GPT Image 2
[Core Function] GPT Image 2 is a state-of-the-art text-to-image generation model. [Strengths] It excels at generating highly detailed, photorealistic images from text descriptions, with native support for ultra-high resolutions including 2K and 4K (up to 3840x2160). [Best For] Highly recommended for: cinematic landscapes, detailed character portraits, high-end commercial concept art, and any scenario requiring maximum resolution and visual fidelity. [Limitations] Do NOT use this model if you need a transparent background (e.g., for icons or UI assets), as it does not support the background: transparent parameter. [Routing] Use this model by default for all high-quality image generation requests. If the user explicitly asks for an image with a transparent background, route to GPT Image 1.5 instead.
Authorizations
API Key authentication. Format: Bearer YOUR_API_KEY.
Body
Request payload for GPT Image 2 generation model.
Request payload for GPT Image 2 generation model.
Image description text, supports up to 32,000 characters
1 - 32000"A children's book drawing of a veterinarian using a stethoscope to listen to the heartbeat of a baby otter"
Output size as width x height, or 'auto' for model-selected size. Presets are valid under OpenAI constraints (total pixels 655360-8294400, edges multiples of 16). Mapping: 1:1 1K/2K; 3:2 1K/2K; 2:3 1K/2K; 4:3 1K/2K; 3:4 1K/2K; 16:9 2K/4K; 9:16 2K/4K. No 1K for 16:9/9:16; no 4K for non-widescreen ratios.
auto, 1024x1024, 2048x2048, 1536x1024, 3072x2048, 1024x1536, 2048x3072, 1024x768, 2048x1536, 768x1024, 1536x2048, 2048x1152, 3840x2160, 1152x2048, 2160x3840 "1024x1024"
Image quality level. 'low': fast draft (default), 'medium': balanced, 'high': best quality
low, medium, high "high"