config-center/compute/providers/google.json

{
  "id": "provider-google-001",
  "provider": "google",
  "label": "Google Gemini",
  "baseUrl": "https://generativelanguage.googleapis.com/v1beta",
  "apiFormat": "google-generative-ai",
  "apiKeyRef": "google",
  "apiKeyVerified": false,
  "enabled": false,
  "status": "unconfigured",
  "priceCurrency": "USD",
  "services": [
    "chat",
    "vision",
    "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",
      "serviceType": [
        "chat"
      ],
      "description": "Google Gemini 3.5 Flash 稳定版，高速多模态模型，1M 上下文",
      "contextWindow": 1048576,
      "maxOutputTokens": 65536,
      "capabilities": [
        "chat",
        "reasoning",
        "code",
        "vision",
        "ultra_long_context",
        "tool_use",
        "fast"
      ],
      "inputPrice": 1.5,
      "outputPrice": 9,
      "defaultTemperature": 1,
      "defaultTopP": 0.95,
      "extra": {
        "cachePricing": {
          "inputCacheRead": 0.75
        },
        "pricingNotes": "Standard paid tier text/image/video price; audio input uses a separate Google pricing row."
      }
    },
    {
      "modelName": "gemini-3.1-flash-lite",
      "displayName": "Gemini 3.1 Flash-Lite",
      "serviceType": [
        "fast"
      ],
      "description": "Google Gemini 3.1 Flash-Lite 稳定版，低成本高吞吐多模态模型，替代已关闭的 Preview 版本",
      "contextWindow": 1048576,
      "maxOutputTokens": 65536,
      "capabilities": [
        "chat",
        "reasoning",
        "code",
        "vision",
        "ultra_long_context",
        "tool_use",
        "fast"
      ],
      "inputPrice": 0.25,
      "outputPrice": 1.5,
      "defaultTemperature": 1,
      "defaultTopP": 0.95,
      "extra": {
        "audioInputPrice": 0.5,
        "cachePricing": {
          "inputCacheRead": 0.125,
          "audioInputCacheRead": 0.25
        }
      }
    },
    {
      "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,
      "outputPrice": 12,
      "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": 0.2,
          "inputCacheReadOver200k": 0.4,
          "storagePerMillionTokensPerHour": 4.5
        }
      }
    },
    {
      "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": 0.5,
      "outputPrice": 3,
      "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": 0.1,
          "storagePerMillionTokensPerHour": 1
        }
      }
    },
    {
      "modelName": "gemini-2.5-pro",
      "displayName": "Gemini 2.5 Pro",
      "serviceType": [
        "chat"
      ],
      "description": "Google Gemini 2.5 Pro，1,048,576 token 上下文，多模态",
      "contextWindow": 1048576,
      "maxOutputTokens": 65536,
      "capabilities": [
        "chat",
        "reasoning",
        "code",
        "vision",
        "ultra_long_context",
        "tool_use"
      ],
      "inputPrice": 1.25,
      "outputPrice": 10,
      "defaultTemperature": 1,
      "defaultTopP": 0.95,
      "extra": {}
    },
    {
      "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,
      "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": {}
    },
    {
      "modelName": "text-embedding-005",
      "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": 0.1,
      "extra": {}
    }
  ],
  "tombstones": [
    "gemini-3.1-flash-lite-preview"
  ]
}