生成内容

curl "https://api.pipellm.ai/v1beta/models/gemini-3-flash-preview:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $PIPELLM_API_KEY" \
  -d '{
    "contents": [{"role": "user", "parts": [{"text": "你好"}]}]
  }'

import os
from google import genai

client = genai.Client(
    api_key=os.environ["PIPELLM_API_KEY"],
    http_options={"base_url": "https://api.pipellm.ai"},
)
print(client.models.generate_content(
    model="gemini-3-flash-preview",
    contents="你好",
).text)

{
  "candidates": [
    {
      "content": {},
      "finishReason": "<string>"
    }
  ],
  "usageMetadata": {}
}

POST

v1beta

models

{model}

:generateContent

curl "https://api.pipellm.ai/v1beta/models/gemini-3-flash-preview:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $PIPELLM_API_KEY" \
  -d '{
    "contents": [{"role": "user", "parts": [{"text": "你好"}]}]
  }'

import os
from google import genai

client = genai.Client(
    api_key=os.environ["PIPELLM_API_KEY"],
    http_options={"base_url": "https://api.pipellm.ai"},
)
print(client.models.generate_content(
    model="gemini-3-flash-preview",
    contents="你好",
).text)

{
  "candidates": [
    {
      "content": {},
      "finishReason": "<string>"
    }
  ],
  "usageMetadata": {}
}

Gemini 原生路径。流式请用 POST /v1beta/models/{model}:streamGenerateContent。

curl "https://api.pipellm.ai/v1beta/models/gemini-3-flash-preview:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $PIPELLM_API_KEY" \
  -d '{
    "contents": [{"role": "user", "parts": [{"text": "你好"}]}]
  }'

import os
from google import genai

client = genai.Client(
    api_key=os.environ["PIPELLM_API_KEY"],
    http_options={"base_url": "https://api.pipellm.ai"},
)
print(client.models.generate_content(
    model="gemini-3-flash-preview",
    contents="你好",
).text)

string

必填

Gemini 模型 ID，例如 gemini-3-flash-preview。

array

必填

对话轮次。

显示 contents[]

string

user 或 model。

array

必填

这一轮的内容块。

显示 parts[]

string

文本提示或模型文本。

object

内联媒体。使用 mime_type（例如 image/png）和 data（base64）。图像模型的生成结果也在这里。

object

可选采样配置。

显示 generationConfig 字段

number

采样温度。

integer

最大输出 token 数。

number

核采样。

integer

Top-k 采样。

Endpoint

POST https://api.pipellm.ai/v1beta/models/{model}:generateContent

这条 free route 只接受 Gemini 原生格式请求，并只路由到 Gemini 平台。如果你想保留 Gemini 格式去调用 OpenAI 或 Anthropic 模型，请使用 Gemini Format Converter。

安装 SDK

pip install google-genai

代码示例

cURL
Python
Node.js
Go

curl "https://api.pipellm.ai/v1beta/models/gemini-3-flash-preview:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $PIPELLM_API_KEY" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {"text": "Why is the sky blue?"}
        ]
      }
    ]
  }'

import os
from google import genai

client = genai.Client(
  api_key=os.getenv('PIPELLM_API_KEY'),
  http_options={'base_url': 'https://api.pipellm.ai'}
)

response = client.models.generate_content(
  model='gemini-3-flash-preview',
  contents='Why is the sky blue?'
)

print(response.text)

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

const ai = new GoogleGenAI({
  apiKey: process.env.PIPELLM_API_KEY,
  httpOptions: {
    baseUrl: 'https://api.pipellm.ai'
  }
});

const response = await ai.models.generateContent({
  model: 'gemini-3-flash-preview',
  contents: 'Why is the sky blue?'
});

console.log(response.text);

package main

import (
  "context"
  "os"
  "github.com/google/generative-ai-go/genai"
  "google.golang.org/api/option"
)

func main() {
  ctx := context.Background()
  client, _ := genai.NewClient(ctx,
    option.WithAPIKey(os.Getenv("PIPELLM_API_KEY")),
    option.WithEndpoint("https://api.pipellm.ai"),
  )
  defer client.Close()

  model := client.GenerativeModel("gemini-3-flash-preview")
  resp, _ := model.GenerateContent(ctx,
    genai.Text("Why is the sky blue?"),
  )
}

请求格式

{
  "contents": [
    {
      "role": "user",
      "parts": [
        {"text": "Your message here"}
      ]
    }
  ],
  "generationConfig": {
    "temperature": 0.7,
    "maxOutputTokens": 1024
  }
}

响应格式

{
  "candidates": [
    {
      "content": {
        "parts": [
          {"text": "The sky appears blue because..."}
        ],
        "role": "model"
      },
      "finishReason": "STOP"
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 10,
    "candidatesTokenCount": 50,
    "totalTokenCount": 60
  }
}

array

生成结果。

显示 candidates[]

object

role 为 model。parts 里是 text 和/或 inline_data。

string

通常是 STOP。

object

promptTokenCount、candidatesTokenCount、totalTokenCount。

错误

错误信封与错误相同。使用 x-goog-api-key。原生 Gemini 路由在请求体不是 Gemini 格式时返回 400。

400 invalid_request_error

缺少 contents、未知模型 ID，或协议不匹配。

{
  "error": {
    "type": "invalid_request_error",
    "code": "400",
    "message": "The 'model' field is required but was not provided in the request"
  }
}

401 authentication_error

缺少或无效的 x-goog-api-key。

{
  "error": {
    "type": "authentication_error",
    "code": "401",
    "message": "Incorrect API key provided. Please visit https://console.pipellm.ai/account/api-keys to find your API key."
  }
}

402 insufficient_balance

{
  "error": {
    "type": "insufficient_balance",
    "code": "402",
    "message": "Insufficient balance. Please recharge your account at https://console.pipellm.ai/billing."
  }
}

429 rate_limit_error

见速率限制。

{
  "error": {
    "type": "rate_limit_error",
    "code": "429",
    "message": "Rate limit exceeded. Your current limit is 120 requests per minute (approximately 2.00 requests per second). Please visit https://console.pipellm.ai/billing to upgrade your plan for higher limits."
  }
}

路由与协议

查看原生路由约束和 converter 路由

Gemini 概述

查看 Header、模型和路由族说明

Gemini Format Converter

保留 Gemini 格式，调用其他协议族模型

API 指南

API 参考

Endpoint

安装 SDK

代码示例

请求格式

响应格式

错误

相关文档

路由与协议

Gemini 概述

Gemini Format Converter

​Endpoint

​安装 SDK

​代码示例

​请求格式

​响应格式

​错误

​相关文档

路由与协议

Gemini 概述

Gemini Format Converter

Endpoint

安装 SDK

代码示例

请求格式

响应格式

错误

相关文档