openai/gpt-image-1-mini/edit

GPT Image 1 Mini is a cost-efficient, natively multimodal model that combines OpenAI's advanced language capabilities, powered by GPT-5, with efficient image generation, allowing seamless processing of both text and image inputs to produce high-quality image outputs.

Documentation

Idle

Your request will cost $0.02 per run.

For $1 you can run this model approximately 50 times.

One more thing:

ExamplesView all

Three fashionable young women in a nighttime urban scene, showcasing Y2K and streetwear aesthetics. Each has distinct styling: plaid shirt with ripped jeans, off-shoulder top with retro socks and chunky sneakers, crop top with cowboy boots and headphones. Elements like a bowling pin, lip gloss, and layered jewelry add personality. The setting is a gritty city spot with muted lighting, capturing a candid, trendy photoshoot vibe. Hyper-detailed, sharp focus, cinematic color grading, emphasizing fashion details and urban coolness.

In a dimly lit, noir-inspired room, a majestic, long-haired white Persian cat commands attention with an unexpected air of cool authority. Its ears are a delicate pink, matching the glittering pink sunglasses perched on its face, which add a playful yet bold contrast to its otherwise regal demeanor. With one paw, it firmly grips a sleek black handgun, smoke curling lazily from the barrel, while golden bullet casings are scattered across the polished wooden table before it. The dark background fades into shadow, emphasizing the cat’s fluffy white fur and the dramatic, almost cinematic tension of the scene—blending feline grace with a surprising, edgy charm that feels straight out of a retro crime thriller.

A young East Asian woman in a light - colored kimono with hydrangea patterns, wearing delicate floral hair clips, smiling softly among dense green hydrangea plants. The scene has a fresh fairy - tale style with diffused sunlight, creating a dreamy and pure atmosphere. Style: Forest fairy, gentle tone, soft focus, hydrangea wonderland.

A woman with neon - highlighted wavy brown hair, in a white cybernetically enhanced cropped sweater and black tech - infused skirt, holds a gray and white cat with glowing cybernetic patterns. The living room is transformed into a neon - lit, rain - soaked urban space with holographic ads and futuristic furniture. Neon pink and blue lights create a high - contrast, cyberpunk aesthetic with digital glitches.

A group of cyberpunk bikers, some with cybernetic limbs and glowing ocular implants, ride futuristic motorcycles with neon - glowing tires, exhausts emitting bioluminescent blue fumes, and cybernetic weapon mounts. They speed through a sprawling cyberpunk metropolis at dusk, where towering skyscrapers covered in holographic billboards are interspersed with massive, rusted industrial structures and flying drone swarms patrolling the skies. The scene is dynamic, with motion blur on the bikes, rain streaking down and reflecting the neon lights, and a mix of warm orange city lights, cool blue neon, and occasional flashes of pink from illegal street art holograms, while a rogue AI’s glitchy, multicolored data streams flicker across some building facades, creating a chaotic yet vibrantly immersive cyberpunk vibe.

A woman with cascading chestnut hair, wearing a pearl necklace and a soft ivory satin gown, poses against a dark velvet backdrop. Her expression is calm and introspective, with light illuminating her face and shoulders, highlighting the softness of her skin and the luster of her hair. Painted in the style of Sargent, with fluid, confident brushstrokes, subtle color transitions (peach blush on cheeks, warm gold in hair), and a timeless, elegant quality—capturing the essence of 19th-century portrait mastery

A woman in a form-fitting beige linen midi dress with a square neckline, wearing a large, wide-brimmed straw hat, brown peep-toe heels, and layered gold jewelry (necklace, bracelets, rings), sits on a concrete ledge by a serene body of water. She poses with one hand lifting the hat brim, the other arm gracefully extended. The background features a weathered stone wall, distant buildings on a tree-lined shore, and warm golden-hour sunlight casting dramatic shadows, creating a sophisticated, timeless fashion editorial aesthetic with a focus on bold posing and retro glamour.

Dress the model in the clothes and hat. Add a cat to the scene and change the background to a Victorian era building.

README

GPT Image 1 Mini is a cost-efficient, natively multimodal model that combines OpenAI's advanced language capabilities, powered by GPT-5, with efficient image generation, allowing seamless processing of both text and image inputs to produce high-quality image outputs.