OpenAI adds application/json support to /v1/images/edits API endpoint
OpenAI updated the /v1/images/edits endpoint to accept application/json requests in addition to multipart uploads, allowing images and optional masks to be referenced via image_url or file_id. This is a developer-facing API ergonomics improvement for GPT image models, reducing friction for integrations that prefer JSON payloads.
Related guides (2)
Related events (8)
OpenAI releases GPT Image 2 with flexible sizing, high-fidelity inputs, and Batch API support
OpenAI released GPT Image 2, a new state-of-the-art image generation and editing model available via API. The model supports flexible image sizes, high-fidelity image inputs, token-based pricing, and Batch API access at a 50% discount. The release represents an upgrade to OpenAI's image generation API offering with notable infrastructure and pricing changes.
OpenAI adds Batch API support for GPT Image model family
OpenAI has extended its Batch API to support four GPT Image models: gpt-image-1.5, chatgpt-image-latest, gpt-image-1, and gpt-image-1-mini. This enables asynchronous, cost-reduced bulk image generation requests through the API. The change is relevant for developers and enterprises running high-volume image generation workloads.
OpenAI Launches GPT-Image-1.5 via ChatGPT Images Update
OpenAI has rolled out an upgraded image generation model, GPT-Image-1.5, to all ChatGPT users and via the API. The update promises more precise edits, more consistent details, and up to 4× faster image generation compared to the previous version. The rollout is global and simultaneous across consumer and API access tiers.
OpenAI expands input_file API support to additional document, spreadsheet, and code file types
OpenAI expanded the input_file parameter in its API to accept a broader range of file types, including documents, presentations, spreadsheets, code files, and plain text. The change is a platform capability update that widens the range of file formats developers can pass directly to models via the API.
New embedding models and API updates from OpenAI
OpenAI announced new embedding models alongside API updates, expanding their developer-facing infrastructure offerings. The release likely includes updated text-embedding models with improved performance or cost characteristics. This is part of OpenAI's ongoing effort to maintain and grow its API platform for enterprise and developer use cases.
OpenAI adds image results to web search in the Responses API
OpenAI's Responses API web search tool now returns image results alongside text results. The feature targets use cases requiring web-grounded visuals such as product photos, landmarks, events, and visual references. This expands the multimodal utility of the Responses API for developers building search-augmented applications.
OpenAI Launches gpt-image-1 Image Generation Model via API
OpenAI has made its latest image generation model, gpt-image-1, available through its API for developers and businesses. The model is positioned for professional-grade, customizable visual generation integrated directly into third-party tools and platforms. This follows OpenAI's earlier consumer-facing image generation features and extends them to programmatic access.
OpenAI Upgrades Moderation API with GPT-4o-Based Multimodal Model
OpenAI has released an updated Moderation API powered by a new model built on GPT-4o, extending content moderation capabilities to both text and images. The update aims to improve accuracy in detecting harmful content, giving developers better tools for building moderation systems. This represents an expansion of OpenAI's safety infrastructure into multimodal domains.