PiAPIGénération d’imagesAI generation

OpenAI: GPT Image 2.5 (Flare / Sunburst)

piapi.image-gen.gpt-image-2-5

Generate images with GPT Image 2.5 through PiAPI's OpenAI-shaped async route, metered by quality and size.

Price: $0.161/successAu prix du fournisseur
Success rate: 100 %Last 30 days · 322 calls
Latency p50: 689 msp95 945 ms
Last verified: 14 sept. 2026Verified working

POSThttps://toolswitch.dev/v1/tools/piapi.image-gen.gpt-image-2-5Preview

Try onlineProvider docs ↗

Uses platform quota
Asynchronous response
Reads public data

Paramètres

Cet outil n’a pas de paramètres. Voir la doc du fournisseur ↗ Provider docs

Exemples de code

Remplacez $TOOLSWITCH_KEY par la clé créée dans la console.

Preview

curl -X POST 'https://toolswitch.dev/v1/tools/piapi.image-gen.gpt-image-2-5' \
  -H "X-Toolswitch-Key: $TOOLSWITCH_KEY" \
  -H "Content-Type: application/json" \
  --data-raw '{"n":1,"size":"1024x1024","model":"gpt-image-2.5-flare","prompt":"A clean editorial illustration of a paper airplane.","quality":"low"}'

import os
import json
import requests

response = requests.request(
    "POST",
    "https://toolswitch.dev/v1/tools/piapi.image-gen.gpt-image-2-5",
    headers={"X-Toolswitch-Key": os.environ["TOOLSWITCH_KEY"]},
    json=json.loads("{\"n\":1,\"size\":\"1024x1024\",\"model\":\"gpt-image-2.5-flare\",\"prompt\":\"A clean editorial illustration of a paper airplane.\",\"quality\":\"low\"}"),
)
response.raise_for_status()
print(response.text)

const response = await fetch("https://toolswitch.dev/v1/tools/piapi.image-gen.gpt-image-2-5", {
  method: "POST",
  headers: {
    "X-Toolswitch-Key": process.env.TOOLSWITCH_KEY ?? "",
    "Content-Type": "application/json",
  },
  body: JSON.stringify(JSON.parse("{\"n\":1,\"size\":\"1024x1024\",\"model\":\"gpt-image-2.5-flare\",\"prompt\":\"A clean editorial illustration of a paper airplane.\",\"quality\":\"low\"}")),
});
if (!response.ok) throw new Error(`Request failed: ${response.status}`);
console.log(await response.text());

Cette API de passerelle est en préversion ; son URL et son authentification peuvent changer. Les paramètres de l’exemple sont des données fictives. Les appels sont facturés à $0.161/success, frais de service inclus.