Pictures

Make a picture with any picture model

One request shape for every picture model — pick it by model (ids in GET /v1/ai/models/catalog): Ideogram for words inside the picture, Recraft for vector and brand styles, FLUX, Qwen Image and Z-Image, Soul 2 for fashion-photo realism, virtual try-on. reference_images edits or takes style from your pictures (models with editing only). options carries a model's own settings where its catalog entry lists some (bria-relight: light_type, light_direction).

Asynchronous: wait with x-wait-ms or poll GET /v1/executions/{id}. Price: one price per picture by model and size — see POST /v1/ai/models/image/estimate. Every picture is marked as AI-generated inside the file and kept 24 hours.

Billing: Per picture, by model and size. A refused or failed request is not charged. · Rate limit: 30/min · Asynchronous

post/v1/ai/models/image

Request

  • Base URL: https://apihub.co.il
  • URL: https://apihub.co.il/v1/ai/models/image
  • Auth: HTTP bearer

Headers

Idempotency-Keystring

Replay-safe: the same execution is returned instead of charging twice

X-Tagstring

Group calls into one job (e.g. one video) — see GET /v1/usage?tag=…

x-wait-msinteger

Wait for the job inside this call (ms)

Request body

seedinteger
size'1K' | '2K' | '4K'

1K ≈ 1024 px on the long side; 2K / 4K where the model makes them

modelstring required

A picture model id from GET /v1/ai/models/catalog — e.g. ideogram-3, recraft-v3, qwen-image, z-image-turbo, soul-2

route'auto' | 'direct' | 'higgsfield' | 'fal'

Team accounts only (ignored for others): where the model runs

stylestring

Recraft: realistic_image, digital_illustration, vector_illustration, icon…

promptstring

What the picture shows (required except for virtual-try-on). Ideogram writes the words you put in quotes inside the picture

optionsobject

A model's own settings, as its catalog entry lists them under options (e.g. bria-relight: light_type, light_direction). A setting the model does not list is refused

aspect_ratio'1:1' | '4:5' | '5:4' | '3:4' | '4:3' | '2:3' | '3:2' | '9:16' | '16:9' | '21:9'
negative_promptstring
reference_imagesstring[]

Pictures to edit or to take style / people / products from — models with editing only. virtual-try-on: [the person, the garment]

Response

Completed (or 202 while processing)

idstring

Execution id — stable across internal retries; use it with GET /v1/executions/{id}

status'pending' | 'processing' | 'completed' | 'partial' | 'failed' | 'cancelled' | 'timeout'
operationstring
tagstring nullable

Your X-Tag, if sent

created_atstring date-time
completed_atstring date-time nullable
outputobject

Operation result (see each operation). While a Studio render is processing: stage (queued · transcribing · downloading · preparing · cleaning_voice · mixing_audio · rendering · finishing), phase (the engine's: download · prepare · voice · audio · encode · qa · upload, or null), progress (a percent, 0–100) and progress_fraction (0–1), eta_seconds (seconds left, never below 0) and estimate_seconds

errorstring nullable

Changes

No recorded changes to this operation across all 2 revisions of this API.