mirror of
https://git.openapi.site/https://github.com/desirecore/config-center.git
synced 2026-10-21 04:44:26 +08:00
feat(compute): update current model catalog (#106)
* feat(compute): update current model catalog * feat(compute): add MiMo V2.6 model profiles
This commit is contained in:
GitHub
@@ -25,6 +25,47 @@
|
||||
"reasoning"
|
||||
],
|
||||
"models": [
|
||||
{
|
||||
"modelName": "claude-opus-5-5",
|
||||
"displayName": "Claude Opus 5.5",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 128000,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"vision",
|
||||
"tool_use",
|
||||
"agent",
|
||||
"long_context"
|
||||
],
|
||||
"description": "Claude 订阅额度计费，长程智能体编程与知识工作模型，1M 上下文",
|
||||
"extra": {
|
||||
"adaptiveThinking": true,
|
||||
"reasoning": {
|
||||
"supportedEfforts": [
|
||||
"low",
|
||||
"medium",
|
||||
"high",
|
||||
"xhigh",
|
||||
"max"
|
||||
],
|
||||
"defaultEffort": "medium"
|
||||
},
|
||||
"thinkingOnly": true,
|
||||
"thinkingRoundTrip": {
|
||||
"enabled": true,
|
||||
"protocol": "anthropic-messages",
|
||||
"allowEmptySignature": false,
|
||||
"scope": "active-tool-turn"
|
||||
},
|
||||
"thinkingToolTurnValidation": "accepts-thinkless"
|
||||
},
|
||||
"source": "preset"
|
||||
},
|
||||
{
|
||||
"modelName": "claude-fable-5-1",
|
||||
"displayName": "Claude Fable 5.1",
|
||||
@@ -72,7 +113,7 @@
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "Claude 订阅额度计费，Opus 系列当前旗舰，复杂智能体编码与长程任务首选，1M 上下文",
|
||||
"description": "Claude 订阅额度计费，Opus 5 系列模型，复杂智能体编码与长程任务首选，1M 上下文",
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 128000,
|
||||
"capabilities": [
|
||||
|
||||
@@ -14,6 +14,64 @@
|
||||
"computer_use"
|
||||
],
|
||||
"models": [
|
||||
{
|
||||
"modelName": "claude-opus-5-5",
|
||||
"displayName": "Claude Opus 5.5",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "Anthropic 面向长程智能体编程与知识工作的 Opus 模型，1M 上下文，始终开启自适应思考",
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 128000,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"vision",
|
||||
"tool_use",
|
||||
"agent",
|
||||
"long_context"
|
||||
],
|
||||
"inputPrice": 4,
|
||||
"outputPrice": 20,
|
||||
"extra": {
|
||||
"thinkingRoundTrip": {
|
||||
"enabled": true,
|
||||
"protocol": "anthropic-messages",
|
||||
"allowEmptySignature": false,
|
||||
"scope": "active-tool-turn"
|
||||
},
|
||||
"thinkingToolTurnValidation": "accepts-thinkless",
|
||||
"serverSideWebSearch": {
|
||||
"enabled": true,
|
||||
"dialect": "anthropic-messages",
|
||||
"fallbackPriority": 2,
|
||||
"searchRequestPriceUsd": 0.01,
|
||||
"toolType": "web_search_20260318"
|
||||
},
|
||||
"cachePricing": {
|
||||
"write5m": 5,
|
||||
"write1h": 8,
|
||||
"read": 0.2
|
||||
},
|
||||
"promptCacheMinTokens": 512,
|
||||
"adaptiveThinking": true,
|
||||
"reasoning": {
|
||||
"supportedEfforts": [
|
||||
"low",
|
||||
"medium",
|
||||
"high",
|
||||
"xhigh",
|
||||
"max"
|
||||
],
|
||||
"defaultEffort": "medium"
|
||||
},
|
||||
"samplingParametersDeprecated": true,
|
||||
"forcedToolChoiceUnsupported": true,
|
||||
"thinkingOnly": true,
|
||||
"pricingNotes": "Prices are per 1M tokens. Full 1M context is billed at standard pricing."
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "claude-fable-5-1",
|
||||
"displayName": "Claude Fable 5.1",
|
||||
@@ -77,7 +135,7 @@
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "Anthropic Opus 系列当前旗舰，复杂智能体编码与长程任务能力显著强于 Opus 4.8，价格不变，1M 上下文",
|
||||
"description": "Anthropic Opus 5 系列模型，复杂智能体编码与长程任务能力显著强于 Opus 4.8，价格不变，1M 上下文",
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 128000,
|
||||
"capabilities": [
|
||||
@@ -170,10 +228,6 @@
|
||||
"write1h": 4,
|
||||
"read": 0.2
|
||||
},
|
||||
"introductoryPricingUntil": "2026-08-31",
|
||||
"standardPricingFrom": "2026-09-01",
|
||||
"standardInputPrice": 3,
|
||||
"standardOutputPrice": 15,
|
||||
"adaptiveThinking": true,
|
||||
"reasoning": {
|
||||
"supportedEfforts": [
|
||||
|
||||
@@ -24,6 +24,7 @@
|
||||
"translation"
|
||||
],
|
||||
"tombstones": [
|
||||
"qwen3.8-max-preview",
|
||||
"qwen3.6-plus",
|
||||
"qwen3.5-plus",
|
||||
"qwen-max",
|
||||
@@ -34,15 +35,15 @@
|
||||
],
|
||||
"models": [
|
||||
{
|
||||
"modelName": "qwen3.8-max-preview",
|
||||
"displayName": "阿里云 Qwen3.8-Max (Preview)",
|
||||
"modelName": "qwen3.8-max",
|
||||
"displayName": "阿里云 Qwen3.8-Max",
|
||||
"serviceType": [
|
||||
"chat",
|
||||
"vision"
|
||||
],
|
||||
"description": "通义千问3.8 Max 预览版，面向复杂推理与长程 Agent 任务的旗舰模型，100万上下文，支持视觉理解、内置工具和 Function Calling",
|
||||
"description": "通义千问3.8 Max 稳定版，支持视觉、视频理解和工具调用，100万上下文",
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 65536,
|
||||
"maxOutputTokens": 131072,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
@@ -51,13 +52,67 @@
|
||||
"long_context",
|
||||
"tool_use",
|
||||
"agent",
|
||||
"vision"
|
||||
"vision",
|
||||
"video_understanding"
|
||||
],
|
||||
"inputPrice": 12,
|
||||
"outputPrice": 36,
|
||||
"defaultTemperature": 0.6,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {}
|
||||
"extra": {
|
||||
"cachedInputPrice": 1.5,
|
||||
"pricingNotes": "CNY per 1M tokens, Beijing region standard price.",
|
||||
"reasoning": {
|
||||
"supportedEfforts": [
|
||||
"low",
|
||||
"medium",
|
||||
"xhigh"
|
||||
],
|
||||
"defaultEffort": "xhigh"
|
||||
},
|
||||
"preserveThinkingDefault": true,
|
||||
"thinkingMaxTokens": 262144
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "qwen3.8-flash",
|
||||
"displayName": "阿里云 Qwen3.8-Flash",
|
||||
"serviceType": [
|
||||
"chat",
|
||||
"vision"
|
||||
],
|
||||
"description": "通义千问3.8 Flash 稳定版，高速多模态推理，100万上下文",
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 131072,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"multilingual",
|
||||
"long_context",
|
||||
"tool_use",
|
||||
"agent",
|
||||
"vision",
|
||||
"video_understanding"
|
||||
],
|
||||
"inputPrice": 0.8,
|
||||
"outputPrice": 2.7,
|
||||
"defaultTemperature": 0.6,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"cachedInputPrice": 0.1,
|
||||
"pricingNotes": "CNY per 1M tokens, Beijing region standard price.",
|
||||
"reasoning": {
|
||||
"supportedEfforts": [
|
||||
"low",
|
||||
"medium",
|
||||
"xhigh"
|
||||
],
|
||||
"defaultEffort": "xhigh"
|
||||
},
|
||||
"preserveThinkingDefault": true,
|
||||
"thinkingMaxTokens": 262144
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "qwen3.7-max",
|
||||
|
||||
@@ -15,6 +15,101 @@
|
||||
"embedding"
|
||||
],
|
||||
"models": [
|
||||
{
|
||||
"modelName": "gemini-3.8-flash",
|
||||
"displayName": "Gemini 3.8 Flash",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "Google 最新稳定版 Flash，面向长程编程和智能体任务，1M 上下文",
|
||||
"contextWindow": 1048576,
|
||||
"maxOutputTokens": 65536,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"vision",
|
||||
"ultra_long_context",
|
||||
"tool_use",
|
||||
"fast"
|
||||
],
|
||||
"inputPrice": 0.75,
|
||||
"outputPrice": 3.75,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"cachePricing": {
|
||||
"inputCacheRead": 0.075
|
||||
},
|
||||
"reasoning": {
|
||||
"supportedEfforts": ["low", "medium", "high"],
|
||||
"defaultEffort": "medium"
|
||||
},
|
||||
"pricingNotes": "Standard paid tier introductory price through 2026-12-31; standard rates rise on 2027-01-01."
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "gemini-3.7-flash",
|
||||
"displayName": "Gemini 3.7 Flash",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "Google 稳定版 Flash，面向日常编程和多步工具调用，1M 上下文",
|
||||
"contextWindow": 1048576,
|
||||
"maxOutputTokens": 65536,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"vision",
|
||||
"ultra_long_context",
|
||||
"tool_use",
|
||||
"fast"
|
||||
],
|
||||
"inputPrice": 0.75,
|
||||
"outputPrice": 3.75,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"cachePricing": {
|
||||
"inputCacheRead": 0.075
|
||||
},
|
||||
"reasoning": {
|
||||
"supportedEfforts": ["low", "medium", "high"],
|
||||
"defaultEffort": "medium"
|
||||
},
|
||||
"pricingNotes": "Standard paid tier introductory price through 2026-12-31; standard rates rise on 2027-01-01."
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "gemini-3.5-flash-lite",
|
||||
"displayName": "Gemini 3.5 Flash-Lite",
|
||||
"serviceType": [
|
||||
"chat",
|
||||
"fast"
|
||||
],
|
||||
"description": "Google 低延迟轻量模型，支持多模态输入，1M 上下文",
|
||||
"contextWindow": 1048576,
|
||||
"maxOutputTokens": 65536,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"vision",
|
||||
"ultra_long_context",
|
||||
"tool_use",
|
||||
"fast"
|
||||
],
|
||||
"inputPrice": 0.3,
|
||||
"outputPrice": 2.5,
|
||||
"defaultTemperature": 1,
|
||||
"defaultTopP": 0.95,
|
||||
"extra": {
|
||||
"cachePricing": {
|
||||
"inputCacheRead": 0.03
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "gemini-3.5-flash",
|
||||
"displayName": "Gemini 3.5 Flash",
|
||||
@@ -141,7 +236,7 @@
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "Google 最新旗舰模型，1,048,576 token 上下文，多模态",
|
||||
"description": "Google Gemini 2.5 Pro，1,048,576 token 上下文，多模态",
|
||||
"contextWindow": 1048576,
|
||||
"maxOutputTokens": 65536,
|
||||
"capabilities": [
|
||||
|
||||
@@ -24,6 +24,72 @@
|
||||
"reasoning"
|
||||
],
|
||||
"models": [
|
||||
{
|
||||
"modelName": "gpt-6-sol",
|
||||
"displayName": "GPT-6 Sol",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "ChatGPT 订阅额度计费，兼顾复杂编程、智能体工作流与成本的 GPT-6 模型；1.05M 上下文",
|
||||
"contextWindow": 1050000,
|
||||
"maxOutputTokens": 128000,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"vision",
|
||||
"ultra_long_context",
|
||||
"tool_use",
|
||||
"agent"
|
||||
],
|
||||
"extra": {
|
||||
"reasoning": {
|
||||
"supportedEfforts": [
|
||||
"none",
|
||||
"low",
|
||||
"medium",
|
||||
"high",
|
||||
"xhigh",
|
||||
"max"
|
||||
],
|
||||
"defaultEffort": "medium"
|
||||
}
|
||||
},
|
||||
"source": "preset"
|
||||
},
|
||||
{
|
||||
"modelName": "gpt-6-luna",
|
||||
"displayName": "GPT-6 Luna",
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "ChatGPT 订阅额度计费，面向明确任务和高吞吐场景的 GPT-6 轻量模型；1.05M 上下文",
|
||||
"contextWindow": 1050000,
|
||||
"maxOutputTokens": 128000,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"vision",
|
||||
"ultra_long_context",
|
||||
"tool_use",
|
||||
"fast"
|
||||
],
|
||||
"extra": {
|
||||
"reasoning": {
|
||||
"supportedEfforts": [
|
||||
"none",
|
||||
"low",
|
||||
"medium",
|
||||
"high",
|
||||
"xhigh",
|
||||
"max"
|
||||
],
|
||||
"defaultEffort": "medium"
|
||||
}
|
||||
},
|
||||
"source": "preset"
|
||||
},
|
||||
{
|
||||
"modelName": "gpt-6-astra",
|
||||
"displayName": "GPT-6 Astra",
|
||||
|
||||
@@ -24,6 +24,141 @@
|
||||
"translation"
|
||||
],
|
||||
"models": [
|
||||
{
|
||||
"modelName": "gpt-image-2.5-sunburst",
|
||||
"displayName": "GPT Image 2.5 Sunburst",
|
||||
"serviceType": [
|
||||
"image_gen"
|
||||
],
|
||||
"description": "图像生成与编辑模型，适合对编辑精度要求高的任务",
|
||||
"capabilities": [
|
||||
"image_generation",
|
||||
"image_editing",
|
||||
"text_rendering",
|
||||
"vision",
|
||||
"high_quality"
|
||||
],
|
||||
"inputPrice": 5,
|
||||
"outputPrice": 30,
|
||||
"extra": {
|
||||
"imageInputPrice": 8,
|
||||
"textCachedInputPrice": 1.25,
|
||||
"imageCachedInputPrice": 2,
|
||||
"pricingNotes": "Text input $5/M tokens, image input $8/M tokens, image output $30/M tokens; quality supports low, medium, high, xhigh, max, auto."
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "gpt-image-2.5-flare",
|
||||
"displayName": "GPT Image 2.5 Flare",
|
||||
"serviceType": [
|
||||
"image_gen"
|
||||
],
|
||||
"description": "快速图像生成与编辑模型，适合日常高质量出图",
|
||||
"capabilities": [
|
||||
"image_generation",
|
||||
"image_editing",
|
||||
"text_rendering",
|
||||
"vision",
|
||||
"fast"
|
||||
],
|
||||
"inputPrice": 5,
|
||||
"outputPrice": 30,
|
||||
"extra": {
|
||||
"imageInputPrice": 8,
|
||||
"textCachedInputPrice": 1.25,
|
||||
"imageCachedInputPrice": 2,
|
||||
"pricingNotes": "Text input $5/M tokens, image input $8/M tokens, image output $30/M tokens; quality supports low, medium, high, xhigh, max, auto."
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "gpt-6-sol",
|
||||
"displayName": "GPT-6 Sol",
|
||||
"serviceType": [
|
||||
"chat",
|
||||
"responses"
|
||||
],
|
||||
"contextWindow": 1050000,
|
||||
"maxOutputTokens": 128000,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"vision",
|
||||
"ultra_long_context",
|
||||
"tool_use",
|
||||
"agent"
|
||||
],
|
||||
"description": "兼顾复杂编程、智能体工作流与成本的 GPT-6 模型；1.05M 上下文",
|
||||
"inputPrice": 2,
|
||||
"outputPrice": 10,
|
||||
"extra": {
|
||||
"serverSideWebSearch": {
|
||||
"enabled": true,
|
||||
"dialect": "openai-responses",
|
||||
"fallbackPriority": 2,
|
||||
"searchRequestPriceUsd": 0.01,
|
||||
"toolType": "web_search"
|
||||
},
|
||||
"cachedInputPrice": 0.2,
|
||||
"reasoning": {
|
||||
"supportedEfforts": [
|
||||
"none",
|
||||
"low",
|
||||
"medium",
|
||||
"high",
|
||||
"xhigh",
|
||||
"max"
|
||||
],
|
||||
"defaultEffort": "medium"
|
||||
},
|
||||
"pricingNotes": "Prices are per 1M tokens. Above 272K input tokens, input and cache rates are 2x and output rates are 1.5x for the full request. Chat Completions function calling requires reasoning_effort=none."
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "gpt-6-luna",
|
||||
"displayName": "GPT-6 Luna",
|
||||
"serviceType": [
|
||||
"chat",
|
||||
"fast",
|
||||
"responses"
|
||||
],
|
||||
"contextWindow": 1050000,
|
||||
"maxOutputTokens": 128000,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"vision",
|
||||
"ultra_long_context",
|
||||
"tool_use",
|
||||
"fast"
|
||||
],
|
||||
"description": "面向明确任务和高吞吐场景的 GPT-6 轻量模型；1.05M 上下文",
|
||||
"inputPrice": 0.1,
|
||||
"outputPrice": 0.5,
|
||||
"extra": {
|
||||
"serverSideWebSearch": {
|
||||
"enabled": true,
|
||||
"dialect": "openai-responses",
|
||||
"fallbackPriority": 3,
|
||||
"searchRequestPriceUsd": 0.01,
|
||||
"toolType": "web_search"
|
||||
},
|
||||
"cachedInputPrice": 0.01,
|
||||
"reasoning": {
|
||||
"supportedEfforts": [
|
||||
"none",
|
||||
"low",
|
||||
"medium",
|
||||
"high",
|
||||
"xhigh",
|
||||
"max"
|
||||
],
|
||||
"defaultEffort": "medium"
|
||||
},
|
||||
"pricingNotes": "Prices are per 1M tokens. Above 272K input tokens, input and cache rates are 2x and output rates are 1.5x for the full request. Chat Completions function calling requires reasoning_effort=none."
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "gpt-6-astra",
|
||||
"displayName": "GPT-6 Astra",
|
||||
@@ -68,7 +203,7 @@
|
||||
"chat",
|
||||
"responses"
|
||||
],
|
||||
"description": "OpenAI 最新前沿模型，面向复杂推理、编码和专业工作流，1M 上下文，128K 最大输出",
|
||||
"description": "OpenAI GPT-5.5 前沿模型，面向复杂推理、编码和专业工作流，1M 上下文，128K 最大输出",
|
||||
"contextWindow": 1050000,
|
||||
"maxOutputTokens": 128000,
|
||||
"capabilities": [
|
||||
@@ -294,7 +429,7 @@
|
||||
"serviceType": [
|
||||
"image_gen"
|
||||
],
|
||||
"description": "OpenAI 最新图像生成和编辑模型，支持文本输入、图像输入与图像输出",
|
||||
"description": "OpenAI GPT Image 2 图像生成和编辑模型，支持文本输入、图像输入与图像输出",
|
||||
"capabilities": [
|
||||
"image_generation",
|
||||
"image_editing",
|
||||
@@ -398,7 +533,7 @@
|
||||
"serviceType": [
|
||||
"chat"
|
||||
],
|
||||
"description": "OpenAI 最新旗舰模型，400K 上下文，编码和智能体任务优化",
|
||||
"description": "OpenAI GPT-5.2，400K 上下文，面向编码和智能体任务",
|
||||
"contextWindow": 400000,
|
||||
"maxOutputTokens": 128000,
|
||||
"capabilities": [
|
||||
|
||||
@@ -14,6 +14,40 @@
|
||||
"reasoning"
|
||||
],
|
||||
"models": [
|
||||
{
|
||||
"modelName": "grok-4.7",
|
||||
"displayName": "Grok 4.7",
|
||||
"serviceType": [
|
||||
"chat",
|
||||
"reasoning"
|
||||
],
|
||||
"description": "xAI 面向编程与智能体任务的旗舰模型，500K 上下文，支持图像输入和可配置推理",
|
||||
"contextWindow": 500000,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"vision",
|
||||
"tool_use",
|
||||
"structured_output",
|
||||
"long_context"
|
||||
],
|
||||
"inputPrice": 2,
|
||||
"outputPrice": 6,
|
||||
"extra": {
|
||||
"cachedInputPrice": 0.5,
|
||||
"reasoning": {
|
||||
"supportedEfforts": [
|
||||
"low",
|
||||
"medium",
|
||||
"high",
|
||||
"xhigh"
|
||||
],
|
||||
"defaultEffort": "high"
|
||||
},
|
||||
"pricingNotes": "Prices are per 1M tokens below 200K prompt tokens; above 200K, input and cache rates are 2x and output rates are 2x. No text output limit is documented."
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "grok-4.3",
|
||||
"displayName": "Grok 4.3",
|
||||
@@ -21,7 +55,7 @@
|
||||
"chat",
|
||||
"reasoning"
|
||||
],
|
||||
"description": "xAI 最新旗舰通用模型，1M 上下文，支持可配置推理、函数调用和结构化输出",
|
||||
"description": "xAI Grok 4.3 通用模型，1M 上下文，支持可配置推理、函数调用和结构化输出",
|
||||
"contextWindow": 1000000,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
|
||||
@@ -19,6 +19,98 @@
|
||||
"asr"
|
||||
],
|
||||
"models": [
|
||||
{
|
||||
"modelName": "mimo-v2.6-pro",
|
||||
"displayName": "MiMo-V2.6-Pro",
|
||||
"serviceType": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"vision"
|
||||
],
|
||||
"description": "小米全模态旗舰推理模型，适合复杂项目与长程智能体任务",
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 131072,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"vision",
|
||||
"audio_understanding",
|
||||
"video_understanding",
|
||||
"tool_use",
|
||||
"agent",
|
||||
"long_context"
|
||||
],
|
||||
"inputPrice": 3,
|
||||
"outputPrice": 6,
|
||||
"extra": {
|
||||
"cachedInputPrice": 0.025,
|
||||
"thinkingDefault": true,
|
||||
"pricingNotes": "CNY per 1M tokens on the Xiaomi MiMo API."
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "mimo-v2.6-flash",
|
||||
"displayName": "MiMo-V2.6-Flash",
|
||||
"serviceType": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"vision"
|
||||
],
|
||||
"description": "小米全模态高效推理模型，适合高频调用与规模化任务",
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 131072,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"vision",
|
||||
"audio_understanding",
|
||||
"video_understanding",
|
||||
"tool_use",
|
||||
"agent",
|
||||
"long_context",
|
||||
"fast"
|
||||
],
|
||||
"inputPrice": 1,
|
||||
"outputPrice": 2,
|
||||
"extra": {
|
||||
"cachedInputPrice": 0.02,
|
||||
"thinkingDefault": true,
|
||||
"pricingNotes": "CNY per 1M tokens on the Xiaomi MiMo API."
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "mimo-v2.6-pro-ultraspeed",
|
||||
"displayName": "MiMo-V2.6-Pro-UltraSpeed",
|
||||
"serviceType": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"vision"
|
||||
],
|
||||
"description": "MiMo-V2.6-Pro 的超高速服务，需向小米申请定制配额",
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 131072,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
"code",
|
||||
"vision",
|
||||
"audio_understanding",
|
||||
"video_understanding",
|
||||
"tool_use",
|
||||
"agent",
|
||||
"long_context",
|
||||
"fast"
|
||||
],
|
||||
"inputPrice": 30,
|
||||
"outputPrice": 60,
|
||||
"extra": {
|
||||
"cachedInputPrice": 0.25,
|
||||
"thinkingDefault": true,
|
||||
"pricingNotes": "CNY per 1M tokens on the Xiaomi MiMo API; UltraSpeed requires custom rate limits."
|
||||
}
|
||||
},
|
||||
{
|
||||
"modelName": "mimo-x-flash-preview",
|
||||
"displayName": "MiMo-X-Flash Preview",
|
||||
@@ -56,9 +148,9 @@
|
||||
"chat",
|
||||
"reasoning"
|
||||
],
|
||||
"description": "小米旗舰推理模型，1M 上下文，1T MoE 参数，擅长复杂 Agent、编程与长文本",
|
||||
"description": "小米 MiMo-V2.5-Pro，1M 上下文，1T MoE 参数，计划于 2026-10-21 下线",
|
||||
"contextWindow": 1000000,
|
||||
"maxOutputTokens": 65536,
|
||||
"maxOutputTokens": 131072,
|
||||
"capabilities": [
|
||||
"chat",
|
||||
"reasoning",
|
||||
|
||||
Reference in New Issue
Block a user