Skip to main content
POST
/
v1beta
/
models
/
gemini-3.1-flash-lite-image:generateContent
Text-to-image: generate an image from a text description
curl --request POST \
  --url https://api.apiyi.com/v1beta/models/gemini-3.1-flash-lite-image:generateContent \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "contents": [
    {
      "parts": [
        {
          "text": "A cute Shiba Inu sitting under cherry blossoms, watercolor style, high detail"
        }
      ]
    }
  ],
  "generationConfig": {
    "responseModalities": [
      "IMAGE"
    ],
    "imageConfig": {
      "aspectRatio": "16:9",
      "imageSize": "1K"
    }
  }
}
'
{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "inlineData": {
              "mimeType": "image/png",
              "data": "<string>"
            }
          }
        ]
      },
      "finishReason": "STOP"
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 10,
    "candidatesTokenCount": 258
  }
}
The interactive Playground on the right supports dropdown selection for parameters (aspect ratio, response type, etc.). Enter your API Key in the Authorization field (format: Bearer sk-xxx) to send test requests with one click.
Scope: This page is for text-to-image generation. Just enter a prompt — no image upload required. For editing an existing image, use the Image Editing endpoint.
🖥️ Browser Playground limitation (important)This endpoint returns a base64-encoded image (inlineData.data, typically several MB) in the response. Due to browser rendering limits, the Playground on the right may show 请求时发生错误: unable to complete request after the response arrives — the request actually succeeded; the browser just can’t render such a long base64 string.Recommended workflow (beginner-friendly):
  • Copy the Python / Node.js / cURL sample below and run it locally. The code automatically base64.b64decodes the response and writes the image to a file.
  • Nano Banana 2 Lite is focused on the 1K canvas, so the response is moderate in size, but running locally is still the safest way to save the image.

​
Code Examples

​
Python

import requests
import base64

API_KEY = "sk-your-api-key"
PROMPT = "A cute Shiba Inu sitting under cherry blossom trees, watercolor style, HD details"

response = requests.post(
    "https://api.apiyi.com/v1beta/models/gemini-3.1-flash-lite-image:generateContent",
    headers={"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"},
    json={
        "contents": [{"parts": [{"text": PROMPT}]}],
        "generationConfig": {
            "responseModalities": ["IMAGE"],
            "imageConfig": {"aspectRatio": "16:9", "imageSize": "1K"}
        }
    },
    timeout=300
).json()

img_data = response["candidates"][0]["content"]["parts"][0]["inlineData"]["data"]
with open("output.png", 'wb') as f:
    f.write(base64.b64decode(img_data))
print("Image saved to output.png")

​
cURL

curl -X POST "https://api.apiyi.com/v1beta/models/gemini-3.1-flash-lite-image:generateContent" \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{"parts": [{"text": "Futuristic city night view, neon lights, cyberpunk style"}]}],
    "generationConfig": {
      "responseModalities": ["IMAGE"],
      "imageConfig": {"aspectRatio": "16:9", "imageSize": "1K"}
    }
  }'

​
Node.js

import fs from "fs";

const API_KEY = "sk-your-api-key";

const response = await fetch(
  "https://api.apiyi.com/v1beta/models/gemini-3.1-flash-lite-image:generateContent",
  {
    method: "POST",
    headers: {
      "Authorization": `Bearer ${API_KEY}`,
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      contents: [{ parts: [{ text: "Futuristic city night view, neon lights, cyberpunk style" }] }],
      generationConfig: {
        responseModalities: ["IMAGE"],
        imageConfig: { aspectRatio: "16:9", imageSize: "1K" }
      }
    })
  }
);

const data = await response.json();
const imgBase64 = data.candidates[0].content.parts[0].inlineData.data;
fs.writeFileSync("output.png", Buffer.from(imgBase64, "base64"));

​
OpenAI-compatible mode

from openai import OpenAI

client = OpenAI(api_key="sk-your-api-key", base_url="https://api.apiyi.com/v1")

response = client.chat.completions.create(
    model="gemini-3.1-flash-lite-image",
    stream=False,
    messages=[{"role": "user", "content": "An autumn landscape painting with red leaves and birds in the distance"}]
)

print(response.choices[0].message.content)

​
Parameter Quick Reference

ParameterTypeRequiredDescription
contents[].parts[].textstringYesText prompt
generationConfig.responseModalitiesarrayYes["IMAGE"] or ["TEXT","IMAGE"]
generationConfig.imageConfig.aspectRatiostringNo14 ratios, default 1:1
generationConfig.imageConfig.imageSizestringNo1K only (Lite is focused on the 1K canvas)
See the field descriptions in the Playground on the right for detailed parameter docs, allowed values, and defaults. All enum-type fields (like aspectRatio) support dropdown selection — no manual typing needed.
Migrating from Nano Banana 2: just change the model name from gemini-3.1-flash-image to gemini-3.1-flash-lite-image; keep other parameters unchanged. Note Lite supports 1K only — if you pass 2K/4K, switch back to 1K.

Authorizations

​
Authorization
string
header
required

API Key obtained from the APIYI console

Body

application/json
​
contents
object[]
required

Content array containing the text prompt

​
generationConfig
object
required

Response

Image generated successfully

​
candidates
object[]

Array of generation results

​
usageMetadata
object