GPT Image 2 Text to Image

GPT Image 2, OpenAI's latest image model, is capable of making fine-grained, detailed edits to images.
25% OFFopenai/gpt-image-2

GPT Image 2, OpenAI's latest image model, is capable of making fine-grained, detailed edits to images.

Try the model

Playground

Open playground
Input
The text prompt to generate an image from.
Additional Settings More

Customize your input with more control.

Quality for the generated image Allowed values: low, medium, high.
The resolution of the generated image. Leave unset to preserve the provider's standard dimensions. Allowed values: 1k, 2k, 4k.
The aspect ratio of the generated image. Allowed values: 1:1, 1:2, 2:1, 1:3, 3:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 9:21, 21:9.
The format of the generated image. Allowed values: jpeg, png, webp.
25% OFF
Result
Example
  1. c544106d-1ee3-4412-99d1-a9bcf6d233f3.png

    What would you like to do next?

    Open original

Saved example result. No new generation was requested.

Displayed run estimate: $0.165. 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
#3 of 106
Elo
1186 ±11
Gap to #1
−36

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

  1. #1GPT Image 2.5 Sunburst (max)OpenAIOn SandBase1222±10
  2. #2GPT Image 2.5 Flare (max)OpenAIOn SandBase1207±10
  3. #3GPT Image 2 (high)OpenAIThis model1186±11
  4. #4Nano Banana 2.1Google1176±12
  5. #5Grok Imagine Image 2.0SpaceXAIOn SandBase1166±12
  6. #6MAI-Image-2.6Microsoft AI1166±12
  7. #7Nano Banana 2 (Gemini 3.1 Flash Image)GoogleOn SandBase1140±10
  8. #8Muse ImageMeta1127±11
  9. #9GPT Image 1.5 (high)OpenAIOn SandBase1123±11
  10. #10MAI-Image-2.6-FlashMicrosoft AI1119±12

GPT Image 2 Text to Image

GPT Image 2 generates detailed images with strong instruction following and accurate in-image text, at three quality levels and 1K to 4K.

Fields

FieldTypeDefaultNotes
promptstring, required—Up to 50,000 characters.
qualitylow / medium / highhighHigher quality costs more; high is the default.
resolution1k / 2k / 4k—Output size tier; omit for 1K.
aspect_ratio1:1 / 1:2 / 2:1 / 1:3 / 3:1 / 2:3 / 3:2 / 3:4 / 4:3 / 4:5 / 5:4 / 9:16 / 16:9 / 9:21 / 21:91:1Output frame shape.
output_formatjpeg / png / webppngOutput file format.

Billing

Price depends on quality and resolution, per image:

Quality1k2k4k
low$0.01$0.02$0.03
medium$0.06$0.10$0.18
high (default)$0.22$0.40$0.72

Failed runs are not charged.

Prompting

  • Quote any text that must appear.
  • Draft at low, finish at high.

Limits

  • One image per request.

Also on SandBase

Other GPT Image endpoints: openai/gpt-image-2.5-sunburst, openai/gpt-image-2.5-sunburst/edit, openai/gpt-image-2.5-flare, openai/gpt-image-2.5-flare/edit, openai/gpt-image-2/edit.