Google Gemini SDK 接入 GPUShare

适用场景: 已经在用 Google genai SDK 的项目可直接切换 base URL,代码零改动。也可以用 Gemini SDK 调用非 Gemini 模型 (Claude / GLM / Grok / DeepSeek 等)。

端点

项	值
Base URL	`https://api.dflop.top`
端点	`/v1beta/models/{model}:generateContent` (兼容 Gemini Native API)
流式端点	`/v1beta/models/{model}:streamGenerateContent`
鉴权	`?key=sk-gpushare-xxx` 或 `x-api-key: sk-gpushare-xxx` (SDK 自动用 key=)
协议	Google Generative AI Native (HTTP / SSE 流式)

安装

pip install google-genai     # Python
npm install @google/genai    # TypeScript

Google 在 2024-2025 把 SDK 从 google-generativeai 切到了新的 google-genai。本文档用新 SDK。

Python

基础调用

from google import genai

client = genai.Client(
    api_key="sk-gpushare-xxx",
    http_options={"base_url": "https://api.dflop.top"},
)

response = client.models.generate_content(
    model="gemini-2.5-pro",
    contents="Say hello in one word.",
)
print(response.text)

流式输出

stream = client.models.generate_content_stream(
    model="gemini-2.5-pro",
    contents="Stream a haiku about latency",
)
for chunk in stream:
    print(chunk.text, end="", flush=True)

跨厂商调用 (重点)

Gemini SDK 可以调用任何支持 Gemini Native 协议的模型 —— 不只是 Gemini:

# 用 Gemini SDK 调 Claude
response = client.models.generate_content(
    model="claude-sonnet-4-5-20250929",
    contents="Hello",
)

# 调 GLM
response = client.models.generate_content(
    model="glm-5.1",
    contents="Hello",
)

# 调 Grok
response = client.models.generate_content(
    model="grok-4-fast-reasoning",
    contents="Hello",
)

# 调 DeepSeek
response = client.models.generate_content(
    model="deepseek-v3.2",
    contents="Hello",
)

多模态 (图像输入)

from google.genai import types

with open("photo.jpg", "rb") as f:
    image_bytes = f.read()

response = client.models.generate_content(
    model="gemini-2.5-pro",
    contents=[
        types.Part.from_bytes(data=image_bytes, mime_type="image/jpeg"),
        "Describe this image",
    ],
)
print(response.text)

System Instruction

response = client.models.generate_content(
    model="gemini-3-pro-preview",
    config=types.GenerateContentConfig(
        system_instruction="You are a terse expert. Answer in one sentence.",
    ),
    contents="Why is the sky blue?",
)
print(response.text)

TypeScript

基础调用

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({
  apiKey: process.env.GPUSHARE_API_KEY,
  httpOptions: { baseUrl: "https://api.dflop.top" },
});

const response = await client.models.generateContent({
  model: "gemini-2.5-pro",
  contents: "Say hello in one word.",
});

console.log(response.text);

流式输出

const stream = await client.models.generateContentStream({
  model: "gemini-2.5-pro",
  contents: "Stream a haiku",
});

for await (const chunk of stream) {
  process.stdout.write(chunk.text ?? "");
}

跨厂商调用

// 用 Gemini SDK 调 Claude
await client.models.generateContent({
  model: "claude-opus-4-5-20251101",
  contents: "Hello",
});

// 调 GLM
await client.models.generateContent({
  model: "glm-4.7",
  contents: "Hello",
});

curl

非流式

curl "https://api.dflop.top/v1beta/models/gemini-2.5-pro:generateContent?key=$GPUSHARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {"parts": [{"text": "Say hello in one word."}]}
    ]
  }'

流式

curl "https://api.dflop.top/v1beta/models/gemini-2.5-pro:streamGenerateContent?key=$GPUSHARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {"parts": [{"text": "Stream a haiku"}]}
    ]
  }' \
  --no-buffer

跨厂商 (curl 调 Claude)

curl "https://api.dflop.top/v1beta/models/claude-sonnet-4-5-20250929:generateContent?key=$GPUSHARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {"parts": [{"text": "Hello"}]}
    ]
  }'

注意事项

URL 模型占位 {model} —— SDK 自动从 model 参数填,curl 直调时手动替换路径
:generateContent vs :streamGenerateContent —— SDK 根据 generate_content vs generate_content_stream 自动切换
Key 鉴权 —— SDK 默认走 ?key= query param;x-api-key header 也可用 (三回退)
错误格式 统一返回 Gemini 风格: {"error": {"code": 400, "message": "...", "status": "INVALID_ARGUMENT"}}
不支持组合:
- GPT-5.x (gpt-5.4, gpt-5.5) 暂不支持 Gemini Native 端点 (sub2api 上游限制)
- 调 GPT-5.x 请改用 OpenAI Chat 或 Anthropic Messages 端点
配额耗尽 返回 HTTP 412 + Gemini 风格错误对象

完整模型列表

支持 Gemini Native 的所有模型(除 GPT-5.x):

厂商	模型
Google	`gemini-2.5-flash`, `gemini-2.5-pro`, `gemini-3-flash-preview`, `gemini-3-pro-preview` (原生直通)
Anthropic	`claude-opus-4-5-20251101`, `claude-sonnet-4-5-20250929`
xAI	`grok-4`, `grok-4.1`, `grok-4.2`, `grok-4-fast-reasoning`, `grok-4-fast-non-reasoning`
智谱	`glm-4.5`/`-air`/`-airx`/`-flash`/`-x`, `glm-4.6`, `glm-4.7`, `glm-5`, `glm-5-turbo`, `glm-5.1`
DeepSeek	`deepseek-v3.1`, `deepseek-v3.2`, `deepseek-v4-flash`, `deepseek-v4-pro`
Moonshot	`kimi-k2.5`, `kimi-k2.6`
MiniMax	`MiniMax-M2.5`, `MiniMax-M2.7`
Alibaba	`qwen3.5-plus`, `qwen3.6-plus`

完整矩阵: 兼容矩阵