GPT Image 1
Neural Network
GPT Image 1 is an OpenAI model for image generation and editing via references with precise text rendering.
Max answer length
(in tokens)
Context size
(in tokens)
Prompt cost
(per 1M tokens)
Image prompt
(per 1K tokens)
How it works GPT Image 1?
GPT Image 1 is an OpenAI model that creates images from text descriptions and edits existing ones via a separate Images API. Key features include precise text rendering directly on the image, support for transparent backgrounds, and up to sixteen reference images in a single edit request, allowing you to define style and objects using examples rather than just words. In BotHub, the model is accessible from Russia without a VPN or foreign card: you pay in rubles for actual tokens used, not a subscription, and the balance does not expire. Over 250 other neural networks are available in the same window for easy switching, and a unified OpenAI-compatible API allows you to connect image generation to your service and swap models without rewriting the integration. It is useful for designers creating banners and covers with readable text, marketers for ad campaign visuals, shops for product cards on transparent backgrounds, illustrators for variations based on reference sets, and developers for streaming image generation.Frequently asked questions about GPT Image 1
You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.
gpt-image-1 is an OpenAI model for image generation: it draws an image based on a text description and can work with references, meaning it accepts images as input. Suitable for illustrations, covers, banners, concepts, social media visuals, and variations of an existing frame.
You receive a ready-to-use raster image that can be downloaded immediately. Specific dimensions and formats depend on request parameters, so we cannot promise them in advance. The prompt is limited to a 4095-token context, which is sufficient for a detailed scene description.
Our data does not indicate a separate reasoning mode for gpt-image-1: the model processes your prompt and returns an image. If a chain of thought is needed, develop the idea using a text model in the same BotHub window, then pass the final description to gpt-image-1.
Function calling and strict JSON are not indicated for gpt-image-1 in our data — the model's result is an image, not structured text. However, you can access it via the unified OpenAI-compatible BotHub API, while leaving logic and JSON handling to a text model.
Images — yes: gpt-image-1 accepts images as input, so you can work with references and edit existing frames. Audio and video as input formats are not indicated in our data, so expect to use text plus images.
The prompt language for the model is not specified in our data, so we cannot promise accuracy in Russian — please test it with your task. BotHub itself is fully Russian-language: interface, support, and payment with Russian cards, accessible from the Russian Federation without a VPN or foreign card.