Gemini 生成内容

POST

v1beta

models

{model}

{operator}

from google import genai

client = genai.Client(
    api_key="<COMETAPI_KEY>",
    http_options={"api_version": "v1beta", "base_url": "https://api.cometapi.com"},
)

response = client.models.generate_content(
    model="gemini-3-flash-preview",
    contents="Explain how AI works in a few words",
)

print(response.text)

{
  "candidates": [
    {
      "content": {
        "role": "<string>",
        "parts": [
          {
            "text": "<string>",
            "functionCall": {
              "name": "<string>",
              "args": {}
            },
            "inlineData": {
              "mimeType": "<string>",
              "data": "<string>"
            },
            "thought": true
          }
        ]
      },
      "safetyRatings": [
        {
          "category": "<string>",
          "probability": "<string>",
          "blocked": true
        }
      ],
      "citationMetadata": {
        "citationSources": [
          {
            "startIndex": 123,
            "endIndex": 123,
            "uri": "<string>",
            "license": "<string>"
          }
        ]
      },
      "tokenCount": 123,
      "avgLogprobs": 123,
      "groundingMetadata": {
        "groundingChunks": [
          {
            "web": {
              "uri": "<string>",
              "title": "<string>"
            }
          }
        ],
        "groundingSupports": [
          {
            "groundingChunkIndices": [
              123
            ],
            "confidenceScores": [
              123
            ],
            "segment": {
              "startIndex": 123,
              "endIndex": 123,
              "text": "<string>"
            }
          }
        ],
        "webSearchQueries": [
          "<string>"
        ]
      },
      "index": 123
    }
  ],
  "promptFeedback": {
    "safetyRatings": [
      {
        "category": "<string>",
        "probability": "<string>",
        "blocked": true
      }
    ]
  },
  "usageMetadata": {
    "promptTokenCount": 123,
    "candidatesTokenCount": 123,
    "totalTokenCount": 123,
    "trafficType": "<string>",
    "thoughtsTokenCount": 123,
    "promptTokensDetails": [
      {
        "modality": "<string>",
        "tokenCount": 123
      }
    ],
    "candidatesTokensDetails": [
      {
        "modality": "<string>",
        "tokenCount": 123
      }
    ]
  },
  "modelVersion": "<string>",
  "createTime": "<string>",
  "responseId": "<string>"
}

CometAPI 支持 Gemini 原生 API 格式，让你能够完整使用 Gemini 特有功能，例如思考控制、Google Search grounding、原生图像生成模态等。当你需要 OpenAI-compatible chat endpoint 无法提供的能力时，请使用此端点。

支持使用 x-goog-api-key 和 Authorization: Bearer 请求头进行身份验证。

快速开始

要通过 CometAPI 使用任何 Gemini SDK 或 HTTP 客户端，请替换 base URL 和 API key：

Setting	Google Default	CometAPI
Base URL	`generativelanguage.googleapis.com`	`api.cometapi.com`
API Key	`$GEMINI_API_KEY`	`$COMETAPI_KEY`

配置思考（推理）

Gemini 模型可以在生成响应前执行内部推理。控制方式取决于模型代际。

Gemini 3 (thinkingLevel)
Gemini 2.5 (thinkingBudget)

Gemini 3 模型使用 thinkingLevel 来控制推理深度。可用级别：MINIMAL、LOW、MEDIUM、HIGH。除非你明确需要其他 Gemini 3 变体，否则请使用 gemini-3-flash-preview 作为默认示例模型。

curl "https://api.cometapi.com/v1beta/models/gemini-3-flash-preview:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $COMETAPI_KEY" \
  -d '{
    "contents": [{"parts": [{"text": "Explain quantum physics simply."}]}],
    "generationConfig": {
      "thinkingConfig": {"thinkingLevel": "LOW"}
    }
  }'

Gemini 2.5 模型使用 thinkingBudget 进行更细粒度的 Token 级控制：

0 — 禁用思考
-1 — 动态（由模型决定，默认）
> 0 — 指定 Token 预算（例如 1024、2048）

curl "https://api.cometapi.com/v1beta/models/gemini-2.5-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $COMETAPI_KEY" \
  -d '{
    "contents": [{"parts": [{"text": "Solve this logic puzzle step by step."}]}],
    "generationConfig": {
      "thinkingConfig": {"thinkingBudget": 2048}
    }
  }'

在 Gemini 2.5 模型中使用 thinkingLevel（或在 Gemini 3 模型中使用 thinkingBudget）可能会导致错误。请为你的模型版本使用正确的参数。

流式返回响应

要在模型生成内容时接收 Server-Sent Events，请使用 streamGenerateContent?alt=sse 作为 operator。每个 SSE 事件都包含一行带有 JSON GenerateContentResponse 对象的 data:。

curl "https://api.cometapi.com/v1beta/models/gemini-3-flash-preview:streamGenerateContent?alt=sse" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $COMETAPI_KEY" \
  --no-buffer \
  -d '{
    "contents": [{"parts": [{"text": "Write a short poem about the stars"}]}]
  }'

设置系统指令

要在整个对话过程中引导模型行为，请使用 systemInstruction：

curl "https://api.cometapi.com/v1beta/models/gemini-3-flash-preview:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $COMETAPI_KEY" \
  -d '{
    "contents": [{"parts": [{"text": "What is 2+2?"}]}],
    "systemInstruction": {
      "parts": [{"text": "You are a math tutor. Always show your work."}]
    }
  }'

请求 JSON 输出

如需强制输出结构化 JSON，请设置 responseMimeType。你也可以选择提供 responseSchema 以进行严格的 schema 验证：

curl "https://api.cometapi.com/v1beta/models/gemini-3-flash-preview:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $COMETAPI_KEY" \
  -d '{
    "contents": [{"parts": [{"text": "List 3 planets with their distances from the sun"}]}],
    "generationConfig": {
      "responseMimeType": "application/json"
    }
  }'

使用 Google Search 进行 grounding

如需启用实时网页搜索，请添加一个 googleSearch 工具：

curl "https://api.cometapi.com/v1beta/models/gemini-3-flash-preview:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $COMETAPI_KEY" \
  -d '{
    "contents": [{"parts": [{"text": "Who won the euro 2024?"}]}],
    "tools": [{"google_search": {}}]
  }'

响应中会包含 groundingMetadata，其中带有来源 URL 和置信度分数。

响应示例

以下是来自 CometAPI 的 Gemini 端点的一个典型响应：

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [{"text": "Hello"}]
      },
      "finishReason": "STOP",
      "avgLogprobs": -0.0023
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 5,
    "candidatesTokenCount": 1,
    "totalTokenCount": 30,
    "trafficType": "ON_DEMAND",
    "thoughtsTokenCount": 24,
    "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 5}],
    "candidatesTokensDetails": [{"modality": "TEXT", "tokenCount": 1}]
  },
  "modelVersion": "gemini-3-flash-preview",
  "createTime": "2026-03-25T04:21:43.756483Z",
  "responseId": "CeynaY3LDtvG4_UP0qaCuQY"
}

usageMetadata 中的 thoughtsTokenCount 字段显示了模型在内部推理上消耗了多少 tokens，即使响应中不包含思考输出也是如此。

与 OpenAI 兼容端点对比

功能	Gemini 原生 (`/v1beta/models/...`)	OpenAI 兼容 (`/v1/chat/completions`)
思考控制	带有 `thinkingLevel` / `thinkingBudget` 的 `thinkingConfig`	不可用
Google Search grounding	`tools: [\{"google_search": \{\}\}]`	不可用
Google Maps grounding	`tools: [\{"googleMaps": \{\}\}]`	不可用
图像生成模态	`responseModalities: ["IMAGE"]`	不可用
认证请求头	`x-goog-api-key` 或 `Bearer`	仅 `Bearer`
响应格式	Gemini 原生（`candidates`, `parts`）	OpenAI 格式（`choices`, `message`）

授权

x-goog-api-key

string

header

必填

Your CometAPI key passed via the x-goog-api-key header. Bearer token authentication (Authorization: Bearer <key>) is also supported.

路径参数

model

string

必填

Gemini model ID. Example: gemini-3-flash-preview, gemini-2.5-pro. See the Models page for current options.

operator

enum<string>

必填

The operation to perform. Use generateContent for synchronous responses, or streamGenerateContent?alt=sse for Server-Sent Events streaming.

可用选项:

generateContent,

streamGenerateContent?alt=sse

请求体

application/json

contents

object[]

Show child attributes

systemInstruction

object

System instructions that guide the model's behavior across the entire conversation. Text only.

Show child attributes

tools

object[]

Tools the model may use to generate responses. Supports function declarations, Google Search, Google Maps, and code execution.

Show child attributes

toolConfig

object

Configuration for tool usage, such as function calling mode.

Show child attributes

safetySettings

object[]

Safety filter settings. Override default thresholds for specific harm categories.

Show child attributes

generationConfig

object

Configuration for model generation behavior including temperature, output length, and response format.

Show child attributes

cachedContent

string

The name of cached content to use as context. Format: cachedContents/{id}. See the Gemini context caching documentation for details.

响应

200 - application/json

Successful response. For streaming requests, the response is a stream of SSE events, each containing a GenerateContentResponse JSON object prefixed with data:.

candidates

object[]

The generated response candidates.

Show child attributes

promptFeedback

object

Feedback on the prompt, including safety blocking information.

Show child attributes

usageMetadata

object

Token usage statistics for the request.

Show child attributes

modelVersion

string

The model version that generated this response.

createTime

string

The timestamp when this response was created (ISO 8601 format).

responseId

string

Unique identifier for this response.

Anthropic 消息

嵌入

from google import genai

client = genai.Client(
    api_key="<COMETAPI_KEY>",
    http_options={"api_version": "v1beta", "base_url": "https://api.cometapi.com"},
)

response = client.models.generate_content(
    model="gemini-3-flash-preview",
    contents="Explain how AI works in a few words",
)

print(response.text)

{
  "candidates": [
    {
      "content": {
        "role": "<string>",
        "parts": [
          {
            "text": "<string>",
            "functionCall": {
              "name": "<string>",
              "args": {}
            },
            "inlineData": {
              "mimeType": "<string>",
              "data": "<string>"
            },
            "thought": true
          }
        ]
      },
      "safetyRatings": [
        {
          "category": "<string>",
          "probability": "<string>",
          "blocked": true
        }
      ],
      "citationMetadata": {
        "citationSources": [
          {
            "startIndex": 123,
            "endIndex": 123,
            "uri": "<string>",
            "license": "<string>"
          }
        ]
      },
      "tokenCount": 123,
      "avgLogprobs": 123,
      "groundingMetadata": {
        "groundingChunks": [
          {
            "web": {
              "uri": "<string>",
              "title": "<string>"
            }
          }
        ],
        "groundingSupports": [
          {
            "groundingChunkIndices": [
              123
            ],
            "confidenceScores": [
              123
            ],
            "segment": {
              "startIndex": 123,
              "endIndex": 123,
              "text": "<string>"
            }
          }
        ],
        "webSearchQueries": [
          "<string>"
        ]
      },
      "index": 123
    }
  ],
  "promptFeedback": {
    "safetyRatings": [
      {
        "category": "<string>",
        "probability": "<string>",
        "blocked": true
      }
    ]
  },
  "usageMetadata": {
    "promptTokenCount": 123,
    "candidatesTokenCount": 123,
    "totalTokenCount": 123,
    "trafficType": "<string>",
    "thoughtsTokenCount": 123,
    "promptTokensDetails": [
      {
        "modality": "<string>",
        "tokenCount": 123
      }
    ],
    "candidatesTokensDetails": [
      {
        "modality": "<string>",
        "tokenCount": 123
      }
    ]
  },
  "modelVersion": "<string>",
  "createTime": "<string>",
  "responseId": "<string>"
}

文本模型

图像模型

视频模型

音频模型

内容审核

API 密钥

快速开始

配置思考（推理）

流式返回响应

设置系统指令

请求 JSON 输出

使用 Google Search 进行 grounding

响应示例

与 OpenAI 兼容端点对比

授权

路径参数

请求体

响应

文本模型

图像模型

视频模型

音频模型

内容审核

API 密钥

Documentation Index

​快速开始

​配置思考（推理）

​流式返回响应

​设置系统指令

​请求 JSON 输出

​使用 Google Search 进行 grounding

​响应示例

​与 OpenAI 兼容端点对比

授权

路径参数

请求体

响应

快速开始

配置思考（推理）

流式返回响应

设置系统指令

请求 JSON 输出

使用 Google Search 进行 grounding

响应示例

与 OpenAI 兼容端点对比