This catalog lists 13 image and video models. They answer on two routes: the image models through OpenAI’s image API, and video or anything slow through a single generations endpoint that you poll. Both calls are below, with the fields that move the price, a Python polling loop and how refunds work. Every price on the page comes from the live media catalog.
The two routes
- POST /v1/images/generations
- OpenAI’s image requestprompt as a top-level field, everything else under input; blocks for up to 100 seconds and replies in OpenAI’s shape
- POST /v1/generations
- { model, input }all settings under input; replies 202 with a generation you poll
- GET /v1/generations/{id}
- the generationits status, its files (URL, type, size) and the charge in units
The image route is there so that an OpenAI SDK image call needs no changes. Video, image-to-video and any job likely to outlast the image route’s wait use the generations route instead. One key from the console covers both. There is also a no-code path: the same models run in the console at app.unrestrictable.ai/console/media, and the media page lists every one of them.
Images through OpenAI’s image API
The shortest possible request on Anime Image Uncensored. response_format takes url or b64_json. When a job is still running at the 100-second mark the route answers 504 generation_pending and includes the generation id, which you then fetch.
curl https://api.unrestrictable.ai/v1/images/generations \ -H "Authorization: Bearer sk-unr-live-…" \ -H "Content-Type: application/json" \ -d '{"model": "anime-image-uncensored", "prompt": "a lighthouse keeper on a storm-bound island, oil painting", "response_format": "url"}'from openai import OpenAI client = OpenAI(base_url="https://api.unrestrictable.ai/v1", api_key="sk-unr-live-…")result = client.images.generate( model="anime-image-uncensored", prompt="a lighthouse keeper on a storm-bound island, oil painting", response_format="url",)print(result.data[0].url)Anything OpenAI’s request has no field for, such as the safety checker, the sampler or a seed, belongs inside input. Each model’s page lists its settings and their defaults.
Video: submit, then poll
Post the job on Wan 3.0 Video Uncensored, then fetch the generation until its status is succeeded or failed. Billing is per second; duration accepts 2 to 30 seconds.
curl https://api.unrestrictable.ai/v1/generations \ -H "Authorization: Bearer sk-unr-live-…" \ -H "Content-Type: application/json" \ -d '{"model": "wan-3.0-video-uncensored", "input": {"prompt": "waves breaking on granite at dusk, slow camera push", "duration": 5}}'curl https://api.unrestrictable.ai/v1/generations/gen_<id> \ -H "Authorization: Bearer sk-unr-live-…"For image-to-video on LTX-2.3 Image-to-Video Uncensored, pass the first frame as a public URL in image_urls:
curl https://api.unrestrictable.ai/v1/generations \ -H "Authorization: Bearer sk-unr-live-…" \ -H "Content-Type: application/json" \ -d '{"model": "ltx-2.3-i2v-uncensored", "input": {"prompt": "the figure turns and walks out of frame", "image_urls": ["https://example.com/frame.png"]}}'A Python poll loop
Polling every five seconds is enough. A generation that fails comes back with status failed, a reason, and its charge marked refunded.
import time, requests H = {"Authorization": "Bearer sk-unr-live-…"}gen = requests.post("https://api.unrestrictable.ai/v1/generations", headers=H, json={ "model": "wan-3.0-video-uncensored", "input": {"prompt": "waves breaking on granite at dusk, slow camera push"},}).json() while gen["status"] not in ("succeeded", "failed"): time.sleep(5) gen = requests.get(f"https://api.unrestrictable.ai/v1/generations/{gen['id']}", headers=H).json() print(gen["status"], gen.get("charge"), [f["url"] for f in gen.get("files", [])])Image prices
The starting price of each image model and the tier it belongs to, read from the media catalog when this page renders. Every tier is on the model page.
| Model | Billed per | Starting at | Tier that price belongs to |
|---|---|---|---|
| Anime Image Uncensored | per image | $0.03 | resolution 1K |
| Chroma Uncensored | per image | $0.08 | any settings |
| CyberRealistic XL Uncensored | per image | $0.0136 | size 512x512 |
| Qwen Edit Uncensored | per image | $0.08 | any settings |
| Qwen Image 2.1 Uncensored | per image | $0.0375 | resolution 1K |
| Qwen Image 3 Uncensored | per image | $0.08 | any settings |
| Seedream 5.0 Lite Edit Uncensored | per image | $0.0313 | any settings |
| Vision Image Uncensored | per image | $0.04 | any settings |
| Vision Pro Image Uncensored | per image | $0.09 | resolution 2K |
| WAI Illustrious SDXL Uncensored | per image | $0.0136 | size 512x512 |
Video prices
Video is billed per second of output, at whichever tier the resolution and other settings fall into. Five seconds of clip is five times that tier’s per-second rate.
| Model | Billed per | Starting at | Tier that price belongs to |
|---|---|---|---|
| LTX-2.3 Image-to-Video Uncensored | per second | $0.08 | resolution 480p |
| Wan 3.0 Image-to-Video Uncensored | per second | $0.20 | resolution 480p |
| Wan 3.0 Video Uncensored | per second | $0.20 | resolution 480p |
Settings that move the price
size,aspect_ratioandresolutionchoose the tier on most models. Which values change it is in the model page’s price table.nasks for more than one image or clip per request; each is charged the unit price.durationon a video model is the count of seconds charged.enable_safety_checkeris off by default on 7 of the 13 models listed; passtrueto switch it on for one request.
Billing, refunds and limits
- A failed generation is refunded in full: the charge reads refunded, and the amount returns to the balance.
- Output files sit under the API’s
/v1/filespath for 30 days. Save what you need before then. - A prompt that would put a minor in an image is refused before pricing or dispatch, with HTTP 400
content_not_allowed. Edit prompts that remove clothing run on images this API produced, never on an uploaded photo. The acceptable use policy spells out the rest. - A non-streamed generation carries its charge inside it; the console’s usage page shows each request with its units.
Questions
Yes. Set base_url to https://api.unrestrictable.ai/v1 and call client.images.generate with an id from the media page. Fields OpenAI's request lacks go under input.
Submit with POST /v1/generations, passing the model and an input object, then GET the generation until its status reads succeeded. The call and a Python loop are above.
No. The status reads failed, the charge shows refunded, and the full amount goes back to the balance.
After thirty days. Each result is a link under the API’s /v1/files path; download anything you want to keep before then.
On the media page: every listed image and video model with its starting price, 13 models at render. Each model page breaks out its tiers. See the media page.
Every model above is on the uncensored model list with its live price per million tokens. Per-token pricing sets the whole catalog side by side, and the family directory groups the builds by base model.