GPT Image 1.5 advances the gpt-image series with improved visual fidelity, better text rendering in images, and more accurate interpretation of complex prompts over gpt-image-1.
import { experimental_generateImage as generateImage } from 'ai';
const result = await generateImage({ model: 'openai/gpt-image-1.5', prompt: 'A red balloon on a wooden table.'});GPT Image 1.5 was released on December 16, 2025 as the successor to gpt-image-1 in OpenAI's image generation lineup. Building on gpt-image-1, it delivers improvements in visual fidelity, text rendering within images, and the model's ability to faithfully interpret complex, multi-element prompts.
Text rendering has been a persistent challenge for image generation models. GPT Image 1.5 improves this substantially, producing more legible and accurate text within generated images. This opens up use cases that require readable text overlays, signs, labels, and other textual elements in visual content.
The model also shows better compositional understanding, handling complex prompts with multiple subjects, specific spatial relationships, and detailed style instructions more accurately. For applications where visual quality and prompt fidelity are critical, it provides a meaningful step up over gpt-image-1.