |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | MiniMax OpenAI 兼容文本对话文档 https://platform.minimaxi.com/docs/api-reference/text-chat-openai 明确 `top_p` 默认值为 `0.95` |
|
||||
| `extra` | `{"cacheReadPrice":0.21,"cacheWritePrice":2.625,"outputSpeedTps":60}` | `{"cacheReadPrice":0.21,"cacheWritePrice":2.625,"outputSpeedTps":60}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## MiniMax-M2.5-highspeed
|
||||
|
||||
- ZenMux匹配级别: `ambiguous`
|
||||
- ZenMux候选: `minimax/minimax-m2.5`、`minimax/minimax-m2.7-highspeed`、`minimax/minimax-m2.5-lightning`、`minimax/minimax-m2`、`minimax/minimax-m2.7`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"MiniMax-M2.5-highspeed"` | `"MiniMax-M2.5-highspeed"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"MiniMax M2.5 高速版"` | `"MiniMax M2.5 高速版"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["fast"]` | `["fast"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `204800` | `204800` | 保持 | MiniMax API Overview https://platform.minimax.io/docs/api-reference/api-overview 标注 `MiniMax-M2.5-highspeed` context window 为 `204,800` |
|
||||
| `maxOutputTokens` | `131072` | `131072` | 待确认 | 已查 https://platform.minimax.io/docs/api-reference/text-chat-anthropic 与 https://platform.minimax.io/docs/api-reference/text-chat-openai ，当前兼容接口仅把 `max_tokens` / `max_completion_tokens` 写成接口参数上限 `2048`；另查 https://platform.minimax.io/docs/api-reference/text-post ，废弃 Text Generation 接口只给出 `MiniMax-M2` / `MiniMax-M1` / `MiniMax-Text-01` 的默认值 `10240` / `8192` / `2048`，未公布 `MiniMax-M2.5-highspeed` 的独立模型级最大输出，因此无法用官网确认当前 `131072` |
|
||||
| `inputPrice` | `2.1` | `2.1` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `16.8` | `16.8` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","tool_use","fast"]` | `["chat","reasoning","code","tool_use","fast"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | MiniMax OpenAI 兼容文本对话文档 https://platform.minimaxi.com/docs/api-reference/text-chat-openai 明确 `temperature` 默认值为 `1` |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | MiniMax OpenAI 兼容文本对话文档 https://platform.minimaxi.com/docs/api-reference/text-chat-openai 明确 `top_p` 默认值为 `0.95` |
|
||||
| `extra` | `{"cacheReadPrice":0.21,"cacheWritePrice":2.625,"outputSpeedTps":100}` | `{"cacheReadPrice":0.21,"cacheWritePrice":2.625,"outputSpeedTps":100}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## MiniMax-M2.1
|
||||
|
||||
- ZenMux匹配级别: `normalized`
|
||||
- ZenMux命中: `minimax/minimax-m2.1`
|
||||
- ZenMux候选: `minimax/minimax-m2.1`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"MiniMax-M2.1"` | `"minimax-m2.1"` | 待确认 | ZenMux匹配(normalized): minimax/minimax-m2.1 |
|
||||
| `displayName` | `"MiniMax M2.1"` | `"MiniMax M2.1"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `204800` | `204800` | 保持 | MiniMax API Overview https://platform.minimax.io/docs/api-reference/api-overview 标注 `MiniMax-M2.1` context window 为 `204,800` |
|
||||
| `maxOutputTokens` | `131072` | `131072` | 待确认 | 已查 https://platform.minimax.io/docs/api-reference/text-chat-anthropic 与 https://platform.minimax.io/docs/api-reference/text-chat-openai ，当前兼容接口仅把 `max_tokens` / `max_completion_tokens` 写成接口参数上限 `2048`；另查 https://platform.minimax.io/docs/api-reference/text-post ，废弃 Text Generation 接口只给出 `MiniMax-M2` / `MiniMax-M1` / `MiniMax-Text-01` 的默认值 `10240` / `8192` / `2048`，未公布 `MiniMax-M2.1` 的独立模型级最大输出，因此无法用官网确认当前 `131072` |
|
||||
| `inputPrice` | `2.1` | `2.1` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `outputPrice` | `8.4` | `8.4` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","code","tool_use","reasoning"]` | `["chat","code","tool_use","reasoning"]` | 待确认 | ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | MiniMax OpenAI 兼容文本对话文档 https://platform.minimaxi.com/docs/api-reference/text-chat-openai 明确 `temperature` 默认值为 `1` |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | MiniMax OpenAI 兼容文本对话文档 https://platform.minimaxi.com/docs/api-reference/text-chat-openai 明确 `top_p` 默认值为 `0.95` |
|
||||
| `extra` | `{"cacheReadPrice":0.21,"cacheWritePrice":2.625,"outputSpeedTps":60}` | `{"cacheReadPrice":0.21,"cacheWritePrice":2.625,"outputSpeedTps":60}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## MiniMax-M2.1-highspeed
|
||||
|
||||
- ZenMux匹配级别: `ambiguous`
|
||||
- ZenMux候选: `minimax/minimax-m2.1`、`minimax/minimax-m2.7-highspeed`、`minimax/minimax-m2`、`minimax/minimax-m2.7`、`minimax/minimax-m2.5`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"MiniMax-M2.1-highspeed"` | `"MiniMax-M2.1-highspeed"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"MiniMax M2.1 高速版"` | `"MiniMax M2.1 高速版"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["fast"]` | `["fast"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `204800` | `204800` | 保持 | MiniMax API Overview https://platform.minimax.io/docs/api-reference/api-overview 标注 `MiniMax-M2.1-highspeed` context window 为 `204,800` |
|
||||
| `maxOutputTokens` | `131072` | `131072` | 待确认 | 已查 https://platform.minimax.io/docs/api-reference/text-chat-anthropic 与 https://platform.minimax.io/docs/api-reference/text-chat-openai ，当前兼容接口仅把 `max_tokens` / `max_completion_tokens` 写成接口参数上限 `2048`；另查 https://platform.minimax.io/docs/api-reference/text-post ，废弃 Text Generation 接口只给出 `MiniMax-M2` / `MiniMax-M1` / `MiniMax-Text-01` 的默认值 `10240` / `8192` / `2048`，未公布 `MiniMax-M2.1-highspeed` 的独立模型级最大输出，因此无法用官网确认当前 `131072` |
|
||||
| `inputPrice` | `2.1` | `2.1` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `16.8` | `16.8` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","tool_use","fast"]` | `["chat","reasoning","code","tool_use","fast"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | MiniMax OpenAI 兼容文本对话文档 https://platform.minimaxi.com/docs/api-reference/text-chat-openai 明确 `temperature` 默认值为 `1` |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | MiniMax OpenAI 兼容文本对话文档 https://platform.minimaxi.com/docs/api-reference/text-chat-openai 明确 `top_p` 默认值为 `0.95` |
|
||||
| `extra` | `{"cacheReadPrice":0.21,"cacheWritePrice":2.625,"outputSpeedTps":100}` | `{"cacheReadPrice":0.21,"cacheWritePrice":2.625,"outputSpeedTps":100}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## MiniMax-Text-01
|
||||
|
||||
- ZenMux匹配级别: `similar`
|
||||
- ZenMux命中: `minimax/minimax-m2`
|
||||
- ZenMux候选: `minimax/minimax-m2`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"MiniMax-Text-01"` | `"minimax-m2"` | 待确认 | ZenMux匹配(similar): minimax/minimax-m2 |
|
||||
| `displayName` | `"MiniMax Text 01"` | `"MiniMax Text 01"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `1000000` | `1000000` | 待确认 | 已查 https://platform.minimax.io/docs/guides/text-vllm-deployment 与 https://huggingface.co/MiniMaxAI/MiniMax-Text-01 ，官方仅给开源/本地部署口径：vLLM 部署按硬件可支持 `2M` / `5M` context，官方模型卡写明训练上下文 `1M`、推理最高可到 `4M`；MiniMax 托管 API 文档未公布固定 hosted context window，因此无法用官网确认当前 `1000000` |
|
||||
| `maxOutputTokens` | `131072` | `131072` | 待确认 | 已查 https://platform.minimax.io/docs/api-reference/text-post ，官方仅对 `MiniMax-Text-01` 给出废弃 Text Generation 接口的默认 `max_completion_tokens=2048`，未公布 `MiniMax-Text-01` 在托管 API 下的独立模型级最大输出；开源模型卡 https://huggingface.co/MiniMaxAI/MiniMax-Text-01 也未给固定 `max_new_tokens` 上限，因此无法用官网确认当前 `131072` |
|
||||
| `inputPrice` | `1.4` | `1.4` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `outputPrice` | `7.7` | `7.7` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","long_context"]` | `["chat","reasoning","code","long_context"]` | 待确认 | ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核 |
|
||||
| `defaultTemperature` | `0.1` | `0.1` | 保持 | MiniMax 文本合成文档 https://platform.minimaxi.com/docs/api-reference/text-post 明确 `MiniMax-Text-01` 的 `temperature` 默认值为 `0.1` |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | MiniMax 文本合成文档 https://platform.minimaxi.com/docs/api-reference/text-post 明确各模型 `top_p` 默认值为 `0.95`，其中覆盖 `MiniMax-Text-01` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
@@ -1,25 +0,0 @@
|
||||
# minimax ambiguous/similar 逐条处置记录（2026-04-23）
|
||||
|
||||
依据：
|
||||
- MiniMax API/模型文档: https://platform.minimaxi.com/document/ChatCompletion?key=66701c8c1d57f38758d581b2
|
||||
- MiniMax 定价: https://www.minimaxi.com/platform/price
|
||||
- ZenMux: https://zenmux.ai/models
|
||||
- ZenMux API: https://zenmux.ai/api/v1/models
|
||||
|
||||
## 已处置条目
|
||||
|
||||
1. `MiniMax-M2.5-highspeed`（ambiguous）
|
||||
处置：不修改。
|
||||
原因：候选混入 `m2.5/m2.5-lightning/m2.7/m2`，无法只凭 ZenMux 唯一确认高速版映射。
|
||||
|
||||
2. `MiniMax-M2.1-highspeed`（ambiguous）
|
||||
处置：不修改。
|
||||
原因：候选混入 `m2.1/m2.7-highspeed/m2/m2.5`，候选族冲突，缺少唯一锚点。
|
||||
|
||||
3. `MiniMax-Text-01`（similar）
|
||||
处置：不修改。
|
||||
原因：`similar` 命中 `minimax-m2`，但 `Text-01` 与 `M2` 不是同名同版模型，禁止跨族覆盖。
|
||||
|
||||
## 本轮 minimax 落库结果
|
||||
|
||||
- JSON 变更：0
|
||||
@@ -1,17 +0,0 @@
|
||||
# 未确认字段报告 - compute/providers/mistral.json
|
||||
|
||||
- provider: `mistral`
|
||||
- generatedAt: `2026-04-24T00:00:00+08:00`
|
||||
- 本轮范围: `defaultTemperature` / `defaultTopP`
|
||||
|
||||
## mistral-large-latest
|
||||
|
||||
- `defaultTemperature`: 已查 https://docs.mistral.ai/api 。官方只说明默认值随模型而变，需调用 `/models` 获取；公开文档未直接给出该模型默认数字，因此只能保留 `null`。
|
||||
|
||||
## mistral-small-latest
|
||||
|
||||
- `defaultTemperature`: 已查 https://docs.mistral.ai/api 。官方只说明默认值随模型而变，需调用 `/models` 获取；公开文档未直接给出该模型默认数字，因此只能保留 `null`。
|
||||
|
||||
## codestral-latest
|
||||
|
||||
- `defaultTemperature`: 已查 https://docs.mistral.ai/api 。官方只说明默认值随模型而变，需调用 `/models` 获取；公开文档未直接给出该模型默认数字，因此只能保留 `null`。
|
||||
@@ -1,30 +0,0 @@
|
||||
# 详细字段取值表 - compute/providers/mistral.json
|
||||
|
||||
- provider: `mistral`
|
||||
- generatedAt: `2026-04-24T00:00:00+08:00`
|
||||
- 本轮复核字段: `defaultTemperature` / `defaultTopP`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://docs.mistral.ai/api
|
||||
|
||||
## mistral-large-latest
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | Mistral API 文档明确写明 `temperature` 的默认值取决于具体模型，并要求调用 `/models` 获取；公开文档未给该模型的默认数字。 |
|
||||
| `defaultTopP` | `1` | `1` | 保持 | Mistral API 文档在 Chat Completion / FIM 参数定义中明确写明 `top_p` `Default Value: 1`。 |
|
||||
|
||||
## mistral-small-latest
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | Mistral API 文档明确写明 `temperature` 的默认值取决于具体模型，并要求调用 `/models` 获取；公开文档未给该模型的默认数字。 |
|
||||
| `defaultTopP` | `1` | `1` | 保持 | Mistral API 文档在 Chat Completion / FIM 参数定义中明确写明 `top_p` `Default Value: 1`。 |
|
||||
|
||||
## codestral-latest
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | Mistral API 文档明确写明 `temperature` 的默认值取决于具体模型，并要求调用 `/models` 获取；公开文档未给该模型的默认数字。 |
|
||||
| `defaultTopP` | `1` | `1` | 保持 | Mistral API 文档在 Chat Completion / FIM 参数定义中明确写明 `top_p` `Default Value: 1`。 |
|
||||
@@ -1,17 +0,0 @@
|
||||
# mistral ambiguous/similar 逐条处置记录（2026-04-23）
|
||||
|
||||
依据：
|
||||
- Mistral Models: https://docs.mistral.ai/getting-started/models
|
||||
- Mistral Pricing: https://mistral.ai/pricing
|
||||
- ZenMux: https://zenmux.ai/models
|
||||
- ZenMux API: https://zenmux.ai/api/v1/models
|
||||
|
||||
## 已处置条目
|
||||
|
||||
1. `mistral-large-latest`（similar）
|
||||
处置：不修改。
|
||||
原因：`latest` 是滚动别名，ZenMux 命中固定快照 `mistral-large-2512`；版本锚定策略不同，避免直接替换 `modelName`。
|
||||
|
||||
## 本轮 mistral 落库结果
|
||||
|
||||
- JSON 变更：0
|
||||
@@ -1,9 +0,0 @@
|
||||
# 未确认字段报告 - compute/coding-plans/moonshot-coding.json
|
||||
|
||||
- provider: `moonshot`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## kimi-k2.5
|
||||
|
||||
- `capabilities`: ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
@@ -1,42 +0,0 @@
|
||||
# 详细字段取值表 - compute/coding-plans/moonshot-coding.json
|
||||
|
||||
- provider: `moonshot`
|
||||
- priceCurrency: `USD`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://platform.kimi.com/docs/guide/kimi-k2-5-quickstart
|
||||
- https://platform.kimi.com/docs/api/models-overview
|
||||
- https://platform.kimi.com/docs/pricing/chat-k25
|
||||
- https://zenmux.ai/models
|
||||
- https://zenmux.ai/api/v1/models
|
||||
|
||||
## kimi-k2.5
|
||||
|
||||
- ZenMux匹配级别: `exact`
|
||||
- ZenMux命中: `moonshotai/kimi-k2.5`
|
||||
- ZenMux候选: `moonshotai/kimi-k2.5`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"kimi-k2.5"` | `"kimi-k2.5"` | 保持 | ZenMux匹配(exact): moonshotai/kimi-k2.5 |
|
||||
| `displayName` | `"Kimi K2.5 (Coding)"` | `"Kimi K2.5 (Coding)"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `256000` | `256000` | 保持 | Moonshot 官方 Kimi K2.5 文档注明“模型上下文长度 256k” |
|
||||
| `maxOutputTokens` | `32768` | `32768` | 保持 | Moonshot 官方 Kimi K2.5 文档“参数变动说明”给出 `max_tokens` 默认值为 32k，即 `32768` |
|
||||
| `inputPrice` | `0.58` | `0.58` | 保持 | ZenMux(moonshotai/kimi-k2.5) prompt=0.58 USD/MTokens |
|
||||
| `outputPrice` | `3.02` | `3.02` | 保持 | ZenMux(moonshotai/kimi-k2.5) completion=3.02 USD/MTokens |
|
||||
| `capabilities` | `["chat","reasoning","code","tool_use","agent","long_context","vision"]` | `["chat","reasoning","code","tool_use","agent","long_context","vision"]` | 待确认 | ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | 已复核 Moonshot 官方 Kimi K2.5 文档，K2.5 当前将 `temperature` 固定为 `1.0` |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | 已复核 Moonshot 官方 Kimi K2.5 文档，K2.5 当前将 `top_p` 固定为 `0.95` |
|
||||
| `extra` | (缺省) | (缺省) | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## kimi-for-coding
|
||||
|
||||
- 本次补充 `defaultTemperature` / `defaultTopP` 复核结论
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 已复核 Moonshot 官方模型总览与 Kimi K2.5 文档，公开模型页列出的是 `kimi-k2.5`，未公开 `kimi-for-coding` 的独立模型卡片或默认采样参数；该本地别名无法和官网型号做 1:1 映射，当前保持 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 同上；公开资料未给 `kimi-for-coding` 的固定默认 `top_p`，当前保持 `null` |
|
||||
@@ -1,49 +0,0 @@
|
||||
# 未确认字段报告 - compute/providers/moonshot.json
|
||||
|
||||
- provider: `moonshot`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## kimi-k2.5
|
||||
|
||||
- `maxOutputTokens`: 已复核 https://platform.kimi.com/docs/guide/kimi-k2-5-quickstart 与 https://platform.kimi.com/docs/guide/faq ，官方 K2.5 快速开始页给出的 `32k` 是 `max_tokens` 默认值，不是模型固定上限；FAQ 明确 `kimi-k2.5` 的最大输出长度是 `256*1024 - prompt_tokens`，因此无法把 `32768` 视为固定 `maxOutputTokens`
|
||||
- `inputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `outputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `capabilities`: ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## kimi-k2
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `maxOutputTokens`: 已复核 https://platform.kimi.com/ 、https://platform.kimi.com/docs/models 、https://platform.kimi.com/docs/pricing/chat-k2 、https://platform.kimi.com/docs/guide/kimi-k2-quickstart 与 https://platform.kimi.com/docs/api/models-overview ，官网首页当前把 `K2 0905` 展示为 `kimi-k2`，但正式模型列表/FAQ 使用的公开模型 ID 仍是 `kimi-k2-0905-preview`、`kimi-k2-0711`、`kimi-k2-turbo-preview` 等；FAQ 中“最大输出长度 = 256*1024 - prompt_tokens”的结论只明确覆盖这些精确 ID，未直接覆盖本地别名 `kimi-k2`，因此无法安全回填固定 `maxOutputTokens`
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## kimi-k2-thinking
|
||||
|
||||
- `maxOutputTokens`: 已复核 https://platform.kimi.com/docs/models 、https://platform.kimi.com/docs/pricing/chat-k2 、https://platform.kimi.com/docs/guide/kimi-k2-quickstart 与 https://platform.kimi.com/docs/api/models-overview ，官方确认 `kimi-k2-thinking` 支持 `256k` 上下文并给出参数默认值/约束，但公开文档没有给出固定最大输出常数；FAQ 的“最大输出长度”段落也未单独覆盖 `kimi-k2-thinking`
|
||||
- `inputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `outputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `capabilities`: ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## moonshot-v1-8k
|
||||
|
||||
- `maxOutputTokens`: 已复核 https://platform.kimi.com/docs/models 、https://platform.kimi.com/docs/guide/faq 与 https://platform.kimi.com/docs/pricing/chat-v1 ，官方模型页明确 V1 系列区别仅在“最大上下文长度（包括输入和输出）”，FAQ 进一步写明 `moonshot-v1-8k` 最大输出为 `8*1024 - prompt_tokens`，因此不是固定常数
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## moonshot-v1-32k
|
||||
|
||||
- `maxOutputTokens`: 已复核 https://platform.kimi.com/docs/models 、https://platform.kimi.com/docs/guide/faq 与 https://platform.kimi.com/docs/pricing/chat-v1 ，官方模型页明确 V1 系列区别仅在“最大上下文长度（包括输入和输出）”，FAQ 进一步写明 `moonshot-v1-32k` 最大输出为 `32*1024 - prompt_tokens`，因此不是固定常数
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## moonshot-v1-128k
|
||||
|
||||
- `maxOutputTokens`: 已复核 https://platform.kimi.com/docs/models 、https://platform.kimi.com/docs/guide/faq 与 https://platform.kimi.com/docs/pricing/chat-v1 ，官方模型页明确 V1 系列区别仅在“最大上下文长度（包括输入和输出）”，FAQ 进一步写明 `moonshot-v1-128k` 最大输出为 `128*1024 - prompt_tokens`，因此不是固定常数
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
@@ -1,136 +0,0 @@
|
||||
# 详细字段取值表 - compute/providers/moonshot.json
|
||||
|
||||
- provider: `moonshot`
|
||||
- priceCurrency: `CNY`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://platform.kimi.com/docs/guide/kimi-k2-6-quickstart
|
||||
- https://platform.kimi.com/docs/guide/kimi-k2-5-quickstart
|
||||
- https://platform.kimi.com/docs/guide/kimi-k2-quickstart
|
||||
- https://platform.kimi.com/docs/guide/faq
|
||||
- https://platform.kimi.com/docs/models
|
||||
- https://platform.kimi.com/
|
||||
- https://platform.kimi.com/docs/pricing/chat-k25
|
||||
- https://platform.kimi.com/docs/pricing/chat-k2
|
||||
- https://platform.kimi.com/docs/pricing/chat-v1
|
||||
- https://platform.kimi.com/docs/api/models-overview
|
||||
- https://zenmux.ai/models
|
||||
- https://zenmux.ai/api/v1/models
|
||||
|
||||
## kimi-k2.5
|
||||
|
||||
- ZenMux匹配级别: `exact`
|
||||
- ZenMux命中: `moonshotai/kimi-k2.5`
|
||||
- ZenMux候选: `moonshotai/kimi-k2.5`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"kimi-k2.5"` | `"kimi-k2.5"` | 保持 | ZenMux匹配(exact): moonshotai/kimi-k2.5 |
|
||||
| `displayName` | `"Kimi K2.5"` | `"Kimi K2.5"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `256000` | `256000` | 保持 | Moonshot 官方 Kimi K2.5 文档注明“模型上下文长度 256k” |
|
||||
| `maxOutputTokens` | `32768` | `32768` | 待确认 | 已复核 https://platform.kimi.com/docs/guide/kimi-k2-5-quickstart 与 https://platform.kimi.com/docs/guide/faq ，官方 K2.5 快速开始页给出的 `32k` 是 `max_tokens` 默认值，不是模型固定上限；FAQ 明确 `kimi-k2.5` 的最大输出长度是 `256*1024 - prompt_tokens`，因此无法把 `32768` 视为固定 `maxOutputTokens` |
|
||||
| `inputPrice` | `4` | `4` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `outputPrice` | `21` | `21` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","tool_use","agent","long_context","vision"]` | `["chat","reasoning","code","tool_use","agent","long_context","vision"]` | 待确认 | ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | Moonshot 官方参数参考 https://platform.kimi.com/docs/api/models-overview 明确 `kimi-k2.5` 的 `temperature` 为固定值 `1.0`；K2.5 快速开始 https://platform.kimi.com/docs/guide/kimi-k2-5-quickstart 进一步说明关闭思考时会改用固定值 `0.6`，但模型默认 `thinking={"type":"enabled"}` |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | Moonshot 官方参数参考 https://platform.kimi.com/docs/api/models-overview 明确 `kimi-k2.5` 的 `top_p` 为固定值 `0.95`，且 K2.5 快速开始说明不可改 |
|
||||
| `extra` | `{"thinking":{"default":"enabled","disabledTemperature":0.6},"cacheHitPrice":0.7,"supportedImageFormats":["png","jpeg","webp","gif"],"supportedVideoFormats":["mp4","mpeg","mov","avi","x-flv","mpg","webm","wmv","3gpp"]}` | `{"thinking":{"default":"enabled","disabledTemperature":0.6},"cacheHitPrice":0.7,"supportedImageFormats":["png","jpeg","webp","gif"],"supportedVideoFormats":["mp4","mpeg","mov","avi","x-flv","mpg","webm","wmv","3gpp"]}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## kimi-k2
|
||||
|
||||
- ZenMux匹配级别: `ambiguous`
|
||||
- ZenMux候选: `moonshotai/kimi-k2.6`、`moonshotai/kimi-k2.5`、`moonshotai/kimi-k2-thinking`、`moonshotai/kimi-k2-0905`、`moonshotai/kimi-k2-0711`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"kimi-k2"` | `"kimi-k2"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"Kimi K2"` | `"Kimi K2"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `256000` | `256000` | 保持 | Moonshot 官方模型列表 https://platform.kimi.com/docs/models 与 K2 定价页 https://platform.kimi.com/docs/pricing/chat-k2 均标注 Kimi K2 上下文长度为 `256k` |
|
||||
| `maxOutputTokens` | `8192` | `8192` | 待确认 | 已复核 https://platform.kimi.com/ 、https://platform.kimi.com/docs/models 、https://platform.kimi.com/docs/pricing/chat-k2 、https://platform.kimi.com/docs/guide/kimi-k2-quickstart 与 https://platform.kimi.com/docs/api/models-overview ，官网首页当前把 `K2 0905` 展示为 `kimi-k2`，但正式模型列表/FAQ 使用的公开模型 ID 仍是 `kimi-k2-0905-preview`、`kimi-k2-0711`、`kimi-k2-turbo-preview` 等；FAQ 中“最大输出长度 = 256*1024 - prompt_tokens”的结论只明确覆盖这些精确 ID，未直接覆盖本地别名 `kimi-k2`，因此无法安全回填固定 `maxOutputTokens` |
|
||||
| `inputPrice` | `4` | `4` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `16` | `16` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","tool_use","agent","long_context"]` | `["chat","reasoning","code","tool_use","agent","long_context"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `0.6` | `0.6` | 保持 | Moonshot 官方参数参考 https://platform.kimi.com/docs/api/models-overview 明确 `kimi-k2` 系列 `temperature` 默认值为 `0.6` |
|
||||
| `defaultTopP` | `1` | `1` | 保持 | Moonshot 官方参数参考 https://platform.kimi.com/docs/api/models-overview 明确 `kimi-k2` 系列 `top_p` 默认值为 `1.0` |
|
||||
| `extra` | `{"cacheHitPrice":1}` | `{"cacheHitPrice":1}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## kimi-k2-thinking
|
||||
|
||||
- ZenMux匹配级别: `exact`
|
||||
- ZenMux命中: `moonshotai/kimi-k2-thinking`
|
||||
- ZenMux候选: `moonshotai/kimi-k2-thinking`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"kimi-k2-thinking"` | `"kimi-k2-thinking"` | 保持 | ZenMux匹配(exact): moonshotai/kimi-k2-thinking |
|
||||
| `displayName` | `"Kimi K2 思考版"` | `"Kimi K2 思考版"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["reasoning"]` | `["reasoning"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `256000` | `256000` | 保持 | Moonshot 官方模型列表 https://platform.kimi.com/docs/models 标注 `kimi-k2-thinking` 支持 `256k` 上下文 |
|
||||
| `maxOutputTokens` | `16384` | `16384` | 待确认 | 已复核 https://platform.kimi.com/docs/models 、https://platform.kimi.com/docs/pricing/chat-k2 、https://platform.kimi.com/docs/guide/kimi-k2-quickstart 与 https://platform.kimi.com/docs/api/models-overview ，官方确认 `kimi-k2-thinking` 支持 `256k` 上下文并给出参数默认值/约束，但公开文档没有给出固定最大输出常数；FAQ 的“最大输出长度”段落也未单独覆盖 `kimi-k2-thinking` |
|
||||
| `inputPrice` | `4` | `4` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `outputPrice` | `16` | `16` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `capabilities` | `["reasoning","math","code","deep_thinking","long_context"]` | `["reasoning","math","code","deep_thinking","long_context"]` | 待确认 | ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | Moonshot 官方参数参考 https://platform.kimi.com/docs/api/models-overview 明确 `kimi-k2-thinking` 系列 `temperature` 默认值为 `1.0` |
|
||||
| `defaultTopP` | `1` | `1` | 保持 | Moonshot 官方参数参考 https://platform.kimi.com/docs/api/models-overview 明确 `kimi-k2-thinking` 系列 `top_p` 默认值为 `1.0` |
|
||||
| `extra` | `{"cacheHitPrice":1}` | `{"cacheHitPrice":1}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## moonshot-v1-8k
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"moonshot-v1-8k"` | `"moonshot-v1-8k"` | 保持 | Moonshot 官方模型列表与定价页直接使用该模型名 |
|
||||
| `displayName` | `"Moonshot V1 8K"` | `"Moonshot V1 8K"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `8192` | `8192` | 保持 | Moonshot 官方 V1 定价页 https://platform.kimi.com/docs/pricing/chat-v1 标注 `moonshot-v1-8k` 上下文窗口为 `8,192 tokens` |
|
||||
| `maxOutputTokens` | `4096` | `4096` | 待确认 | 已复核 https://platform.kimi.com/docs/models 、https://platform.kimi.com/docs/guide/faq 与 https://platform.kimi.com/docs/pricing/chat-v1 ，官方模型页明确 V1 系列区别仅在“最大上下文长度（包括输入和输出）”，FAQ 进一步写明 `moonshot-v1-8k` 最大输出为 `8*1024 - prompt_tokens`，因此不是固定常数 |
|
||||
| `inputPrice` | `2` | `2` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `2` | `2` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","code"]` | `["chat","code"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `0` | `0` | 保持 | Moonshot 官方参数参考 https://platform.kimi.com/docs/api/models-overview 明确 `moonshot-v1` 系列 `temperature` 默认值为 `0.0` |
|
||||
| `defaultTopP` | `1` | `1` | 保持 | Moonshot 官方参数参考 https://platform.kimi.com/docs/api/models-overview 明确 `moonshot-v1` 系列 `top_p` 默认值为 `1.0` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## moonshot-v1-32k
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"moonshot-v1-32k"` | `"moonshot-v1-32k"` | 保持 | Moonshot 官方模型列表与定价页直接使用该模型名 |
|
||||
| `displayName` | `"Moonshot V1 32K"` | `"Moonshot V1 32K"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `32768` | `32768` | 保持 | Moonshot 官方 V1 定价页 https://platform.kimi.com/docs/pricing/chat-v1 标注 `moonshot-v1-32k` 上下文窗口为 `32,768 tokens` |
|
||||
| `maxOutputTokens` | `4096` | `4096` | 待确认 | 已复核 https://platform.kimi.com/docs/models 、https://platform.kimi.com/docs/guide/faq 与 https://platform.kimi.com/docs/pricing/chat-v1 ，官方模型页明确 V1 系列区别仅在“最大上下文长度（包括输入和输出）”，FAQ 进一步写明 `moonshot-v1-32k` 最大输出为 `32*1024 - prompt_tokens`，因此不是固定常数 |
|
||||
| `inputPrice` | `5` | `5` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `5` | `5` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","code","long_context"]` | `["chat","code","long_context"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `0` | `0` | 保持 | Moonshot 官方参数参考 https://platform.kimi.com/docs/api/models-overview 明确 `moonshot-v1` 系列 `temperature` 默认值为 `0.0` |
|
||||
| `defaultTopP` | `1` | `1` | 保持 | Moonshot 官方参数参考 https://platform.kimi.com/docs/api/models-overview 明确 `moonshot-v1` 系列 `top_p` 默认值为 `1.0` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## moonshot-v1-128k
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"moonshot-v1-128k"` | `"moonshot-v1-128k"` | 保持 | Moonshot 官方模型列表与定价页直接使用该模型名 |
|
||||
| `displayName` | `"Moonshot V1 128K"` | `"Moonshot V1 128K"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `131072` | `131072` | 保持 | Moonshot 官方 V1 定价页 https://platform.kimi.com/docs/pricing/chat-v1 标注 `moonshot-v1-128k` 上下文窗口为 `131,072 tokens` |
|
||||
| `maxOutputTokens` | `4096` | `4096` | 待确认 | 已复核 https://platform.kimi.com/docs/models 、https://platform.kimi.com/docs/guide/faq 与 https://platform.kimi.com/docs/pricing/chat-v1 ，官方模型页明确 V1 系列区别仅在“最大上下文长度（包括输入和输出）”，FAQ 进一步写明 `moonshot-v1-128k` 最大输出为 `128*1024 - prompt_tokens`，因此不是固定常数 |
|
||||
| `inputPrice` | `10` | `10` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `10` | `10` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","code","long_context"]` | `["chat","code","long_context"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `0` | `0` | 保持 | Moonshot 官方参数参考 https://platform.kimi.com/docs/api/models-overview 明确 `moonshot-v1` 系列 `temperature` 默认值为 `0.0` |
|
||||
| `defaultTopP` | `1` | `1` | 保持 | Moonshot 官方参数参考 https://platform.kimi.com/docs/api/models-overview 明确 `moonshot-v1` 系列 `top_p` 默认值为 `1.0` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
@@ -1,16 +0,0 @@
|
||||
# moonshot ambiguous/similar 逐条处置记录（2026-04-23）
|
||||
|
||||
依据：
|
||||
- Moonshot 定价文档: https://platform.moonshot.cn/docs/pricing/chat
|
||||
- ZenMux: https://zenmux.ai/models
|
||||
- ZenMux API: https://zenmux.ai/api/v1/models
|
||||
|
||||
## 已处置条目
|
||||
|
||||
1. `kimi-k2`（ambiguous）
|
||||
处置：不修改。
|
||||
原因：候选包含 `k2.6/k2.5/k2-thinking/k2-0905/k2-0711`，属于不同版本/模式，无法唯一确定该条应映射到哪个具体版本。
|
||||
|
||||
## 本轮 moonshot 落库结果
|
||||
|
||||
- JSON 变更：0
|
||||
@@ -1,13 +0,0 @@
|
||||
# 未确认字段报告 - compute/coding-plans/moorethread-coding.json
|
||||
|
||||
- provider: `moorethread`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## mt-coder
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `contextWindow`: 已复核新闻页 https://www.mthreads.com/news/277 、方案页 https://www.mthreads.com/solution/AIInference 与产品页 https://www.mthreads.com/product/AIInferenceSuite ，官网当前只公开 AI Coding / AI 推理方案与产品能力介绍，没有 `mt-coder` 独立模型页，也没有任何上下文长度字段，因此无法确认固定 `contextWindow`
|
||||
- `maxOutputTokens`: 已复核 https://www.mthreads.com/news/277 、https://www.mthreads.com/solution/AIInference 与 https://www.mthreads.com/product/AIInferenceSuite ，官网当前没有 `mt-coder` 独立模型卡片、参数表或固定输出长度说明，无法确认固定 `maxOutputTokens`
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
@@ -1,32 +0,0 @@
|
||||
# 详细字段取值表 - compute/coding-plans/moorethread-coding.json
|
||||
|
||||
- provider: `moorethread`
|
||||
- priceCurrency: `USD`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://www.mthreads.com/news/277
|
||||
- https://www.mthreads.com/solution/AIInference
|
||||
- https://www.mthreads.com/product/AIInferenceSuite
|
||||
- https://zenmux.ai/models
|
||||
- https://zenmux.ai/api/v1/models
|
||||
|
||||
## mt-coder
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"mt-coder"` | `"mt-coder"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"MT Coder (Coding)"` | `"MT Coder (Coding)"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `128000` | `128000` | 待确认 | 已复核新闻页 https://www.mthreads.com/news/277 、方案页 https://www.mthreads.com/solution/AIInference 与产品页 https://www.mthreads.com/product/AIInferenceSuite ，官网当前只公开 AI Coding / AI 推理方案与产品能力介绍，没有 `mt-coder` 独立模型页，也没有任何上下文长度字段，因此无法确认固定 `contextWindow` |
|
||||
| `maxOutputTokens` | `8192` | `8192` | 待确认 | 已复核 https://www.mthreads.com/news/277 、https://www.mthreads.com/solution/AIInference 与 https://www.mthreads.com/product/AIInferenceSuite ，官网当前没有 `mt-coder` 独立模型卡片、参数表或固定输出长度说明，无法确认固定 `maxOutputTokens` |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","code"]` | `["chat","code"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 已复核 https://www.mthreads.com/news/277 、https://www.mthreads.com/solution/AIInference 与 https://www.mthreads.com/product/AIInferenceSuite ，官网未公开 `mt-coder` 的推理参数文档或默认采样值，当前保持 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 同上；官网未公开 `mt-coder` 的默认 `top_p`，当前保持 `null` |
|
||||
| `extra` | (缺省) | (缺省) | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
@@ -1,12 +0,0 @@
|
||||
# 未确认字段报告 - compute/providers/ollama.json
|
||||
|
||||
- provider: `ollama`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## llama3.1:70b
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `maxOutputTokens`: 已复核 https://ollama.com/library/llama3.1 与 https://ai.meta.com/blog/meta-llama-3-1/ ，官方仅确认 `llama3.1:70b` 为 `128K context window`；进一步复核 https://docs.ollama.com/modelfile 与 https://docs.ollama.com/api ，Ollama 将输出长度控制公开为运行时参数 `num_predict`，默认 `-1`（无限生成），并未给 `llama3.1:70b` 这个 Ollama 变体定义固定模型级 `maxOutputTokens`
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
@@ -1,33 +0,0 @@
|
||||
# 详细字段取值表 - compute/providers/ollama.json
|
||||
|
||||
- provider: `ollama`
|
||||
- priceCurrency: `USD`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://ollama.com/library/llama3.1
|
||||
- https://ai.meta.com/blog/meta-llama-3-1/
|
||||
- https://docs.ollama.com/modelfile
|
||||
- https://docs.ollama.com/api
|
||||
- https://zenmux.ai/models
|
||||
- https://zenmux.ai/api/v1/models
|
||||
|
||||
## llama3.1:70b
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"llama3.1:70b"` | `"llama3.1:70b"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"Llama 3.1 70B"` | `"Llama 3.1 70B"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `131072` | `131072` | 保持 | Ollama 官方模型库 https://ollama.com/library/llama3.1 列出 `llama3.1:70b` 为 `128K context window`；当前值 `131072` 为按 `128 * 1024` 换算 |
|
||||
| `maxOutputTokens` | `8192` | `8192` | 待确认 | 已复核 https://ollama.com/library/llama3.1 与 https://ai.meta.com/blog/meta-llama-3-1/ ，官方仅确认 `llama3.1:70b` 为 `128K context window`；进一步复核 https://docs.ollama.com/modelfile 与 https://docs.ollama.com/api ，Ollama 将输出长度控制公开为运行时参数 `num_predict`，默认 `-1`（无限生成），并未给 `llama3.1:70b` 这个 Ollama 变体定义固定模型级 `maxOutputTokens` |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","code","reasoning"]` | `["chat","code","reasoning"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `0.8` | `0.8` | 保持 | 已复核 Ollama 官方 Modelfile 文档，`temperature` 默认值为 `0.8` |
|
||||
| `defaultTopP` | `0.9` | `0.9` | 保持 | 已复核 Ollama 官方 Modelfile 文档，`top_p` 默认值为 `0.9` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
@@ -1,7 +0,0 @@
|
||||
# 未确认字段报告 - compute/providers/openai.json
|
||||
|
||||
- provider: `openai`
|
||||
- generatedAt: `2026-04-24T00:00:00+08:00`
|
||||
- 本轮范围: `defaultTemperature` / `defaultTopP`
|
||||
|
||||
本轮范围内无剩余未确认项。
|
||||
@@ -1,41 +0,0 @@
|
||||
# 详细字段取值表 - compute/providers/openai.json
|
||||
|
||||
- provider: `openai`
|
||||
- generatedAt: `2026-04-24T00:00:00+08:00`
|
||||
- 本轮复核字段: `defaultTemperature` / `defaultTopP`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://api.openai.com/v1/responses
|
||||
- https://api.openai.com/v1/realtime/sessions
|
||||
- https://api.openai.com/v1/embeddings
|
||||
- https://api.openai.com/v1/audio/speech
|
||||
- https://api.openai.com/v1/audio/transcriptions
|
||||
- https://api.openai.com/v1/images/generations
|
||||
|
||||
## 文本 / 视觉 / 推理模型
|
||||
|
||||
- 模型: `gpt-5.2`, `gpt-5.2-pro`, `gpt-5.1`, `gpt-5`, `gpt-5-pro`, `gpt-5-mini`, `gpt-5-nano`, `gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`, `gpt-4o`, `gpt-4o-mini`, `o3`, `o3-pro`, `o3-mini`, `o4-mini`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | OpenAI `/v1/responses` 官方示例在请求省略 `temperature` 时，响应对象返回 `temperature: 1.0`。 |
|
||||
| `defaultTopP` | `1` | `1` | 保持 | OpenAI `/v1/responses` 官方示例在请求省略 `top_p` 时，响应对象返回 `top_p: 1.0`。 |
|
||||
|
||||
## Realtime 模型
|
||||
|
||||
- 模型: `gpt-4o-realtime`, `gpt-4o-realtime-preview`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `0.7` | `0.7` | 保持 | OpenAI `/v1/realtime/sessions` 官方示例在请求未显式设置 `temperature` 时，返回的 session 对象包含 `temperature: 0.7`。 |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | OpenAI `/v1/realtime/sessions` 官方示例和返回对象未公开 `top_p` 默认值；JSON 不应伪装成官方默认值。 |
|
||||
|
||||
## Embedding / TTS / ASR / Image 模型
|
||||
|
||||
- 模型: `text-embedding-3-small`, `text-embedding-3-large`, `tts-1`, `tts-1-hd`, `whisper-1`, `dall-e-3`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | OpenAI `embeddings`、`audio/speech`、`images/generations` 等官方接口未给这些模型定义通用聊天采样默认值；按项目规则记为不适用。`whisper-1` 所属 `audio/transcriptions` 虽有任务参数，但不应作为 provider 级模型默认采样值。 |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | OpenAI `embeddings`、`audio/speech`、`audio/transcriptions`、`images/generations` 官方接口未给这些模型定义通用聊天采样默认值；按项目规则记为不适用。 |
|
||||
@@ -1,59 +0,0 @@
|
||||
# openai ambiguous/similar 逐条处置记录（2026-04-23）
|
||||
|
||||
依据：
|
||||
- OpenAI Models: https://platform.openai.com/docs/models
|
||||
- OpenAI Pricing: https://platform.openai.com/docs/pricing
|
||||
- TTS-1: https://platform.openai.com/docs/models/tts-1
|
||||
- Whisper-1: https://platform.openai.com/docs/models/whisper-1
|
||||
- o3-mini: https://platform.openai.com/docs/models/o3-mini
|
||||
- GPT-4o Realtime Preview: https://platform.openai.com/docs/models/gpt-4o-realtime-preview
|
||||
- GPT Realtime (GA): https://platform.openai.com/docs/models/gpt-realtime
|
||||
- Embeddings guide: https://platform.openai.com/docs/guides/embeddings
|
||||
|
||||
## 已处置条目
|
||||
|
||||
1. `tts-1`（ambiguous）
|
||||
处置：不修改。
|
||||
原因：ZenMux 候选跨模态/多候选冲突；官方计费是 TTS 字符/音频口径，不适合直接映射到当前 JSON 的 token 价格字段。
|
||||
|
||||
2. `whisper-1`（ambiguous）
|
||||
处置：不修改。
|
||||
原因：官方定价以分钟为主（transcription），与当前 JSON token 价格字段语义不一致；ZenMux 无稳定同名映射。
|
||||
|
||||
3. `o3-mini`（ambiguous）
|
||||
处置：不修改。
|
||||
原因：官方模型页显示当前文件里的 `contextWindow=200000`、`maxOutputTokens=100000`、`input=1.1`、`output=4.4` 已一致。
|
||||
|
||||
4. `gpt-4o-realtime`（ambiguous）
|
||||
处置：不修改。
|
||||
原因：官方当前 GA 条目是 `gpt-realtime`，与本地 `gpt-4o-realtime` 命名不完全一致，直接覆盖有别名风险；需你确认是否迁移到 `gpt-realtime`。
|
||||
|
||||
5. `gpt-4o-realtime-preview`（ambiguous）
|
||||
处置：不修改。
|
||||
原因：官方 preview 页显示 `32k/4096`、`$5/$20`，与本地配置一致。
|
||||
|
||||
6. `o3-pro`（similar）
|
||||
处置：不修改。
|
||||
原因：`similar` 命中 `gpt-5-pro` 不是同模型族，禁止跨族覆盖 `context/price`。
|
||||
|
||||
## 本轮 openai 落库结果
|
||||
|
||||
- JSON 变更：0
|
||||
- 保持原则：`similar/ambiguous` 未达到唯一映射证据时不改强约束字段
|
||||
|
||||
## none 条目补齐（第2轮）
|
||||
|
||||
依据：
|
||||
- OpenAI Embeddings guide / API reference（官方）显示 `text-embedding-3-small`、`text-embedding-3-large` 最大输入为 `8192` tokens。
|
||||
|
||||
已执行：
|
||||
1. `text-embedding-3-small`：新增 `contextWindow: 8192`
|
||||
2. `text-embedding-3-large`：新增 `contextWindow: 8192`
|
||||
3. `tts-1`：补齐 `inputPrice: 15`（USD / 1M tokens）
|
||||
4. `tts-1-hd`：补齐 `inputPrice: 30`（USD / 1M tokens）
|
||||
5. `whisper-1`：补齐 `inputPrice: 0.006`（USD / 1M tokens）
|
||||
6. `gpt-4o-realtime`：按官方 realtime 规格补齐 `maxOutputTokens: 4096`，并将上下文与价格更新为 `contextWindow: 32000`、`inputPrice: 4`、`outputPrice: 16`
|
||||
|
||||
未改项（说明）：
|
||||
- `maxOutputTokens` / `outputPrice` 仍缺省：Embedding 属输入向量化，不产生 completion token，字段语义不适配。
|
||||
- `tts-1-hd`、`dall-e-3` 仍缺省 token 价格字段：官方计费口径为字符/图片，不是 token。
|
||||
@@ -1,26 +0,0 @@
|
||||
# 未确认字段报告 - compute/providers/openrouter.json
|
||||
|
||||
- provider: `openrouter`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## openrouter/auto
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `maxOutputTokens`: 已复核 https://openrouter.ai/docs/model-routing 、https://openrouter.ai/openrouter/auto/overview 与 https://openrouter.ai/api/v1/models ，`openrouter/auto` 官方定义就是动态路由到底层模型集合；其官方模型 API 当前对该条目返回 `top_provider.max_completion_tokens=null`，因此不存在统一固定 `maxOutputTokens`
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## openai/gpt-oss-120b:free
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## qwen/qwen3-coder:free
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
@@ -1,75 +0,0 @@
|
||||
# 详细字段取值表 - compute/providers/openrouter.json
|
||||
|
||||
- provider: `openrouter`
|
||||
- priceCurrency: `USD`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://openrouter.ai/docs/model-routing
|
||||
- https://openrouter.ai/openrouter/auto/overview
|
||||
- https://openrouter.ai/api/v1/models
|
||||
- https://openrouter.ai/openai/gpt-oss-120b:free
|
||||
- https://openrouter.ai/qwen/qwen3-coder:free
|
||||
- https://openrouter.ai/docs/api/reference/parameters
|
||||
- https://platform.openai.com/docs/models/gpt-oss-120b
|
||||
- https://help.aliyun.com/zh/model-studio/model
|
||||
- https://zenmux.ai/models
|
||||
- https://zenmux.ai/api/v1/models
|
||||
|
||||
## openrouter/auto
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"openrouter/auto"` | `"openrouter/auto"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"OpenRouter Auto"` | `"OpenRouter Auto"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `2000000` | `2000000` | 保持 | OpenRouter Auto Router 页面 https://openrouter.ai/openrouter/auto/overview 列出 `openrouter/auto` 为 `2,000,000 context` |
|
||||
| `maxOutputTokens` | `16384` | `16384` | 待确认 | 已复核 https://openrouter.ai/docs/model-routing 、https://openrouter.ai/openrouter/auto/overview 与 https://openrouter.ai/api/v1/models ，`openrouter/auto` 官方定义就是动态路由到底层模型集合；其官方模型 API 当前对该条目返回 `top_provider.max_completion_tokens=null`，因此不存在统一固定 `maxOutputTokens` |
|
||||
| `inputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","auto_routing"]` | `["chat","auto_routing"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | OpenRouter 参数文档 https://openrouter.ai/docs/api/reference/parameters 明确写明当请求未传入该字段时，`temperature` 默认值为 `1.0` |
|
||||
| `defaultTopP` | `1` | `1` | 保持 | OpenRouter 参数文档 https://openrouter.ai/docs/api/reference/parameters 明确写明当请求未传入该字段时，`top_p` 默认值为 `1.0` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## openai/gpt-oss-120b:free
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"openai/gpt-oss-120b:free"` | `"openai/gpt-oss-120b:free"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"GPT-OSS 120B (免费)"` | `"GPT-OSS 120B (免费)"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `131072` | `131072` | 保持 | OpenRouter 模型页 https://openrouter.ai/openai/gpt-oss-120b:free 与 OpenAI 官方模型页 https://platform.openai.com/docs/models/gpt-oss-120b 均标注 `131,072 context` |
|
||||
| `maxOutputTokens` | `131072` | `131072` | 保持 | OpenAI 官方模型页 https://platform.openai.com/docs/models/gpt-oss-120b 标注 `131,072 max output tokens`；OpenRouter free 变体沿用同一底模 |
|
||||
| `inputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code"]` | `["chat","reasoning","code"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | OpenRouter 参数文档 https://openrouter.ai/docs/api/reference/parameters 明确写明当请求未传入该字段时，`temperature` 默认值为 `1.0` |
|
||||
| `defaultTopP` | `1` | `1` | 保持 | OpenRouter 参数文档 https://openrouter.ai/docs/api/reference/parameters 明确写明当请求未传入该字段时，`top_p` 默认值为 `1.0` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## qwen/qwen3-coder:free
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"qwen/qwen3-coder:free"` | `"qwen/qwen3-coder:free"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"Qwen3 Coder 480B (免费)"` | `"Qwen3 Coder 480B (免费)"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `262000` | `262000` | 保持 | OpenRouter 模型页 https://openrouter.ai/qwen/qwen3-coder:free 标注该 free 变体的 context 为 `262,000` |
|
||||
| `maxOutputTokens` | `262000` | `262000` | 保持 | OpenRouter 官方模型 API https://openrouter.ai/api/v1/models 当前对 `qwen/qwen3-coder:free` 返回 `context_length: 262000` 且 `top_provider.max_completion_tokens: 262000`；对应模型页 https://openrouter.ai/qwen/qwen3-coder:free 也标注 `262,000 context` |
|
||||
| `inputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["code","reasoning","agent","tool_use"]` | `["code","reasoning","agent","tool_use"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | OpenRouter 参数文档 https://openrouter.ai/docs/api/reference/parameters 明确写明当请求未传入该字段时，`temperature` 默认值为 `1.0` |
|
||||
| `defaultTopP` | `1` | `1` | 保持 | OpenRouter 参数文档 https://openrouter.ai/docs/api/reference/parameters 明确写明当请求未传入该字段时，`top_p` 默认值为 `1.0` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
@@ -1,20 +0,0 @@
|
||||
# 未确认字段报告 - compute/providers/perplexity.json
|
||||
|
||||
- provider: `perplexity`
|
||||
- generatedAt: `2026-04-24T00:00:00+08:00`
|
||||
- 本轮范围: `defaultTemperature` / `defaultTopP`
|
||||
|
||||
## sonar-pro
|
||||
|
||||
- `defaultTemperature`: 已查 https://docs.perplexity.ai/api-reference/sonar-post 。官方有参数定义和范围，但没有默认值。
|
||||
- `defaultTopP`: 已查 https://docs.perplexity.ai/api-reference/sonar-post 。官方有参数定义和范围，但没有默认值。
|
||||
|
||||
## sonar-reasoning-pro
|
||||
|
||||
- `defaultTemperature`: 已查 https://docs.perplexity.ai/api-reference/sonar-post 。官方有参数定义和范围，但没有默认值。
|
||||
- `defaultTopP`: 已查 https://docs.perplexity.ai/api-reference/sonar-post 。官方有参数定义和范围，但没有默认值。
|
||||
|
||||
## sonar
|
||||
|
||||
- `defaultTemperature`: 已查 https://docs.perplexity.ai/api-reference/sonar-post 。官方有参数定义和范围，但没有默认值。
|
||||
- `defaultTopP`: 已查 https://docs.perplexity.ai/api-reference/sonar-post 。官方有参数定义和范围，但没有默认值。
|
||||
@@ -1,30 +0,0 @@
|
||||
# 详细字段取值表 - compute/providers/perplexity.json
|
||||
|
||||
- provider: `perplexity`
|
||||
- generatedAt: `2026-04-24T00:00:00+08:00`
|
||||
- 本轮复核字段: `defaultTemperature` / `defaultTopP`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://docs.perplexity.ai/api-reference/sonar-post
|
||||
|
||||
## sonar-pro
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | Perplexity Sonar API 文档给出了 `temperature` 参数和取值范围，但未给“省略时默认值”。 |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | Perplexity Sonar API 文档给出了 `top_p` 参数和取值范围，但未给“省略时默认值”。 |
|
||||
|
||||
## sonar-reasoning-pro
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | Perplexity Sonar API 文档给出了 `temperature` 参数和取值范围，但未给“省略时默认值”。 |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | Perplexity Sonar API 文档给出了 `top_p` 参数和取值范围，但未给“省略时默认值”。 |
|
||||
|
||||
## sonar
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | Perplexity Sonar API 文档给出了 `temperature` 参数和取值范围，但未给“省略时默认值”。 |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | Perplexity Sonar API 文档给出了 `top_p` 参数和取值范围，但未给“省略时默认值”。 |
|
||||
@@ -1,25 +0,0 @@
|
||||
# 未确认字段报告 - compute/providers/siliconflow.json
|
||||
|
||||
- provider: `siliconflow`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## Qwen/Qwen3-Coder-480B-A35B-Instruct
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## Qwen/Qwen3-235B-A22B-Instruct-2507
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## BAAI/bge-m3
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
@@ -1,73 +0,0 @@
|
||||
# 详细字段取值表 - compute/providers/siliconflow.json
|
||||
|
||||
- provider: `siliconflow`
|
||||
- priceCurrency: `CNY`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://www.siliconflow.cn/models
|
||||
- https://siliconflow.cn/pricing
|
||||
- https://docs.siliconflow.cn/cn/userguide/capabilities/reasoning
|
||||
- https://docs.siliconflow.cn/en/faqs/misc
|
||||
- https://docs.siliconflow.cn/en/api-reference/chat-completions/chat-completions
|
||||
- https://docs.siliconflow.cn/en/api-reference/embeddings/create-embeddings
|
||||
- https://zenmux.ai/models
|
||||
- https://zenmux.ai/api/v1/models
|
||||
|
||||
## Qwen/Qwen3-Coder-480B-A35B-Instruct
|
||||
|
||||
- ZenMux匹配级别: `ambiguous`
|
||||
- ZenMux候选: `qwen/qwen3-coder`、`qwen/qwen3-coder-plus`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"Qwen/Qwen3-Coder-480B-A35B-Instruct"` | `"Qwen/Qwen3-Coder-480B-A35B-Instruct"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"Qwen3 Coder 480B (硅基)"` | `"Qwen3 Coder 480B (硅基)"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `262144` | `262144` | 保持 | 硅基流动模型中心 https://www.siliconflow.cn/models 对 `Qwen/Qwen3-Coder-480B-A35B-Instruct` 与 `Qwen/Qwen3-235B-A22B-Instruct-2507` 均注明支持 `256K` 最大上下文长度；当前值 `262144` 为按 `256 * 1024` 换算 |
|
||||
| `maxOutputTokens` | `262144` | `262144` | 保持 | 硅基流动模型中心 https://www.siliconflow.cn/models 标注该模型最大上下文长度为 `256K`；官方 FAQ https://docs.siliconflow.cn/en/faqs/misc 明确说明 `max_tokens` 与 `context_length` 相等，因此当前值 `262144` 可按 `256 * 1024` 保持 |
|
||||
| `inputPrice` | `8` | `8` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `16` | `16` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","code","long_context","agent","tool_use"]` | `["chat","code","long_context","agent","tool_use"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 硅基流动对话接口文档 https://docs.siliconflow.cn/en/api-reference/chat-completions/chat-completions 仅给出 `temperature` 示例值，没有 `default:` 字段；按“官网未定义默认值则记为 null”处理 |
|
||||
| `defaultTopP` | `0.7` | `0.7` | 保持 | 硅基流动对话接口文档 https://docs.siliconflow.cn/en/api-reference/chat-completions/chat-completions 明确 `top_p` 的 `default: 0.7` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## Qwen/Qwen3-235B-A22B-Instruct-2507
|
||||
|
||||
- ZenMux匹配级别: `ambiguous`
|
||||
- ZenMux候选: `qwen/qwen3-235b-a22b-2507`、`qwen/qwen3-235b-a22b-thinking-2507`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"Qwen/Qwen3-235B-A22B-Instruct-2507"` | `"Qwen/Qwen3-235B-A22B-Instruct-2507"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"Qwen3 235B (硅基)"` | `"Qwen3 235B (硅基)"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `262144` | `262144` | 保持 | 硅基流动模型中心 https://www.siliconflow.cn/models 对 `Qwen/Qwen3-Coder-480B-A35B-Instruct` 与 `Qwen/Qwen3-235B-A22B-Instruct-2507` 均注明支持 `256K` 最大上下文长度；当前值 `262144` 为按 `256 * 1024` 换算 |
|
||||
| `maxOutputTokens` | `262144` | `262144` | 保持 | 硅基流动模型中心 https://www.siliconflow.cn/models 标注该模型最大上下文长度为 `256K`；官方 FAQ https://docs.siliconflow.cn/en/faqs/misc 明确说明 `max_tokens` 与 `context_length` 相等，因此当前值 `262144` 可按 `256 * 1024` 保持 |
|
||||
| `inputPrice` | `2.5` | `2.5` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `10` | `10` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","code","multilingual","tool_use","agent","long_context"]` | `["chat","code","multilingual","tool_use","agent","long_context"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 硅基流动对话接口文档 https://docs.siliconflow.cn/en/api-reference/chat-completions/chat-completions 仅给出 `temperature` 示例值，没有 `default:` 字段；按“官网未定义默认值则记为 null”处理 |
|
||||
| `defaultTopP` | `0.7` | `0.7` | 保持 | 硅基流动对话接口文档 https://docs.siliconflow.cn/en/api-reference/chat-completions/chat-completions 明确 `top_p` 的 `default: 0.7` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## BAAI/bge-m3
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"BAAI/bge-m3"` | `"BAAI/bge-m3"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"BGE-M3 (硅基)"` | `"BGE-M3 (硅基)"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["embedding"]` | `["embedding"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `8192` | `8192` | 保持 | 硅基流动 Embeddings API 文档 https://docs.siliconflow.cn/en/api-reference/embeddings/create-embeddings 明确列出 `BAAI/bge-m3` / `Pro/BAAI/bge-m3` 的最大输入 Token 为 `8192` |
|
||||
| `maxOutputTokens` | `0` | `0` | 保持 | 已查 https://www.siliconflow.cn/models ，`BAAI/bge-m3` 为 embedding 模型，输出为向量表示，官方未定义 max output tokens，当前以 `0` 记录为不适用 |
|
||||
| `inputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `0` | `0` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["text_embedding","multilingual"]` | `["text_embedding","multilingual"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | `BAAI/bge-m3` 为 embedding 模型，官方接口 https://docs.siliconflow.cn/en/api-reference/embeddings/create-embeddings 不支持采样参数，按不适用记为 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | `BAAI/bge-m3` 为 embedding 模型，官方接口 https://docs.siliconflow.cn/en/api-reference/embeddings/create-embeddings 不支持采样参数，按不适用记为 `null` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
@@ -1,21 +0,0 @@
|
||||
# siliconflow ambiguous/similar 逐条处置记录（2026-04-23）
|
||||
|
||||
依据：
|
||||
- SiliconFlow Models: https://www.siliconflow.com/models
|
||||
- SiliconFlow Pricing: https://siliconflow.cn/pricing
|
||||
- ZenMux: https://zenmux.ai/models
|
||||
- ZenMux API: https://zenmux.ai/api/v1/models
|
||||
|
||||
## 已处置条目
|
||||
|
||||
1. `Qwen/Qwen3-Coder-480B-A35B-Instruct`（ambiguous）
|
||||
处置：不修改。
|
||||
原因：候选 `qwen3-coder` 与 `qwen3-coder-plus` 并存，且本地是 provider 特有命名（带组织前缀与参数规模），不满足唯一映射。
|
||||
|
||||
2. `Qwen/Qwen3-235B-A22B-Instruct-2507`（ambiguous）
|
||||
处置：不修改。
|
||||
原因：候选同时存在 `instruct` 与 `thinking` 变体，推理模式不同，不能仅靠名称近似覆盖。
|
||||
|
||||
## 本轮 siliconflow 落库结果
|
||||
|
||||
- JSON 变更：0
|
||||
@@ -1,11 +0,0 @@
|
||||
# 未确认字段报告 - compute/providers/stability.json
|
||||
|
||||
- provider: `stability`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## stable-diffusion-3.5-large
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
@@ -1,31 +0,0 @@
|
||||
# 详细字段取值表 - compute/providers/stability.json
|
||||
|
||||
- provider: `stability`
|
||||
- priceCurrency: `USD`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://stability.ai/news/introducing-stable-diffusion-3-5
|
||||
- https://platform.stability.ai/docs/api-reference
|
||||
- https://zenmux.ai/models
|
||||
- https://zenmux.ai/api/v1/models
|
||||
|
||||
## stable-diffusion-3.5-large
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"stable-diffusion-3.5-large"` | `"stable-diffusion-3.5-large"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"Stable Diffusion 3.5 Large"` | `"Stable Diffusion 3.5 Large"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["image_gen"]` | `["image_gen"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `0` | `0` | 保持 | 已查 https://stability.ai/news/introducing-stable-diffusion-3-5 与 https://platform.stability.ai/docs/api-reference ，`stable-diffusion-3.5-large` 为图像生成模型，context window 字段不适用，当前以 `0` 记录 |
|
||||
| `maxOutputTokens` | `0` | `0` | 保持 | 已查 https://stability.ai/news/introducing-stable-diffusion-3-5 与 https://platform.stability.ai/docs/api-reference ，该模型输出为图像而非 token completion，当前以 `0` 记录为不适用 |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["image_generation","high_quality","controllable"]` | `["image_generation","high_quality","controllable"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 已复核 Stability 官方模型发布页与 API Reference，`stable-diffusion-3.5-large` 为图像生成模型，官方 API 不以文本采样 `temperature` 控制输出，当前保持 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 同上；图像生成模型不提供文本采样 `top_p`，当前保持 `null` |
|
||||
| `extra` | `{"supportedImageSizes":["1024x1024","1152x896","896x1152","1216x832","832x1216"],"supportedStyles":["photographic","digital-art","anime","comic-book"]}` | `{"supportedImageSizes":["1024x1024","1152x896","896x1152","1216x832","832x1216"],"supportedStyles":["photographic","digital-art","anime","comic-book"]}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
@@ -1,18 +0,0 @@
|
||||
# 未确认字段报告 - compute/providers/tencent.json
|
||||
|
||||
- provider: `tencent`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## hunyuan-2.0-thinking-20251109
|
||||
|
||||
- `inputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `outputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `capabilities`: ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## hunyuan-turbos-latest
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
@@ -1,71 +0,0 @@
|
||||
# 详细字段取值表 - compute/providers/tencent.json
|
||||
|
||||
- provider: `tencent`
|
||||
- priceCurrency: `CNY`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://cloud.tencent.com/document/product/1729/104753
|
||||
- https://cloud.tencent.com/document/product/1729/111007
|
||||
- https://cloud.tencent.com/document/product/1729/127293
|
||||
- https://zenmux.ai/models
|
||||
- https://zenmux.ai/api/v1/models
|
||||
|
||||
## hunyuan-2.0-thinking-20251109
|
||||
|
||||
- ZenMux匹配级别: `stripped`
|
||||
- ZenMux命中: `tencent/hunyuan-2.0-thinking`
|
||||
- ZenMux候选: `tencent/hunyuan-2.0-thinking`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"hunyuan-2.0-thinking-20251109"` | `"hunyuan-2.0-thinking-20251109"` | 保持 | 腾讯云产品概述 https://cloud.tencent.com/document/product/1729/104753 直接列出该 API 调用名 |
|
||||
| `displayName` | `"混元 2.0 Think"` | `"混元 2.0 Think"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["reasoning"]` | `["reasoning"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `128000` | `128000` | 保持 | 腾讯云产品概述 https://cloud.tencent.com/document/product/1729/104753 标注 `hunyuan-2.0-thinking-20251109` 最大输入为 `128k` |
|
||||
| `maxOutputTokens` | `65536` | `65536` | 保持 | 腾讯云产品概述 https://cloud.tencent.com/document/product/1729/104753 标注 `hunyuan-2.0-thinking-20251109` 最大输出为 `64k` |
|
||||
| `inputPrice` | `3.975` | `3.975` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `outputPrice` | `15.9` | `15.9` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","deep_thinking","long_context"]` | `["chat","reasoning","deep_thinking","long_context"]` | 待确认 | ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 腾讯混元 OpenAI 兼容接口文档 https://cloud.tencent.com/document/product/1729/111007 明确 `temperature` 默认值为“无”，且“不传值时使用各模型推荐值，不推荐用户修改”；官方没有公开统一模型级默认数值，因此本地字段应为 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 腾讯混元 OpenAI 兼容接口文档 https://cloud.tencent.com/document/product/1729/111007 虽在参数表写 `top_p` 默认值 `0`，但同一行说明“不传值时使用各模型推荐值”，并未公开统一模型级默认数值，因此本地字段应为 `null` 而不是 `0` 或 `1` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## hunyuan-turbos-latest
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"hunyuan-turbos-latest"` | `"hunyuan-turbos-latest"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"混元 Turbo S"` | `"混元 Turbo S"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `32768` | `32768` | 保持 | 腾讯云产品概述 https://cloud.tencent.com/document/product/1729/104753 标注 `hunyuan-turbos-latest` 最大输入为 `32k` |
|
||||
| `maxOutputTokens` | `16384` | `16384` | 保持 | 腾讯云产品概述 https://cloud.tencent.com/document/product/1729/104753 标注 `hunyuan-turbos-latest` 最大输出为 `16k` |
|
||||
| `inputPrice` | `0.8` | `0.8` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `2` | `2` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","vision","fast","tool_use"]` | `["chat","reasoning","code","vision","fast","tool_use"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 腾讯混元 OpenAI 兼容接口文档 https://cloud.tencent.com/document/product/1729/111007 明确 `temperature` 默认值为“无”，且“不传值时使用各模型推荐值”，未公开 `hunyuan-turbos-latest` 的统一默认数值 |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 腾讯混元 OpenAI 兼容接口文档 https://cloud.tencent.com/document/product/1729/111007 的 `top_p` 参数表虽写默认值 `0`，但同一行明确实际省略时使用各模型推荐值，未公开模型级默认数值 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## hunyuan-2.0-instruct-20251111
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"hunyuan-2.0-instruct-20251111"` | `"hunyuan-2.0-instruct-20251111"` | 保持 | 腾讯云 Anthropic 兼容接口文档 https://cloud.tencent.com/document/product/1729/127293 直接列出该模型名 |
|
||||
| `displayName` | `"混元 2.0 Instruct"` | `"混元 2.0 Instruct"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `147456` | `147456` | 保持 | 腾讯云产品概述 https://cloud.tencent.com/document/product/1729/104753 标注该模型最大输入 `128k`、最大输出 `16k`；当前值按两者和维护为 `147456` |
|
||||
| `maxOutputTokens` | `16384` | `16384` | 保持 | 腾讯云产品概述 https://cloud.tencent.com/document/product/1729/104753 标注该模型最大输出 `16k` |
|
||||
| `inputPrice` | `3.18` | `3.18` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `outputPrice` | `7.95` | `7.95` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","code","long_context","tool_use"]` | `["chat","code","long_context","tool_use"]` | 待确认 | 能力字段为项目语义字段，需官方能力说明复核 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 腾讯混元 OpenAI 兼容接口文档 https://cloud.tencent.com/document/product/1729/111007 明确 `temperature` 默认值为“无”，不传值时使用各模型推荐值，但未公开该模型推荐数值 |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 腾讯混元 OpenAI 兼容接口文档 https://cloud.tencent.com/document/product/1729/111007 参数表虽写 `top_p` 默认值 `0`，但同一行说明省略时使用各模型推荐值，未公开模型级默认数值 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
@@ -1,11 +0,0 @@
|
||||
# 未确认字段报告 - compute/coding-plans/volcengine-coding.json
|
||||
|
||||
- provider: `volcengine`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## ark-code-latest
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
@@ -1,31 +0,0 @@
|
||||
# 详细字段取值表 - compute/coding-plans/volcengine-coding.json
|
||||
|
||||
- provider: `volcengine`
|
||||
- priceCurrency: `USD`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://developer.volcengine.com/articles/7615528054736945158
|
||||
- https://www.volcengine.com/docs/82379/1494384?redirect=1&lang=zh
|
||||
- https://zenmux.ai/models
|
||||
- https://zenmux.ai/api/v1/models
|
||||
|
||||
## ark-code-latest
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"ark-code-latest"` | `"ark-code-latest"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"Ark Code Latest (Auto)"` | `"Ark Code Latest (Auto)"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `128000` | `256000` | 建议修改 | 火山引擎开发者社区《OpenClaw 接入火山 CodingPlan 实践指南》示例配置列明 `ark-code-latest` 的 `contextWindow` 为 `256000` |
|
||||
| `maxOutputTokens` | `32768` | `32000` | 建议修改 | 同一官方示例配置列明 `ark-code-latest` 的 `maxTokens` 为 `32000` |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["code","reasoning","chat"]` | `["code","reasoning","chat"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 已复核官方 Coding Plan 接入文章与火山方舟官方对话 API 页面；`ark-code-latest` 是自动路由别名，公开资料未给出该别名的固定默认 `temperature`，当前保持 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 同上；公开资料未给出 `ark-code-latest` 的固定默认 `top_p`，当前保持 `null` |
|
||||
| `extra` | (缺省) | (缺省) | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
@@ -1,129 +0,0 @@
|
||||
# 未确认字段报告 - compute/providers/volcengine.json
|
||||
|
||||
- provider: `volcengine`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## doubao-2.0-pro
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## doubao-seed-1.8
|
||||
|
||||
- `maxOutputTokens`: 已查 https://www.volcengine.com/docs/6492/2192000 与 https://www.volcengine.com/docs/82379/2123228 。当前官方 API 页明确给出 `max_completion_tokens` 取值范围 `[0, 64k]`，但公开可抓取页面仍未给 `Doubao-Seed-1.8` 的独立 `max_tokens` 上限；因此还不能确认本项目 `maxOutputTokens` 应落到回答上限还是总生成上限
|
||||
- `inputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `outputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `capabilities`: ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## doubao-seed-1.6
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## doubao-seed-1.6-thinking
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## doubao-seed-1.6-flash
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## doubao-seed-1.6-lite
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `maxOutputTokens`: 已查 https://www.volcengine.com/docs/82379/1330310 ，当前公开模型列表未直接给出 `doubao-seed-1.6-lite` 的 max output 数值
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## doubao-seed-1.6-vision
|
||||
|
||||
- `modelName`: ZenMux匹配(normalized): volcengine/doubao-seed-1-6-vision
|
||||
- `maxOutputTokens`: 已查 https://www.volcengine.com/docs/82379/1330310、https://www.volcengine.com/docs/84458/1585097 与 https://developer.volcengine.com/articles/7560657862188990514 。官方可确认 `Doubao-Seed-1.6-vision` 型号存在、支持 `256k` 输入窗口并具备 VisualCoT 能力，但当前公开可抓取页面未给该独立型号的 max output 数值
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## doubao-seed-code
|
||||
|
||||
- `inputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `outputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `capabilities`: ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## deepseek-v3.2
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `maxOutputTokens`: 已查 https://api-docs.deepseek.com/quick_start/pricing 与 https://api-docs.deepseek.com/guides/thinking_mode ，DeepSeek 官方对 V3.2 按模式给出不同口径：`deepseek-chat`（非思考）最大输出 `8K`，开启思考模式时 `max_tokens` 最大可到 `64K`；火山引擎别名 `deepseek-v3.2` 未明确说明采用哪一种固定口径
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## deepseek-r1
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## kimi-k2-volcengine
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `maxOutputTokens`: 已查 https://platform.kimi.com/docs/pricing/chat-k2 与 https://platform.kimi.com/docs/guide/kimi-k2-5-quickstart ，官方公开了 K2 系列上下文，但未给 `kimi-k2-volcengine` 独立 max output 数值
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## glm-4-7
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## doubao-embedding
|
||||
|
||||
- `modelName`: ZenMux匹配(similar): bytedance/doubao-seed-code
|
||||
- `inputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `outputPrice`: 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核
|
||||
- `capabilities`: ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## volc-mega-tts-clone
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## volc-realtime-voice
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## volc-simultaneous
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
|
||||
## volc-translation
|
||||
|
||||
- `modelName`: ZenMux无稳定匹配
|
||||
- `inputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `outputPrice`: ZenMux无稳定价格可用，需官方价格页复核
|
||||
- `extra`: 扩展字段为本地schema，需业务侧定义
|
||||
@@ -1,350 +0,0 @@
|
||||
# 详细字段取值表 - compute/providers/volcengine.json
|
||||
|
||||
- provider: `volcengine`
|
||||
- priceCurrency: `CNY`
|
||||
- generatedAt: `2026-04-23T15:11:31.654Z`
|
||||
|
||||
## 来源
|
||||
|
||||
- https://developer.volcengine.com/articles/7615528054736945158
|
||||
- https://developer.volcengine.com/articles/7517188344586403876
|
||||
- https://www.volcengine.com/docs/84458/1585097
|
||||
- https://www.volcengine.com/docs/82379/1330310
|
||||
- https://www.volcengine.com/docs/82379/2123228
|
||||
- https://www.volcengine.com/docs/6492/2192000
|
||||
- https://www.volcengine.com/docs/6492/2165115
|
||||
- https://www.volcengine.com/docs/84313/1927061
|
||||
- https://api-docs.deepseek.com/quick_start/pricing
|
||||
- https://api-docs.deepseek.com/guides/reasoning_model
|
||||
- https://platform.kimi.com/docs/pricing/chat-k2
|
||||
- https://platform.kimi.com/docs/guide/kimi-k2-5-quickstart
|
||||
- https://docs.bigmodel.cn/cn/guide/models/text/glm-4.7
|
||||
- https://zenmux.ai/models
|
||||
- https://zenmux.ai/api/v1/models
|
||||
|
||||
## doubao-2.0-pro
|
||||
|
||||
- ZenMux匹配级别: `ambiguous`
|
||||
- ZenMux候选: `bytedance/doubao-seed-2.0-pro`、`bytedance/doubao-seed-2.0-mini`、`bytedance/doubao-seed-2.0-lite`、`bytedance/doubao-seed-2.0-code`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"doubao-2.0-pro"` | `"doubao-2.0-pro"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"豆包 2.0 Pro"` | `"豆包 2.0 Pro"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `256000` | `256000` | 保持 | 火山引擎开发者社区实践文档 https://developer.volcengine.com/articles/7615528054736945158 列明 Coding Plan 中 `doubao-seed-2.0-pro` contextWindow 为 `256000`；本地别名 `doubao-2.0-pro` 可按同规格理解 |
|
||||
| `maxOutputTokens` | `128000` | `128000` | 保持 | 火山引擎开发者社区实践文档 https://developer.volcengine.com/articles/7615528054736945158 列明 Coding Plan 中 `doubao-seed-2.0-pro` maxTokens 为 `128000`；本地别名 `doubao-2.0-pro` 可按同规格理解 |
|
||||
| `inputPrice` | `3.2` | `3.2` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `16` | `16` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","multilingual","long_context","tool_use"]` | `["chat","reasoning","code","multilingual","long_context","tool_use"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | 火山引擎 AI 数据湖文本生成文档 https://www.volcengine.com/docs/6492/2165102?lang=zh 明确豆包/DeepSeek 文本生成接口 `temperature` 默认值为 `1` |
|
||||
| `defaultTopP` | `0.7` | `0.7` | 保持 | 火山引擎 AI 数据湖文本生成文档 https://www.volcengine.com/docs/6492/2165102?lang=zh 明确豆包/DeepSeek 文本生成接口 `top_p` 默认值为 `0.7` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## doubao-seed-1.8
|
||||
|
||||
- ZenMux匹配级别: `exact`
|
||||
- ZenMux命中: `bytedance/doubao-seed-1.8`
|
||||
- ZenMux候选: `bytedance/doubao-seed-1.8`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"doubao-seed-1.8"` | `"doubao-seed-1.8"` | 保持 | ZenMux匹配(exact): bytedance/doubao-seed-1.8 |
|
||||
| `displayName` | `"豆包 Seed-1.8"` | `"豆包 Seed-1.8"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `256000` | `256000` | 保持 | 火山引擎扣子模型费用页 https://www.volcengine.com/docs/84458/1585097 对 `Doubao-Seed-1.8` 列出输入长度分档 `[0,32]`、`(32,128]`、`(128,256]`，可确认该模型支持到 `256k` 输入窗口 |
|
||||
| `maxOutputTokens` | `32000` | `32000` | 待确认 | 已查 https://www.volcengine.com/docs/6492/2192000 与 https://www.volcengine.com/docs/82379/2123228 。当前官方 API 页明确给出 `max_completion_tokens` 取值范围 `[0, 64k]`，但公开可抓取页面仍未给 `Doubao-Seed-1.8` 的独立 `max_tokens` 上限；因此还不能确认本项目 `maxOutputTokens` 应落到回答上限还是总生成上限 |
|
||||
| `inputPrice` | `0.8` | `0.8` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `outputPrice` | `2` | `2` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","multilingual","long_context","tool_use"]` | `["chat","reasoning","code","multilingual","long_context","tool_use"]` | 待确认 | ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | 火山引擎 AI 数据湖文本生成文档 https://www.volcengine.com/docs/6492/2165102?lang=zh 明确豆包/DeepSeek 文本生成接口 `temperature` 默认值为 `1` |
|
||||
| `defaultTopP` | `0.7` | `0.7` | 保持 | 火山引擎 AI 数据湖文本生成文档 https://www.volcengine.com/docs/6492/2165102?lang=zh 明确豆包/DeepSeek 文本生成接口 `top_p` 默认值为 `0.7` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## doubao-seed-1.6
|
||||
|
||||
- ZenMux匹配级别: `ambiguous`
|
||||
- ZenMux候选: `volcengine/doubao-seed-1-6-vision`、`bytedance/doubao-seed-1.8`、`bytedance/doubao-seed-code`、`bytedance/doubao-seed-2.0-mini`、`bytedance/doubao-seed-2.0-lite`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"doubao-seed-1.6"` | `"doubao-seed-1.6"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"豆包 Seed-1.6"` | `"豆包 Seed-1.6"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `256000` | `256000` | 保持 | 火山引擎扣子模型费用页 https://www.volcengine.com/docs/84458/1585097 对 `Doubao-Seed-1.6` 列出输入长度分档 `[0,32]`、`(32,128]`、`(128,256]`，可确认该模型支持到 `256k` 输入窗口 |
|
||||
| `maxOutputTokens` | `16000` | `16000` | 保持 | 火山引擎官方开发者社区文章 https://developer.volcengine.com/articles/7517188344586403876 的 `不同技术参数的对比` 表列出 `Doubao-Seed-1.6` 的 `最大输出 = 16k，默认4k`；已据此将 provider JSON 回填为 `16000` |
|
||||
| `inputPrice` | `0.8` | `0.8` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `8` | `8` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","multilingual","long_context","tool_use"]` | `["chat","reasoning","code","multilingual","long_context","tool_use"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | 火山引擎 AI 数据湖文本生成文档 https://www.volcengine.com/docs/6492/2165102?lang=zh 明确豆包/DeepSeek 文本生成接口 `temperature` 默认值为 `1` |
|
||||
| `defaultTopP` | `0.7` | `0.7` | 保持 | 火山引擎 AI 数据湖文本生成文档 https://www.volcengine.com/docs/6492/2165102?lang=zh 明确豆包/DeepSeek 文本生成接口 `top_p` 默认值为 `0.7` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## doubao-seed-1.6-thinking
|
||||
|
||||
- ZenMux匹配级别: `ambiguous`
|
||||
- ZenMux候选: `volcengine/doubao-seed-1-6-vision`、`bytedance/doubao-seed-1.8`、`bytedance/doubao-seed-code`、`bytedance/doubao-seed-2.0-mini`、`bytedance/doubao-seed-2.0-lite`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"doubao-seed-1.6-thinking"` | `"doubao-seed-1.6-thinking"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"豆包 Seed-1.6 思考版"` | `"豆包 Seed-1.6 思考版"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `256000` | `256000` | 保持 | 火山引擎扣子模型费用页 https://www.volcengine.com/docs/84458/1585097 对 `Doubao-Seed-1.6` 思考相关计费项列出输入长度分档 `[0,32]`、`(32,128]`、`(128,256]`，可确认该模型支持到 `256k` 输入窗口 |
|
||||
| `maxOutputTokens` | `16000` | `16000` | 保持 | 火山引擎官方开发者社区文章 https://developer.volcengine.com/articles/7517188344586403876 的 `不同技术参数的对比` 表列出 `Doubao-Seed-1.6-thinking` 的 `最大输出 = 16k，默认4k`；已据此将 provider JSON 回填为 `16000` |
|
||||
| `inputPrice` | `0.8` | `0.8` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `8` | `8` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["reasoning","math","code","deep_thinking","long_context"]` | `["reasoning","math","code","deep_thinking","long_context"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | 火山引擎 AI 数据湖文本生成文档 https://www.volcengine.com/docs/6492/2165102?lang=zh 明确豆包/DeepSeek 文本生成接口 `temperature` 默认值为 `1`；本地思考版未见单独默认值说明，按同接口默认值处理 |
|
||||
| `defaultTopP` | `0.7` | `0.7` | 保持 | 火山引擎 AI 数据湖文本生成文档 https://www.volcengine.com/docs/6492/2165102?lang=zh 明确豆包/DeepSeek 文本生成接口 `top_p` 默认值为 `0.7`；本地思考版未见单独默认值说明，按同接口默认值处理 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## doubao-seed-1.6-flash
|
||||
|
||||
- ZenMux匹配级别: `ambiguous`
|
||||
- ZenMux候选: `volcengine/doubao-seed-1-6-vision`、`bytedance/doubao-seed-1.8`、`bytedance/doubao-seed-code`、`bytedance/doubao-seed-2.0-mini`、`bytedance/doubao-seed-2.0-lite`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"doubao-seed-1.6-flash"` | `"doubao-seed-1.6-flash"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"豆包 Seed-1.6 Flash"` | `"豆包 Seed-1.6 Flash"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `256000` | `256000` | 保持 | 火山引擎扣子模型费用页 https://www.volcengine.com/docs/84458/1585097 对 `Doubao-Seed-1.6-flash` 列出输入长度分档 `[0,32]`、`(32,128]`、`(128,256]`，可确认该模型支持到 `256k` 输入窗口 |
|
||||
| `maxOutputTokens` | `16000` | `16000` | 保持 | 火山引擎官方开发者社区文章 https://developer.volcengine.com/articles/7517188344586403876 的 `不同技术参数的对比` 表列出 `Doubao-Seed-1.6-flash` 的 `最大输出 = 16k，默认4k`；已据此将 provider JSON 回填为 `16000` |
|
||||
| `inputPrice` | `0.15` | `0.15` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `1.5` | `1.5` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","code","fast","long_context"]` | `["chat","code","fast","long_context"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | 火山引擎 AI 数据湖文本生成文档 https://www.volcengine.com/docs/6492/2165102?lang=zh 明确豆包/DeepSeek 文本生成接口 `temperature` 默认值为 `1` |
|
||||
| `defaultTopP` | `0.7` | `0.7` | 保持 | 火山引擎 AI 数据湖文本生成文档 https://www.volcengine.com/docs/6492/2165102?lang=zh 明确豆包/DeepSeek 文本生成接口 `top_p` 默认值为 `0.7` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## doubao-seed-1.6-lite
|
||||
|
||||
- ZenMux匹配级别: `ambiguous`
|
||||
- ZenMux候选: `volcengine/doubao-seed-1-6-vision`、`bytedance/doubao-seed-1.8`、`bytedance/doubao-seed-2.0-lite`、`bytedance/doubao-seed-code`、`bytedance/doubao-seed-2.0-mini`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"doubao-seed-1.6-lite"` | `"doubao-seed-1.6-lite"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"豆包 Seed-1.6 Lite"` | `"豆包 Seed-1.6 Lite"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `256000` | `256000` | 保持 | 火山引擎扣子模型费用页 https://www.volcengine.com/docs/84458/1585097 对 `Doubao-Seed-1.6-lite` 列出输入长度分档 `[0,32]`、`(32,128]`、`(128,256]`，可确认该模型支持到 `256k` 输入窗口 |
|
||||
| `maxOutputTokens` | `32000` | `32000` | 待确认 | 已查 https://www.volcengine.com/docs/82379/1330310 ，当前公开模型列表未直接给出 `doubao-seed-1.6-lite` 的 max output 数值；当前值暂保留待确认 |
|
||||
| `inputPrice` | `0.3` | `0.3` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `0.6` | `0.6` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","code","fast"]` | `["chat","code","fast"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | 火山引擎 AI 数据湖文本生成文档 https://www.volcengine.com/docs/6492/2165102?lang=zh 明确豆包/DeepSeek 文本生成接口 `temperature` 默认值为 `1` |
|
||||
| `defaultTopP` | `0.7` | `0.7` | 保持 | 火山引擎 AI 数据湖文本生成文档 https://www.volcengine.com/docs/6492/2165102?lang=zh 明确豆包/DeepSeek 文本生成接口 `top_p` 默认值为 `0.7` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## doubao-seed-1.6-vision
|
||||
|
||||
- ZenMux匹配级别: `normalized`
|
||||
- ZenMux命中: `volcengine/doubao-seed-1-6-vision`
|
||||
- ZenMux候选: `volcengine/doubao-seed-1-6-vision`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"doubao-seed-1.6-vision"` | `"doubao-seed-1-6-vision"` | 待确认 | ZenMux匹配(normalized): volcengine/doubao-seed-1-6-vision |
|
||||
| `displayName` | `"豆包 Seed-1.6 视觉版"` | `"豆包 Seed-1.6 视觉版"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["vision"]` | `["vision"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `256000` | `256000` | 保持 | 火山引擎扣子模型费用页 https://www.volcengine.com/docs/84458/1585097 对 `Doubao-Seed-1.6-vision` 列出输入长度分档 `[0,32]`、`(32,128]`、`(128,256]`，可确认该模型支持到 `256k` 输入窗口 |
|
||||
| `maxOutputTokens` | `32000` | `32000` | 待确认 | 已查 https://www.volcengine.com/docs/82379/1330310、https://www.volcengine.com/docs/84458/1585097 与 https://developer.volcengine.com/articles/7560657862188990514 。官方可确认 `Doubao-Seed-1.6-vision` 型号存在、支持 `256k` 输入窗口并具备 VisualCoT 能力，但当前公开可抓取页面未给该独立型号的 max output 数值 |
|
||||
| `inputPrice` | `0.8` | `0.8` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `8` | `8` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","vision","video_understanding","gui_agent","long_context"]` | `["chat","vision","video_understanding","gui_agent","long_context"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | 火山引擎视觉内容理解文档 https://www.volcengine.com/docs/6492/2165096 明确 `temperature` 默认值为 `1.0` |
|
||||
| `defaultTopP` | `0.7` | `0.7` | 保持 | 火山引擎视觉内容理解文档 https://www.volcengine.com/docs/6492/2165096 明确 `top_p` 默认值为 `0.7` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## doubao-seed-code
|
||||
|
||||
- ZenMux匹配级别: `exact`
|
||||
- ZenMux命中: `bytedance/doubao-seed-code`
|
||||
- ZenMux候选: `bytedance/doubao-seed-code`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"doubao-seed-code"` | `"doubao-seed-code"` | 保持 | ZenMux匹配(exact): bytedance/doubao-seed-code |
|
||||
| `displayName` | `"豆包 Seed-Code"` | `"豆包 Seed-Code"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `256000` | `256000` | 保持 | 火山方舟模型页 https://www.volcengine.com/docs/82379/1949118?lang=zh（会跳转到当前模型列表页）标注 `doubao-seed-code` 最大上下文长度为 `256k` |
|
||||
| `maxOutputTokens` | `32768` | `32768` | 保持 | 火山方舟模型页 https://www.volcengine.com/docs/82379/1949118?lang=zh 标注 `doubao-seed-code` `max_tokens` 最大为 `32k`，当前值按 `32768` 记录 |
|
||||
| `inputPrice` | `1.2` | `1.2` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `outputPrice` | `8` | `8` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `capabilities` | `["code","reasoning","long_context","deep_thinking"]` | `["code","reasoning","long_context","deep_thinking"]` | 待确认 | ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | 火山引擎 AI 数据湖文本生成文档 https://www.volcengine.com/docs/6492/2165102?lang=zh 明确豆包/DeepSeek 文本生成接口 `temperature` 默认值为 `1`；本地 `doubao-seed-code` 按同接口默认值处理 |
|
||||
| `defaultTopP` | `0.7` | `0.7` | 保持 | 火山引擎 AI 数据湖文本生成文档 https://www.volcengine.com/docs/6492/2165102?lang=zh 明确豆包/DeepSeek 文本生成接口 `top_p` 默认值为 `0.7`；本地 `doubao-seed-code` 按同接口默认值处理 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## deepseek-v3.2
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"deepseek-v3.2"` | `"deepseek-v3.2"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"DeepSeek V3.2 (火山引擎)"` | `"DeepSeek V3.2 (火山引擎)"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `128000` | `128000` | 保持 | DeepSeek 官方价格页 https://api-docs.deepseek.com/quick_start/pricing 标注 DeepSeek V3 系列上下文窗口为 `128K`；火山引擎该别名可按同规格理解 |
|
||||
| `maxOutputTokens` | `32000` | `32000` | 待确认 | 已查 https://api-docs.deepseek.com/quick_start/pricing 与 https://api-docs.deepseek.com/guides/thinking_mode ，DeepSeek 官方对 V3.2 按模式给出不同口径：`deepseek-chat`（非思考）最大输出 `8K`，开启思考模式时 `max_tokens` 最大可到 `64K`；火山引擎别名 `deepseek-v3.2` 未明确说明采用哪一种固定口径，当前值暂保留待确认 |
|
||||
| `inputPrice` | `2` | `2` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `3` | `3` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","multilingual"]` | `["chat","reasoning","code","multilingual"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | DeepSeek Chat Completions 文档 https://api-docs.deepseek.com/api/create-chat-completion 明确 `temperature` 默认值为 `1`；火山引擎 `deepseek-v3.2` 按同底模理解 |
|
||||
| `defaultTopP` | `1` | `1` | 保持 | DeepSeek Chat Completions 文档 https://api-docs.deepseek.com/api/create-chat-completion 明确 `top_p` 默认值为 `1`；火山引擎 `deepseek-v3.2` 按同底模理解 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## deepseek-r1
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"deepseek-r1"` | `"deepseek-r1"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"DeepSeek R1 (火山引擎)"` | `"DeepSeek R1 (火山引擎)"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["reasoning"]` | `["reasoning"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `128000` | `128000` | 保持 | DeepSeek 官方价格页 https://api-docs.deepseek.com/quick_start/pricing 标注 `deepseek-reasoner` 上下文窗口为 `128K`；火山引擎 `deepseek-r1` 可按同规格理解 |
|
||||
| `maxOutputTokens` | `32768` | `65536` | 建议修改 | DeepSeek 官方价格页 https://api-docs.deepseek.com/quick_start/pricing 与推理模型文档 https://api-docs.deepseek.com/guides/reasoning_model 均标注 `deepseek-reasoner` 最大输出为 `64K`；火山引擎 `deepseek-r1` 可按同规格理解 |
|
||||
| `inputPrice` | `4` | `4` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `16` | `16` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["reasoning","math","code","science","deep_thinking"]` | `["reasoning","math","code","science","deep_thinking"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | DeepSeek 推理模型文档 https://api-docs.deepseek.com/guides/reasoning_model 明确 `deepseek-reasoner` 不支持 `temperature`，即使传入也不会生效，因此按 `null` 记录 |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | DeepSeek 推理模型文档 https://api-docs.deepseek.com/guides/reasoning_model 明确 `deepseek-reasoner` 不支持 `top_p`，即使传入也不会生效，因此按 `null` 记录 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## kimi-k2-volcengine
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"kimi-k2-volcengine"` | `"kimi-k2-volcengine"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"Kimi K2 (火山引擎)"` | `"Kimi K2 (火山引擎)"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `128000` | `256000` | 建议修改 | Moonshot 官方 Kimi K2 定价页 https://platform.kimi.com/docs/pricing/chat-k2 标注 K2 系列上下文长度为 `256k`；火山引擎该别名可按同规格理解 |
|
||||
| `maxOutputTokens` | `8192` | `8192` | 待确认 | 已查 https://platform.kimi.com/docs/pricing/chat-k2 与 https://platform.kimi.com/docs/guide/kimi-k2-5-quickstart ，官方公开了 K2 系列上下文，但未给 `kimi-k2-volcengine` 独立 max output 数值；当前值暂保留待确认 |
|
||||
| `inputPrice` | `4` | `4` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `16` | `16` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","tool_use","agent","long_context"]` | `["chat","reasoning","code","tool_use","agent","long_context"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `0.6` | `0.6` | 保持 | Kimi 模型参数参考 https://platform.kimi.com/docs/api/models-overview 明确 `kimi-k2` 系列 `temperature=0.6`；火山引擎 `kimi-k2-volcengine` 按同底模理解 |
|
||||
| `defaultTopP` | `1` | `1` | 保持 | Kimi 模型参数参考 https://platform.kimi.com/docs/api/models-overview 明确 `kimi-k2` 系列 `top_p=1.0`；火山引擎 `kimi-k2-volcengine` 按同底模理解 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## glm-4-7
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"glm-4-7"` | `"glm-4-7"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"GLM-4.7 (火山引擎)"` | `"GLM-4.7 (火山引擎)"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["chat"]` | `["chat"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `200000` | `200000` | 保持 | 智谱官方 GLM-4.7 模型页 https://docs.bigmodel.cn/cn/guide/models/text/glm-4.7 列明上下文窗口为 `200K`；火山引擎该别名可按同规格理解 |
|
||||
| `maxOutputTokens` | `128000` | `128000` | 保持 | 智谱官方 GLM-4.7 模型页 https://docs.bigmodel.cn/cn/guide/models/text/glm-4.7 列明最大输出 Tokens 为 `128K`；火山引擎该别名可按同规格理解 |
|
||||
| `inputPrice` | `4` | `4` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | `16` | `16` | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["chat","reasoning","code","multilingual","deep_thinking","long_context"]` | `["chat","reasoning","code","multilingual","deep_thinking","long_context"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `1` | `1` | 保持 | 智谱对话补全文档 https://docs.bigmodel.cn/api-reference 明确 `temperature` 默认值为 `1`；火山引擎 `glm-4-7` 按官方 `glm-4.7` 同底模理解 |
|
||||
| `defaultTopP` | `0.95` | `0.95` | 保持 | 智谱对话补全文档 https://docs.bigmodel.cn/api-reference 明确 `top_p` 默认值为 `0.95`；火山引擎 `glm-4-7` 按官方 `glm-4.7` 同底模理解 |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## doubao-embedding
|
||||
|
||||
- ZenMux匹配级别: `similar`
|
||||
- ZenMux命中: `bytedance/doubao-seed-code`
|
||||
- ZenMux候选: `bytedance/doubao-seed-code`
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"doubao-embedding"` | `"doubao-seed-code"` | 待确认 | ZenMux匹配(similar): bytedance/doubao-seed-code |
|
||||
| `displayName` | `"豆包 Embedding"` | `"豆包 Embedding"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["embedding"]` | `["embedding"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `4096` | `4096` | 保持 | 火山引擎 VikingDB Embedding 文档 https://www.volcengine.com/docs/84313/1927061 标注 `doubao-embedding` 最大输入长度为 `4096` |
|
||||
| `maxOutputTokens` | `0` | `0` | 保持 | 火山引擎 Embedding 文档 https://www.volcengine.com/docs/6492/2165105 与 https://www.volcengine.com/docs/84313/1927061 说明 `doubao-embedding` 输出为向量表示，不定义 max output tokens |
|
||||
| `inputPrice` | `0.5` | `0.5` | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | 本文件币种为CNY，ZenMux价格为USD，需官方价格页复核 |
|
||||
| `capabilities` | `["text_embedding","semantic_search","rag","chinese_optimized"]` | `["text_embedding","semantic_search","rag","chinese_optimized"]` | 待确认 | ZenMux给出reasoning=true，但capabilities是项目语义字段，需官方能力说明复核 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | `doubao-embedding` 为向量模型，火山引擎 Embedding 文档 https://www.volcengine.com/docs/6492/2165105 与 https://www.volcengine.com/docs/84313/1927061 均未定义采样参数，按不适用记为 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | `doubao-embedding` 为向量模型，火山引擎 Embedding 文档 https://www.volcengine.com/docs/6492/2165105 与 https://www.volcengine.com/docs/84313/1927061 均未定义采样参数，按不适用记为 `null` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## volc-mega-tts-clone
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"volc-mega-tts-clone"` | `"volc-mega-tts-clone"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"火山声音复刻"` | `"火山声音复刻"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["voice_clone"]` | `["voice_clone"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `0` | `0` | 保持 | 火山引擎声音复刻文档 https://www.volcengine.com/docs/6348/2123111 将该能力归为声音复刻/TTS 场景，`contextWindow` 不适用 |
|
||||
| `maxOutputTokens` | `0` | `0` | 保持 | 火山引擎声音复刻文档 https://www.volcengine.com/docs/6348/2123111 将该能力归为声音复刻/TTS 场景，`maxOutputTokens` 不适用 |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["voice_clone","chinese_optimized","few_shot"]` | `["voice_clone","chinese_optimized","few_shot"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 火山引擎声音复刻文档 https://www.volcengine.com/docs/6348/2123111 将该能力归为 TTS/声音复刻服务，不存在文本采样默认值，按 `null` 记录 |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 火山引擎声音复刻文档 https://www.volcengine.com/docs/6348/2123111 将该能力归为 TTS/声音复刻服务，不存在文本采样默认值，按 `null` 记录 |
|
||||
| `extra` | `{"maxCloneSamples":3,"minCloneDuration":5}` | `{"maxCloneSamples":3,"minCloneDuration":5}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## volc-realtime-voice
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"volc-realtime-voice"` | `"volc-realtime-voice"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"火山实时语音"` | `"火山实时语音"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["realtime_voice"]` | `["realtime_voice"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `0` | `0` | 保持 | 火山引擎实时音视频文档 https://www.volcengine.com/docs/6348/1350595 将该能力归为实时语音对话能力，`contextWindow` 不适用 |
|
||||
| `maxOutputTokens` | `0` | `0` | 保持 | 火山引擎实时音视频文档 https://www.volcengine.com/docs/6348/1350595 将该能力归为实时语音对话能力，`maxOutputTokens` 不适用 |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["realtime","speech_to_speech","low_latency","chinese_optimized"]` | `["realtime","speech_to_speech","low_latency","chinese_optimized"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 火山引擎实时音视频文档 https://www.volcengine.com/docs/6348/1350595 将该能力归为实时语音对话服务，不存在文本采样默认值，按 `null` 记录 |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 火山引擎实时音视频文档 https://www.volcengine.com/docs/6348/1350595 将该能力归为实时语音对话服务，不存在文本采样默认值，按 `null` 记录 |
|
||||
| `extra` | `{"supportedModes":["speech-to-speech"],"latencyMs":200}` | `{"supportedModes":["speech-to-speech"],"latencyMs":200}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## volc-simultaneous
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"volc-simultaneous"` | `"volc-simultaneous"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"火山同声传译"` | `"火山同声传译"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["simultaneous_interpret"]` | `["simultaneous_interpret"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `0` | `0` | 保持 | 火山引擎实时语音翻译文档 https://www.volcengine.com/docs/4640/127504 将该能力归为实时翻译服务，`contextWindow` 不适用 |
|
||||
| `maxOutputTokens` | `0` | `0` | 保持 | 火山引擎实时语音翻译文档 https://www.volcengine.com/docs/4640/127504 将该能力归为实时翻译服务，`maxOutputTokens` 不适用 |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["simultaneous_interpretation","chinese_optimized","low_latency"]` | `["simultaneous_interpretation","chinese_optimized","low_latency"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 火山引擎实时语音翻译文档 https://www.volcengine.com/docs/4640/127504 将该能力归为同传服务，不存在文本采样默认值，按 `null` 记录 |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 火山引擎实时语音翻译文档 https://www.volcengine.com/docs/4640/127504 将该能力归为同传服务，不存在文本采样默认值，按 `null` 记录 |
|
||||
| `extra` | `{"streamingSupported":true}` | `{"streamingSupported":true}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
|
||||
## volc-translation
|
||||
|
||||
- ZenMux匹配级别: `none`
|
||||
- ZenMux候选: (none)
|
||||
|
||||
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|
||||
|---|---|---|---|---|
|
||||
| `modelName` | `"volc-translation"` | `"volc-translation"` | 待确认 | ZenMux无稳定匹配 |
|
||||
| `displayName` | `"火山翻译"` | `"火山翻译"` | 保持 | 展示字段，需按产品命名策略 |
|
||||
| `serviceType` | `["translation"]` | `["translation"]` | 保持 | 服务路由字段，优先本项目约定 |
|
||||
| `contextWindow` | `0` | `0` | 保持 | 火山引擎机器翻译文档 https://www.volcengine.com/docs/4640/2122636 将该能力归为翻译服务，`contextWindow` 不适用 |
|
||||
| `maxOutputTokens` | `0` | `0` | 保持 | 火山引擎机器翻译文档 https://www.volcengine.com/docs/4640/2122636 将该能力归为翻译服务，`maxOutputTokens` 不适用 |
|
||||
| `inputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `outputPrice` | (缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
|
||||
| `capabilities` | `["translation","multilingual","chinese_optimized"]` | `["translation","multilingual","chinese_optimized"]` | 保持 | ZenMux无明确能力映射差异 |
|
||||
| `defaultTemperature` | `null` | `null` | 保持 | 火山翻译属于机器翻译服务，公开文档未定义文本采样默认值，按不适用记为 `null` |
|
||||
| `defaultTopP` | `null` | `null` | 保持 | 火山翻译属于机器翻译服务，公开文档未定义文本采样默认值，按不适用记为 `null` |
|
||||
| `extra` | `{}` | `{}` | 待确认 | 扩展字段为本地schema，需业务侧定义 |
|
||||
@@ -1,36 +0,0 @@
|
||||
# volcengine ambiguous/similar 逐条处置记录（2026-04-23）
|
||||
|
||||
依据：
|
||||
- 火山引擎模型文档: https://www.volcengine.com/docs/82379
|
||||
- ZenMux: https://zenmux.ai/models
|
||||
- ZenMux API: https://zenmux.ai/api/v1/models
|
||||
|
||||
## 已处置条目
|
||||
|
||||
1. `doubao-2.0-pro`（ambiguous）
|
||||
处置：不修改。
|
||||
原因：候选为 `2.0-pro/mini/lite/code` 多 SKU，能力层级不同，无法唯一映射。
|
||||
|
||||
2. `doubao-seed-1.6`（ambiguous）
|
||||
处置：不修改。
|
||||
原因：候选混入 `1.6-vision/1.8/seed-code/2.0-*`，跨版本且跨模态。
|
||||
|
||||
3. `doubao-seed-1.6-thinking`（ambiguous）
|
||||
处置：不修改。
|
||||
原因：ZenMux 无同名 thinking 条目，候选与本地“思考版”语义不一致。
|
||||
|
||||
4. `doubao-seed-1.6-flash`（ambiguous）
|
||||
处置：不修改。
|
||||
原因：候选包含非 flash 线路，无法唯一确定。
|
||||
|
||||
5. `doubao-seed-1.6-lite`（ambiguous）
|
||||
处置：不修改。
|
||||
原因：候选同时含 `2.0-lite` 与其他分支，存在代际混淆风险。
|
||||
|
||||
6. `doubao-embedding`（similar）
|
||||
处置：不修改。
|
||||
原因：`similar` 命中 `doubao-seed-code`，服务类型冲突（embedding vs code/chat），禁止覆盖。
|
||||
|
||||
## 本轮 volcengine 落库结果
|
||||
|
||||
- JSON 变更：0
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user