Ideogram 3
Make images from a text prompt with Ideogram 3 by Ideogram, at 111 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.
Ideogram 3 is an Ideogram image model listed for text rendered inside images. It makes images from a text prompt only. The price is flat at 111 credits per image, higher than Ideogram V4 (28).
#At a glance
- Maker
- Ideogram
- 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
#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.
| Setting | Credits per image |
|---|---|
| Any aspect ratio | 111 |
The price is the same at every aspect ratio.
#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 Ideogram 3
Open the model picker, which groups models by maker, and choose Ideogram 3.
Step 3: Write your prompt
Describe the image. Ideogram 3 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
- You need to be signed in to generate. Ideogram 3 is available on every plan, including Free; credits are the limit.
- No reference image. If you attach one, the Studio says "Ideogram 3 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
The picker lists Ideogram V4, GPT Image 2 and Qwen-Image 3.0 for typography or text and layouts.
No. Ideogram 3 works from a text prompt only. The models that accept a reference image are listed on Image models.
