GPT Image 1.5
Make images from a text prompt with GPT Image 1.5 by OpenAI, from 63 credits per image. See its settings, limits and exact prices.
For the complete documentation index, see llms.txt. This page is also available as Markdown.
GPT Image 1.5 is an earlier OpenAI image model that the Studio will stop listing on 2026-12-01. It works from a text prompt only. The price depends on the aspect ratio: 92 credits at 16:9 and 4:3, 63 at 1:1, and 94 at 3:4 and 9:16.
#At a glance
- Maker
- OpenAI
- Type
- Image model
- Modes
- Text to image
- Aspect ratios
- 16:9, 4:3, 1:1, 3:4, 9:16. The Studio starts on 4:3.
- Outputs per run
- 1 to 4, set with Count
- Reference image
- Not accepted. This model works from a text prompt only.
- Resolution
- No resolution choice
- Retires
- 2026-12-01
#What it costs
These are credits per image, as of 2026-10-10. The Studio shows the live quote for your settings before you generate, and the total it charges is that quote multiplied by Count.
| Aspect ratio | Credits per image |
|---|---|
| 16:9, 4:3 | 92 |
| 1:1 | 63 |
| 3:4, 9:16 | 94 |
The aspect ratio sets the price, because this model is billed by output size.
#Use it in Studio
Step 1: Open Create Image
In Studio, open Create Image. Sign in when the Studio asks, because every generation needs an account.
Step 2: Choose GPT Image 1.5
Open the model picker, which groups models by maker, and choose GPT Image 1.5.
Step 3: Write your prompt
Describe the image. GPT Image 1.5 works from text only, so there is no reference image to attach.
Step 4: Set the output
Choose an aspect ratio and Count from 1 to 4.
Step 5: Check the price and generate
The Studio shows the credit price for your settings. It is the same price the server charges. Results appear as cards and are saved to your Library.
#Limits
- Retires on 2026-12-01. From that day the Studio stops listing GPT Image 1.5.
- You need to be signed in to generate. GPT Image 1.5 is available on every plan, including Free; credits are the limit.
- No reference image. If you attach one, the Studio says "GPT Image 1.5 can't use a reference image — remove it or pick another model".
- If a generation fails, the credits are refunded. The Studio does not run a different model in its place.
#Common questions
From that date the Studio no longer lists the model in the picker. Images you already made stay in your Library. GPT Image 2 and GPT Image 2.5 are the newer OpenAI image models.
This model is billed by output size, and the ratio you pick sets the size. The 1:1 square costs 63 credits and the tall and wide ratios cost more.
No. GPT Image 1.5 works from a text prompt only. The models that accept a reference image are listed on Image models.