GPT Image 1.5 Text to Image

Gpt Image 1.5 is OpenAI's advanced text-to-image AI model. Create photorealistic images, illustrations, and concept art from natural language descriptions with exceptional detail and prompt adherence.
API docs
openai/gpt-image-1.5

Gpt Image 1.5 is OpenAI's advanced text-to-image AI model. Create photorealistic images, illustrations, and concept art from natural language descriptions with exceptional detail and prompt adherence.

Try the model

Playground

Open playground
Input
The prompt for image generation
Output aspect ratio: 1:1 (1024x1024), 3:2 (1536x1024) or 2:3 (1024x1536). Allowed values: 1:1, 3:2, 2:3.
Advanced settings
Output format for the images Allowed values: jpeg, png.
Background for the generated image Allowed values: auto, transparent, opaque.
Quality for the generated image Allowed values: low, medium, high.
Result
Example
  1. fcd85d3c-165b-4f66-9a8e-e5a593837462.png

    What would you like to do next?

    Open original

Saved example result. No new generation was requested.

Displayed run estimate: $0.138. Final charges follow the model’s billing rules below.

Human preference

Arena

Elo ratings from blind side-by-side votes, compared with other image and video models.

Rankings sourced from Artificial Analysis Arena

Leaderboard
Text to Image
Rank
#11 of 108
Elo
1124 ±11
Gap to #1
−135

Text-to-image arena: people pick the better of two images generated from the same prompt, without seeing the model names.

  1. #6Nano Banana 2.1Google1176±12
  2. #7MAI-Image-2.6Microsoft AI1168±12
  3. #8Grok Imagine Image 2.0SpaceXAIOn SandBase1166±12
  4. #9Nano Banana 2 (Gemini 3.1 Flash Image)GoogleOn SandBase1142±10
  5. #10Muse ImageMeta1128±11
  6. #11GPT Image 1.5 (high)OpenAIThis model1124±11
  7. #12MAI-Image-2.6-FlashMicrosoft AI1122±12
  8. #13MAI-Image-2.5Microsoft AI1120±11
  9. #14Nano Banana Pro (Gemini 3 Pro Image)GoogleOn SandBase1119±10
  10. #15FLUX 3 ImageBlack Forest Labs1117±12

GPT Image 1.5 Text to Image

GPT Image 1.5 text-to-image, with transparent-background output for logos and stickers.

Fields

FieldTypeDefaultNotes
promptstring, required—Up to 32,000 characters.
aspect_ratio1:1 / 3:2 / 2:31:11:1, 3:2, or 2:3; non-square sizes cost more.
output_formatjpeg / pngpngOutput file format.
backgroundauto / transparent / opaqueautotransparent returns a PNG with alpha.
qualitylow / medium / highhighHigher quality costs more; high is the default.

Billing

Price depends on quality and shape, plus $0.005 per started 1,000 prompt characters:

Quality, short prompt1:13:2 or 2:3
low$0.014$0.018
medium$0.039$0.056
high$0.138$0.205

Failed runs are not charged.

Prompting

  • Use background: transparent with PNG output for cut-out assets.

Limits

  • Three shapes only: 1:1, 3:2, 2:3.

Also on SandBase

Related: openai/gpt-image-1.5/edit, openai/gpt-image-2 (newer).