gemini-3-pro-image-preview，同时支持 OpenAI 兼容端点。
核心能力
- 文生图 - 根据文本生成图片
- Gemini 原生 API - 使用 generateContent
- 图片输出 - 在 responseModalities 中请求 IMAGE
- 内容片段 - 使用 Gemini 多模态输入结构
输出规格
| 属性 | 取值 |
|---|---|
| 端点 | /v1/models/gemini-3-pro-image-preview:generateContent |
| 输出模态 | IMAGE |
| 响应 | Gemini content parts 中的图片数据 |
快速示例
Gemini 原生 API
- cURL
- Python
curl "https://api.mixroute.ai/v1/models/gemini-3-pro-image-preview:generateContent" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"contents": [
{
"parts": [
{
"text": "A minimal red circle centered on a white background"
}
]
}
],
"generationConfig": {
"responseModalities": [
"TEXT",
"IMAGE"
]
}
}'
import requests
response = requests.post(
"https://api.mixroute.ai/v1/models/gemini-3-pro-image-preview:generateContent",
headers={"Authorization": "Bearer YOUR_API_KEY"},
json={'contents': [{'parts': [{'text': 'A minimal red circle centered on a white '
'background'}]}],
'generationConfig': {'responseModalities': ['TEXT', 'IMAGE']}},
)
print(response.json())
OpenAI 兼容 API
- cURL
- Python
- Streaming
curl "https://api.mixroute.ai/v1/chat/completions" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3-pro-image-preview",
"messages": [
{
"role": "user",
"content": "Explain quantum entanglement in simple terms."
}
],
"max_tokens": 256
}'
from openai import OpenAI
client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.mixroute.ai/v1")
response = client.chat.completions.create(
model="gemini-3-pro-image-preview",
messages=[{"role": "user", "content": "Explain quantum entanglement in simple terms."}],
max_tokens=256,
)
print(response.choices[0].message.content)
from openai import OpenAI
client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.mixroute.ai/v1")
stream = client.chat.completions.create(
model="gemini-3-pro-image-preview",
messages=[{"role": "user", "content": "Write a short poem about the sea."}],
max_tokens=256,
stream=True,
)
for chunk in stream:
print(chunk.choices[0].delta.content or "", end="")
参数
| 参数 | 类型 | 必填 | 说明 |
|---|---|---|---|
contents | array | 是 | 提示词与可选多模态内容片段。 |
generationConfig.responseModalities | array | 是 | 包含 IMAGE 以请求图片输出。 |
generationConfig | object | 否 | 其他生成参数。 |