import base64
import requests
API_KEY = "<YOUR_API_KEY>"
MODEL = "gemini-2.5-flash-image" # or the provider’s exact model name
ENDPOINT = "(MODEL)
# Load an image into base64
with open("./sample.jpg", "rb") as f:
 image_b64 = base64.b64encode(f.read).decode("utf-8")
payload = {
 "contents": [{
 "role": "user",
 "parts": [
 {"text": "Describe this image in one sentence, then list three key details."},
 {
 "inline_data": {
 "mime_type": "image/jpeg",
 "data": image_b64
 }
 }
 ]
 }],
 "generationConfig": {
 "temperature": 0.4,
 "maxOutputTokens": 300
 }
}
resp = requests.post(f"{ENDPOINT}?key={API_KEY}", json=payload)
resp.raise_for_status
print(resp.json["candidates"][0]["content"]["parts"][0]["text"]) 

payload = {
 "contents": [{
 "role": "user",
 "parts": [
 {"text": "Add a subtle label 'Sample' in the top-right corner."},
 {"inline_data": {"mime_type": "image/png", "data": image_b64}}
 ]
 }],
 "generationConfig": {"temperature": 0.3, "maxOutputTokens": 0},
 "tools": [{"imageEdit": {"strength": 0.25}}]
}

from fastapi import FastAPI, UploadFile, File
import base64, requests, os
app = FastAPI
API_KEY = os.getenv("API_KEY")
MODEL = "gemini-2.5-flash-image"
ENDPOINT = f"("/caption")
async def caption(file: UploadFile = File:
 b = await file.read
 b64 = base64.b64encode(b).decode("utf-8")
 payload = {
 "contents": [{
 "role": "user",
 "parts": [
 {"text": "Return concise JSON with fields: caption, objects[]."},
 {"inline_data": {"mime_type": file.content_type, "data": b64}}
 ]
 }],
 "generationConfig": {"temperature": 0.2, "maxOutputTokens": 200}
 }
 r = requests.post(f"{ENDPOINT}?key={API_KEY}", json=payload, timeout=30)
 r.raise_for_status
 return r.json