Model API

Ideogram V3

Generate high-quality images, posters, and logos with Ideogram V3. Features exceptional typography handling and realistic outputs optimized for commercial and creative use.

Model id

Use this in every request

ideogram/v3

This model has other modes with their own ids: ideogram/v3/edit, ideogram/v3/remix, ideogram/v3/replace-background, ideogram/v3/generate-transparent.

Run it

Quote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.

# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "ideogram/v3",
  "input": {
    "prompt": "A red ceramic cup on a wooden table, soft morning light"
  }
}'

# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"model": "ideogram/v3", "quote_id": "QUOTE_ID", "input": {"prompt":"A red ceramic cup on a wooden table, soft morning light"}}'

# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
  -H "Authorization: Bearer $RAYWAKE_API_KEY"

Input

Input fields for ideogram/v3
Name	Type	Description
`image_urls`	array of image URLs	A set of images to use as style references (maximum total size 10MB across all style references). The images should be in JPEG, PNG or WebP format
`rendering_speed`	string (enum)	The rendering speed to use. Default: `BALANCED` One of: `TURBO`, `BALANCED`, `QUALITY`
`style_codes`	array of strings	A list of 8 character hexadecimal codes representing the style of the image. Cannot be used in conjunction with style_reference_images or style
`style`	string (enum)	The style type to generate with. Cannot be used with style_codes. One of: `AUTO`, `GENERAL`, `REALISTIC`, `DESIGN`
`enable_prompt_expansion`	boolean	Determine if MagicPrompt should be used in generating the request or not. Default: `true`
`num_images`	integer	Number of images to generate. Default: `1`
`seed`	integer	Seed for the random number generator
`sync_mode`	boolean	If `True`, the media will be returned as a data URI and the output data won't be available in the request history. Default: `false`
`style_preset`	string (enum)	Style preset for generation. The chosen style preset will guide the generation.
`prompt`required	string	Prompt
`image_size`	string (enum)	The resolution of the generated image Default: `square_hd` One of: `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9`
`negative_prompt`	string	Description of what to exclude from an image. Descriptions in the prompt take precedence to descriptions in the negative prompt.

Output

A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.

Job excerpt

"outputs": [
  { "type": "image", "url": "https://…", "mime_type": "image/png", "thumbnail_url": "https://…" }
]

Pricing

Turbo$0.05/ image
Balanced$0.10/ image
Quality$0.15/ image

The exact charge for your input comes from a quote. How charges settle