Models

Every video and picture model, with its price

The models of every maker in one list — Kling, Alibaba (Wan, HappyHorse, Qwen), ByteDance (Seedance, Seedream), MiniMax (H3, Hailuo), Lightricks (LTX), xAI (Grok Imagine), PixVerse, Ideogram, Recraft, Black Forest Labs (FLUX), Bria (relight), FASHN (virtual try-on), OpenAI (GPT Image) and Higgsfield's own (Soul, Cinema Studio, Genjutsu). Each runs at its maker's own API (runs_at_maker).

For each model: what it takes (takes: t2v text · i2v a first frame · flf first + last frame · ref reference pictures · v2v a video · t2i text · edit pictures), its lengths, resolutions, aspect ratios, sound, how many reference pictures and its price from (Credits); where it applies: options (the model's own settings and their values — Bria's light), styles (Genjutsu Restyle's presets, by id or name), length_from_video (the clip is as long as the video sent), consent_required (a person's picture put into motion needs the customer's consent declaration). Listed: the models that run now — ?include=all adds the ones still being connected (ready: false). ?kind=video or ?kind=image to filter. Free.

Billing: Free · Rate limit: 120/min

get/v1/ai/models/catalog

Request

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

Query parameters

kind'video' | 'image'

Only video or only picture models

include'all'

all = also the models still being connected (ready: false)

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=…

Response

Completed

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.