Google · Released 2025-10-09

Nano Banana (Gemini 2.5 Flash Image)

Name: Nano Banana (Gemini 2.5 Flash Image)
Brand: Google
Price: 0.30 USD
Availability: InStock

Text → ImageImage → Image

Gemini 2.5 Flash Image (“Nano Banana”) is Google’s state-of-the-art image generation and editing model with advanced contextual understanding. It supports image creation, editing, and multi-turn conversational refinement, enabling flexible visual workflows. Developers can control image aspect ratios through the image_config API parameter.

google/gemini-2.5-flash-image

Official example

Input

Prompt

圣诞节的纽约时代广场，节日氛围浓厚！

Output

Parameters

Derived from the model input schema

Parameter	Type	Default	Description
`prompt`Required	string	—	提示词
`aspect_ratio`	string	1:1	宽高比1:1 · 3:2 · 2:3 · 3:4 · 4:3 · 4:5 …
`response_modalities`	array	IMAGE	响应模态
`image`Required	string	—	图片Url
`images`Required	array	—	图片Url数组1 – 5

API example

Submit a generation task, then poll for the result — one API key for every model.

Get API Key Get API Key

# Submit task
curl https://router-integration.test.cogfoundry.ai/api/v1/tasks/generations \
  -H "Authorization: Bearer $MODEL_CENTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google/gemini-2.5-flash-image",
  "aspect_ratio": "4:3",
  "prompt": "圣诞节的纽约时代广场，节日氛围浓厚！",
  "response_modalities": [
    "IMAGE"
  ]
}'

# Poll result（REQUEST_ID 来自上一步返回的 data.request_id）
curl https://router-integration.test.cogfoundry.ai/api/v1/tasks/generations/REQUEST_ID \
  -H "Authorization: Bearer $MODEL_CENTER_API_KEY"

import requests

BASE = "https://router-integration.test.cogfoundry.ai/api/v1"
KEY = "$MODEL_CENTER_API_KEY"
headers = {"Authorization": f"Bearer {KEY}", "Content-Type": "application/json"}

# Submit task
resp = requests.post(f"{BASE}/tasks/generations", headers=headers, data='''{
  "model": "google/gemini-2.5-flash-image",
  "aspect_ratio": "4:3",
  "prompt": "圣诞节的纽约时代广场，节日氛围浓厚！",
  "response_modalities": [
    "IMAGE"
  ]
}''')
request_id = resp.json()["data"]["request_id"]

# Poll result
result = requests.get(f"{BASE}/tasks/generations/{request_id}", headers=headers)
print(result.json())

const BASE = "https://router-integration.test.cogfoundry.ai/api/v1";
const KEY = "$MODEL_CENTER_API_KEY";
const headers = { Authorization: "Bearer " + KEY, "Content-Type": "application/json" };

// Submit task
const payload = {
  "model": "google/gemini-2.5-flash-image",
  "aspect_ratio": "4:3",
  "prompt": "圣诞节的纽约时代广场，节日氛围浓厚！",
  "response_modalities": [
    "IMAGE"
  ]
};
const resp = await fetch(BASE + "/tasks/generations", {
  method: "POST",
  headers,
  body: JSON.stringify(payload),
});
const { data } = await resp.json();

// Poll result
const result = await fetch(BASE + "/tasks/generations/" + data.request_id, { headers });
console.log(await result.json());