Images
Creates an image from a prompt, or edits the images you send.
Updated on Aug 09, 2026
Generates and edits images with hinow/himegia. One call, one image, flat price per image. The guided usage is in Image generation.
https://api.hinow.ai/v1/imagesBearerCreates an image from a prompt, or edits the images sent in images.
Parâmetros
modelstring· bodyobrigatório`hinow/himegia` for the HiNow image model.
promptstring· bodyobrigatórioThe description of the scene — or, with `images`, the editing instruction.
imagesarray· bodySource images for editing or reference: public URLs or `data:` in base64.
parameters.aspect_ratiostring· body`1:1` (default), `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3`, `21:9`, `9:21`.
parameters.output_formatstring· body`jpeg` (default), `png` or `webp`.
parameters.num_inference_stepsinteger· bodyInference steps: 20 to 40, default 28. More steps, more detail, more time.
parameters.guidance_scalenumber· bodyAdherence to the prompt: 1.5 to 3.5, default 2.5.
Respostas
{
"success": true,
"data": {
"urls": ["https://s3.us1-stlouis.hinow.ai/hi-storage/.../8c9ab329.jpg"],
"thumbnail_url": "https://s3.us1-stlouis.hinow.ai/hi-storage/.../8c9ab329_thumb.webp",
"model": "hinow/himegia",
"category": "text_to_image",
"operation": "generate",
"cost": { "amount": 0.082, "currency": "USD", "value_type": "per_image" },
"metadata": { "format": "image/jpeg", "size": 236652 }
},
"request_id": "83d88c3e-6219-4efd-a6fb-6fed0df29c23"
}| Field | What it tells you |
|---|---|
data.urls | The generated image, in the platform's storage. Download and store on your side anything that goes to production. |
data.thumbnail_url | Thumbnail in webp, for listings and previews. |
data.operation | generate when it created from scratch; editing when it worked on images. |
data.cost | The exact cost of the call — { "amount": 0.082, "value_type": "per_image" }. |
data.metadata | Format and size in bytes of the final file. |
request_id | Identifier of the call, for support and auditing. |
The error envelope is specific to this endpoint
Errors come as {"success": false, "error": {"code": "MODEL_NOT_FOUND", "num_code": 4001, "message": "..."}} — the same format as authentication, not the one from https://api.hinow.ai/v1/chat/completions. Handle them by HTTP status code and by error.code.
Timeouts of a different scale
Generation takes from a few seconds to more than thirty, depending on the complexity of the request. Use a timeout of at least 120 seconds and process in a queue when volume is high.

