GPT Image 2.5 Sunburst

openai/gpt-image-2.5-sunburst

OpenAI's most capable image model, tuned for workflows where editing precision matters most. Generates and edits images from text and image input, with inpainting support. Token-based billing: text + image input tokens and image output tokens. Use it for detailed edits and demanding creative direction.

Capability tier of the GPT Image 2.5 generation; best for precise edits.

Génération d'imagesÉdition d'images

Tarification

Source : https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst · Vérifié le 2026-09-09

EntréeOfficiel $5 / M tokens

$1.5/ M tokens−3/10

SortiePrix affiché

—/ M tokens

Lecture cache $0.375/M · Écriture cache —/M

Estimer le coût

Tokens d'entréeTokens de sortie

Coût estimé$0.015

Protocoles supportés

OpenAI Chat CompletionsStatus: Non supporté—
OpenAI ResponsesStatus: Non supporté—
Anthropic MessagesStatus: Non supporté—
Google Vertex AIStatus: Non supporté—
OpenAI ImagesStatus: Disponiblehttps://api.onehop.ai/v1
OpenAI SoraStatus: Non supporté—

Essayez dans le chat playground

IDs d'appel

Utilisez l'un ou l'autre des IDs pour appeler ce modèle via l'API.

Nom OneHopopenai/gpt-image-2.5-sunburst

Tester

Remplacez le placeholder ONEHOP_KEY par votre API key. Créer →

from openai import OpenAI

client = OpenAI(
    base_url="https://api.onehop.ai/v1",
    api_key="<ONEHOP_KEY>",
)

response = client.images.generate(
    model="openai/gpt-image-2.5-sunburst",
    prompt="A red panda coding under the moonlight",
    n=1,
)
print(response.data[0].url)

base_url: https://api.onehop.ai/v1

Autres variantes de cette famille

GPT Image 2

OpenAI GPT Image 2 — high-fidelity image generation & editing.

$1.5/M↓ · —

GPT Image 2.5 Flare

OpenAI GPT Image 2.5 Flare — fastest high-quality image generation & editing.

$1.5/M↓ · —

from openai import OpenAI client = OpenAI( base_url="https://api.onehop.ai/v1", api_key="<ONEHOP_KEY>", ) response = client.images.generate( model="openai/gpt-image-2.5-sunburst", prompt="A red panda coding under the moonlight", n=1, ) print(response.data[0].url)