例行检查

• 我已确认目前没有类似 issue
• 我已确认我已升级到最新版本
• 我已完整查看过项目 README,已确定现有版本无法满足需求
• 我理解并愿意跟进此 issue,协助测试和提供反馈
• 我理解并认可上述内容，并理解项目维护者精力有限，不遵循规则的 issue 可能会被无视或直接关闭

功能描述

官方在开放 gemini-1.5-pro-latest 的同时，也开放了 gemini-1.0-ultra-latest 的权限，希望能够支持！

应用场景

list models返回如下：

{
  "models": [
    {
      "name": "models/chat-bison-001",
      "version": "001",
      "displayName": "PaLM 2 Chat (Legacy)",
      "description": "A legacy text-only model optimized for chat conversations",
      "inputTokenLimit": 4096,
      "outputTokenLimit": 1024,
      "supportedGenerationMethods": [
        "generateMessage",
        "countMessageTokens"
      ],
      "temperature": 0.25,
      "topP": 0.95,
      "topK": 40
    },
    {
      "name": "models/text-bison-001",
      "version": "001",
      "displayName": "PaLM 2 (Legacy)",
      "description": "A legacy model that understands text and generates text as an output",
      "inputTokenLimit": 8196,
      "outputTokenLimit": 1024,
      "supportedGenerationMethods": [
        "generateText",
        "countTextTokens",
        "createTunedTextModel"
      ],
      "temperature": 0.7,
      "topP": 0.95,
      "topK": 40
    },
    {
      "name": "models/embedding-gecko-001",
      "version": "001",
      "displayName": "Embedding Gecko",
      "description": "Obtain a distributed representation of a text.",
      "inputTokenLimit": 1024,
      "outputTokenLimit": 1,
      "supportedGenerationMethods": [
        "embedText",
        "countTextTokens"
      ]
    },
    {
      "name": "models/gemini-1.0-pro",
      "version": "001",
      "displayName": "Gemini 1.0 Pro",
      "description": "The best model for scaling across a wide range of tasks",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 1
    },
    {
      "name": "models/gemini-1.0-pro-001",
      "version": "001",
      "displayName": "Gemini 1.0 Pro 001 (Tuning)",
      "description": "The best model for scaling across a wide range of tasks. This is a stable model that supports tuning.",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createTunedModel"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 1
    },
    {
      "name": "models/gemini-1.0-pro-latest",
      "version": "001",
      "displayName": "Gemini 1.0 Pro Latest",
      "description": "The best model for scaling across a wide range of tasks. This is the latest model.",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 1
    },
    {
      "name": "models/gemini-1.0-pro-vision-latest",
      "version": "001",
      "displayName": "Gemini 1.0 Pro Vision",
      "description": "The best image understanding model to handle a broad range of applications",
      "inputTokenLimit": 12288,
      "outputTokenLimit": 4096,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.4,
      "topP": 1,
      "topK": 32
    },
    {
      "name": "models/gemini-1.0-ultra-latest",
      "version": "001",
      "displayName": "Gemini 1.0 Ultra",
      "description": "The most capable model for highly complex tasks",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 32
    },
    {
      "name": "models/gemini-1.5-pro-latest",
      "version": "001",
      "displayName": "Gemini 1.5 Pro",
      "description": "Mid-size multimodal model that supports up to 1 million tokens",
      "inputTokenLimit": 1048576,
      "outputTokenLimit": 8192,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 2,
      "topP": 0.4,
      "topK": 32
    },
    {
      "name": "models/gemini-pro",
      "version": "001",
      "displayName": "Gemini 1.0 Pro",
      "description": "The best model for scaling across a wide range of tasks",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 1
    },
    {
      "name": "models/gemini-pro-vision",
      "version": "001",
      "displayName": "Gemini 1.0 Pro Vision",
      "description": "The best image understanding model to handle a broad range of applications",
      "inputTokenLimit": 12288,
      "outputTokenLimit": 4096,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.4,
      "topP": 1,
      "topK": 32
    },
    {
      "name": "models/gemini-ultra",
      "version": "001",
      "displayName": "Gemini 1.0 Ultra",
      "description": "The most capable model for highly complex tasks",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 32
    },
    {
      "name": "models/embedding-001",
      "version": "001",
      "displayName": "Embedding 001",
      "description": "Obtain a distributed representation of a text.",
      "inputTokenLimit": 2048,
      "outputTokenLimit": 1,
      "supportedGenerationMethods": [
        "embedContent"
      ]
    },
    {
      "name": "models/aqa",
      "version": "001",
      "displayName": "Model that performs Attributed Question Answering.",
      "description": "Model trained to return answers to questions that are grounded in provided sources, along with estimating answerable probability.",
      "inputTokenLimit": 7168,
      "outputTokenLimit": 1024,
      "supportedGenerationMethods": [
        "generateAnswer"
      ],
      "temperature": 0.2,
      "topP": 1,
      "topK": 40
    }
  ]
}