Image model
Ideogram
Ideogram tracks Ideogram's latest version and currently runs Ideogram 4.6, for text-to-image and edits with reliable in-image text. Presets cover 1K and 2K sizes on the model's 32-pixel grid. An edit takes one source image and up to four references.
ideogram/ideogramAPI
Call Ideogram
Every model takes the same request, so switching to Ideogram is a change to the model field. These samples are written for its own contract and send as they are.
Specifications
What Ideogram accepts
Read from the same registry the API validates against. A request outside it is refused when the task is created, before anything is charged.
Modes and inputs
- Text → Image
- Prompt only
- Image → Image
- 1 source image · required
- Up to 4 reference images
Input roles
source- The image to edit
reference- An image to take style or content from
A role goes in inputs[].as. Leave it out, or send auto, and Mynth assigns one the model accepts.
Output
- Aspect ratios
- 1:1
- 4:3
- 3:4
- 3:2
- 2:3
- 5:4
- 4:5
- 8:5
- 5:8
- 16:9
- 9:16
- 2:1
- 1:2
- 3:1
- 1:3
- 12:5
- 5:12
- 8:3
- 3:8
- 23:9
- 9:23
Leave out
size, or sendauto, and Mynth picks one for the prompt. Any other ratio snaps to the closest of these. Sizes- 4K
- No. A 4k size fails the task
Prompt
- Negative prompt
- Not supported. Dropped before the provider call, no error
The contract as GET /models returns it
{
"modes": {
"txt->img": {},
"img->img": {
"inputs": {
"rules": [
{
"type": "image",
"kind": "source",
"min": 1,
"max": 1
},
{
"type": "image",
"kind": "reference",
"max": 4
}
],
"maxTotal": 5
}
}
}
}Pricing
What it costs
Pay per result, in USD, with no subscription. A failed image or video costs nothing. How pricing works
Rates
- Image
- $0.06 / image
- Input image
- Free
Estimate a request
1 × $0.06
Held when the task is created. Only images that succeed are charged.