Generate Content

Call Google Gemini models through the Gemini native protocol. OfoxAI is compatible with the Google GenAI SDK.

Endpoint


POST https://api.ofox.ai/gemini/v1beta/models/{model}:generateContent
POST https://api.ofox.ai/gemini/v1beta/models/{model}:streamGenerateContent

Authentication

The Gemini protocol uses the x-goog-api-key header:


x-goog-api-key: <your OFOXAI_API_KEY>

Request Examples

cURL

Terminal


curl "https://api.ofox.ai/gemini/v1beta/models/google/gemini-3.1-flash-lite-preview:generateContent" \
  -H "x-goog-api-key: $OFOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "parts": [{"text": "用 Python 实现一个简单的 Web 服务器"}]
      }
    ]
  }'

Python

gemini_chat.py


from google import genai
 
client = genai.Client(
    api_key="<你的 OFOXAI_API_KEY>",
    http_options={"api_version": "v1beta", "base_url": "https://api.ofox.ai/gemini",}
)
 
response = client.models.generate_content(
    model="google/gemini-3.1-flash-lite-preview",
    contents="用 Python 实现一个简单的 Web 服务器"
)
 
print(response.text)

TypeScript

gemini_chat.ts


import { GoogleGenAI } from '@google/genai'
 
const ai = new GoogleGenAI({
  apiKey: '<你的 OFOXAI_API_KEY>',
  httpOptions: {
    apiVersion: 'v1beta',
    baseUrl: 'https://api.ofox.ai/gemini',
  }
})
 
const response = await ai.models.generateContent({
  model: 'google/gemini-3.1-flash-lite-preview',
  contents: '用 Python 实现一个简单的 Web 服务器'
})
 
console.log(response.text)

Streaming

Python

gemini_stream.py


response = client.models.generate_content_stream(
    model="google/gemini-3.1-flash-lite-preview",
    contents="写一篇关于 AI 的文章"
)
 
for chunk in response:
    print(chunk.text, end="", flush=True)

Multimodal Input

Gemini natively supports multimodal input, including images, audio, and video:


import base64
 
# Image analysis
with open("photo.jpg", "rb") as f:
    image_data = base64.b64encode(f.read()).decode()
 
response = client.models.generate_content(
    model="google/gemini-3.1-flash-lite-preview",
    contents=[
        {"text": "描述这张图片的内容"},
        {"inline_data": {"mime_type": "image/jpeg", "data": image_data}}
    ]
)

Generate & edit images

Under the Gemini native protocol, generateContent is a single endpoint that handles both image generation (text → image) and image editing (image + text → image). Recommended model: google/gemini-3.1-flash-image-preview.


POST https://api.ofox.ai/gemini/v1beta/models/google/gemini-3.1-flash-image-preview:generateContent

You can also call the same model for generation through the OpenAI-compatible endpoint, but image editing is only available via the Gemini native protocol.

Generate: text → image

Python

gen.py


from google import genai
 
client = genai.Client(
    api_key="YOUR_OFOX_API_KEY",
    http_options={"api_version": "v1beta", "base_url": "https://api.ofox.ai/gemini"},
)
 
resp = client.models.generate_content(
    model="google/gemini-3.1-flash-image-preview",
    contents="A simple red apple on a white table, photorealistic",
)
 
for part in resp.candidates[0].content.parts:
    if part.inline_data and part.inline_data.data:
        with open("output.png", "wb") as f:
            f.write(part.inline_data.data)
        break

TypeScript

gen.ts


import { GoogleGenAI } from '@google/genai'
import fs from 'node:fs'
 
const ai = new GoogleGenAI({
  apiKey: 'YOUR_OFOX_API_KEY',
  httpOptions: { apiVersion: 'v1beta', baseUrl: 'https://api.ofox.ai/gemini' },
})
 
const resp = await ai.models.generateContent({
  model: 'google/gemini-3.1-flash-image-preview',
  contents: 'A simple red apple on a white table, photorealistic',
})
 
for (const part of resp.candidates![0].content!.parts!) {
  if (part.inlineData?.data) {
    fs.writeFileSync('output.png', Buffer.from(part.inlineData.data, 'base64'))
    break
  }
}

cURL

Terminal


curl -X POST 'https://api.ofox.ai/gemini/v1beta/models/google/gemini-3.1-flash-image-preview:generateContent' \
  -H 'x-goog-api-key: YOUR_OFOX_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "contents": [
      { "parts": [{ "text": "A simple red apple on a white table, photorealistic" }] }
    ]
  }'

Sample output:

Red apple generated via the Gemini native protocol

Edit: image + text → image

Pass the source image as inlineData alongside the text instruction in parts:

Python

edit.py


from google import genai
from google.genai import types
 
client = genai.Client(
    api_key="YOUR_OFOX_API_KEY",
    http_options={"api_version": "v1beta", "base_url": "https://api.ofox.ai/gemini"},
)
 
with open("apple.png", "rb") as f:
    image_bytes = f.read()
 
resp = client.models.generate_content(
    model="google/gemini-3.1-flash-image-preview",
    contents=[
        "把苹果改成绿色，其他保持不变",
        types.Part.from_bytes(data=image_bytes, mime_type="image/png"),
    ],
)
 
for part in resp.candidates[0].content.parts:
    if part.inline_data and part.inline_data.data:
        with open("apple_edited.png", "wb") as out:
            out.write(part.inline_data.data)
        break

TypeScript

edit.ts


import { GoogleGenAI } from '@google/genai'
import fs from 'node:fs'
 
const ai = new GoogleGenAI({
  apiKey: 'YOUR_OFOX_API_KEY',
  httpOptions: { apiVersion: 'v1beta', baseUrl: 'https://api.ofox.ai/gemini' },
})
 
const imageBase64 = fs.readFileSync('apple.png').toString('base64')
 
const resp = await ai.models.generateContent({
  model: 'google/gemini-3.1-flash-image-preview',
  contents: [{
    parts: [
      { text: '把苹果改成绿色，其他保持不变' },
      { inlineData: { mimeType: 'image/png', data: imageBase64 } },
    ],
  }],
})
 
for (const part of resp.candidates![0].content!.parts!) {
  if (part.inlineData?.data) {
    fs.writeFileSync('apple_edited.png', Buffer.from(part.inlineData.data, 'base64'))
    break
  }
}

cURL

Terminal


IMG_B64=$(base64 -i apple.png)
 
curl -X POST 'https://api.ofox.ai/gemini/v1beta/models/google/gemini-3.1-flash-image-preview:generateContent' \
  -H 'x-goog-api-key: YOUR_OFOX_API_KEY' \
  -H 'Content-Type: application/json' \
  -d "{
    \"contents\": [{
      \"parts\": [
        { \"text\": \"把苹果改成绿色，其他保持不变\" },
        { \"inlineData\": { \"mimeType\": \"image/png\", \"data\": \"$IMG_B64\" } }
      ]
    }]
  }"

Before / after:

Original	Edited

Response


{
  "candidates": [{
    "content": {
      "role": "model",
      "parts": [
        { "text": "...", "thought": true },
        { "inlineData": { "mimeType": "image/png", "data": "<image Base64>" } }
      ]
    },
    "finishReason": "STOP"
  }],
  "modelVersion": "google/gemini-3.1-flash-image-preview",
  "usageMetadata": {
    "promptTokenCount": 1097,
    "candidatesTokenCount": 1120,
    "thoughtsTokenCount": 1306,
    "totalTokenCount": 3523,
    "candidatesTokensDetails": [
      { "modality": "IMAGE", "tokenCount": 1120 }
    ]
  }
}

The image is in candidates[0].content.parts[].inlineData.data as a Base64 string
parts may include several text entries with thought: true reasoning — iterate and pick out only inlineData
In usageMetadata.candidatesTokensDetails, the tokenCount for modality: IMAGE is the image-output cost

Supported Models

The table below lists common picks. For the complete list of available models, see:

Programmatic: GET /gemini/v1beta/models — query the live set of models on your account
Browse: Model Catalog — visual search with pricing

Model	Description
`google/gemini-3.1-pro-preview`	Gemini 3.1 Pro — Most capable reasoning
`google/gemini-3-pro-preview`	Gemini 3 Pro — Balanced performance
`google/gemini-3.1-flash-lite-preview`	Gemini 3 Flash — Fast and cost-effective
`google/gemini-3.1-flash-image-preview`	Gemini Flash Image — Image generation and editing

OfoxAI’s Gemini protocol supports the major features of the Google GenAI SDK, including Function Calling, Code Execution, Grounding, and image generation and editing.