gpt-image-1

GPT Image 1 represents a departure from the diffusion-based approaches that defined earlier AI image generators. Built on the GPT-4o multimodal architecture, it uses an autoregressive approach to synthesize visuals directly from text and image inputs, marking a significant architectural evolution from the DALL·E series. The model is engineered to handle complex, context-aware visual generation tasks with particular strength in three areas: rendering legible, stylistically adaptable text within images; following detailed natural language instructions with precision; and producing photorealistic outputs with strong compositional control. Its multimodal design allows it to accept both text prompts and reference images, enabling sophisticated image editing and inpainting workflows.

The practical strengths of GPT Image 1 center on consistency and reliability in real-world creative applications. Unlike earlier image generation models that often required extensive prompt tweaking to achieve readable text or precise adherence to user instructions, this model delivers more dependable results with less iteration. Its integration into platforms like ChatBotKit demonstrates how the model's visual intelligence can be leveraged across different AI ecosystems, allowing it to enhance other language models for tasks like contextual image manipulation. Developers can access the model through the OpenAI API for high-fidelity image synthesis, while its ability to handle both generation and editing tasks makes it suitable for applications ranging from interface mockups and marketing assets to dynamic content creation workflows.

OpenAIgpt-image-1gpt-imagedeprecated

Open provider page Provider docs

Quick Info

Provider: OpenAI
Model key: gpt-image-1
Release date: Apr 24, 2025
Last updated: Apr 24, 2025
Input modalities
Output modalities
Capabilities

Limits

Input tokens: 0 tokens
Output tokens: 0 tokens
Context window: 0 tokens

Latest news about gpt-image-1

OpenAI

Official sourceAnnouncement

On April 23, 2025, OpenAI introduced gpt-image-1 to the API, the natively multimodal model that powered ChatGPT's image generation and had produced over 700 million images for 130 million users in its first week. The model creates images across diverse styles, follows custom guidelines, leverages world knowledge, and accurately renders text for professional-grade output. Leading partners including Adobe (Firefly and Express), Canva (Canva AI and Magic Studio), and GoDaddy (GoDaddy Airo) were already integrating gpt-image-1 for design, logo creation, and editing workflows. The API release gave developers and businesses direct access to the same image generation capabilities used inside ChatGPT, enabling integration into their own tools and platforms across creative, e-commerce, education, enterprise software, and gaming domains. Early use cases highlighted in the announcement include transforming rough sketches into graphic elements in Canva, generating editable logos with background removal in GoDaddy, and offering creators flexible aesthetic style choices through Adobe's ecosystem. The announcement positioned gpt-image-1 as unlocking practical, high-fidelity image generation for production applications.

OpenAI

Coverage

Microsoft announced GPT-image-1's arrival in Azure AI Foundry on April 23, 2025, making the OpenAI image generation model available to gated customers via API, with a playground rollout planned the following week. The post is authored by Steve Sweetman, VP of Product Management for Foundry Models, framing the launch as Azure-hosted availability for the model. The model supports text-to-image, image-to-image generation, text-driven transformation, and inpainting with user-drawn bounding boxes, and accepts uploaded images alongside text prompts. Key improvements cited over DALL-E include granular instruction following, reliable in-image text rendering, and image-input acceptance, targeting use cases such as educational materials, storybook illustration, game asset production, and UI design.

OpenAI

Official sourceDocumentation

OpenAI's developer documentation describes GPT-Image-1 as a natively multimodal language model accepting text and image inputs and producing image outputs, with a performance tier labeled "High" at the slowest speed. Pricing is token-based with text input at $5.00 per million tokens ($1.25 cached) and image input at $10.00 per million tokens ($2.50 cached), plus image output at $40.00 per million tokens. Per-image generation costs range from $0.011 (low quality, 1024×1024) up to $0.25 (high quality, 1536×1024 or 1024×1536). The model is exposed across multiple API endpoints including Image generation (v1/images/generations), Responses, Chat Completions, and Batch, with text and image input modalities and image output only; audio and video are not supported. The docs page currently labels GPT-Image-1 as "Our previous image generation model," indicating it has since been superseded in OpenAI's catalog by a newer image model. The page links to a Playground for hands-on testing of the named model.