Generate with HunyuanImage 3.0 Instruct Uncensored.
Images, priced per image.
Price per image
| Settings | |
|---|---|
| any settings | $0.1125 |
First request
curl https://api.uncensoredllm.ai/v1/images/generations \ -H "Authorization: Bearer sk-ullm-live-…" \ -H "Content-Type: application/json" \ -d '{"model":"hunyuan-image-3-instruct-uncensored","prompt":"a lighthouse at dusk"}'HunyuanImage 3.0 Instruct Uncensored settings: aspect ratio, negative prompt, num images, steps
| Setting | Values | Default |
|---|---|---|
prompt | text | required |
aspect_ratio | 1:1, 3:2, 16:9, 21:9, 9:16, 2:3, 3:4, 4:5 | 1:1 |
negative_prompt | text | |
num_images | 1 to 4 | 1 |
steps | 1 to 50 | 20 |
cfg_scale | 0.1 to 20 | |
seed | 0 to 999,999,999 | |
output_format | png, jpeg, webp | png |
enable_safety_checker | true or false | false |
What each HunyuanImage 3.0 Instruct Uncensored setting does
HunyuanImage 3.0 Instruct Uncensored is an image model you call with an API key, with the safety checker off by default, priced per image from $0.1125. Every setting below is optional unless the table above marks it required; anything you leave out takes its default.
prompt: What to make, in plain words. The only setting most requests need.aspect_ratio: The frame shape, width to height.negative_prompt: What to keep out of the result.seed: A number that makes a result repeatable: the same seed with the same settings gives the same output.output_format: The file type of the result.enable_safety_checker: Off unless the request sends true.
What HunyuanImage 3.0 Instruct Uncensored costs
The charge is quoted from the request before anything runs and taken when the job starts. Prices are read from the live catalog each time this page renders.
| Settings | Per image | 1 image | 10 images | 100 images |
|---|---|---|---|---|
| any settings | $0.1125 | $0.1125 | $1.13 | $11.25 |
There is no subscription. The balance is prepaid from $10 in the console, and the same key runs the uncensored chat models.
Calling HunyuanImage 3.0 Instruct Uncensored by API
POST /v1/images/generations takes OpenAI’s image request: prompt at the top level, settings the OpenAI shape has no field for inside input, and response_format as url or b64_json. It waits up to 100 seconds and answers in OpenAI’s shape, so the OpenAI SDK’s image call works unchanged; a job still running at that point answers 504 generation_pending with the generation id to fetch. The request in the panel above uses this route.
POST /v1/generations takes { "model", "input" } with every setting in input and answers 202 with a generation. Poll it with GET /v1/generations/{id} until its status reads succeeded or failed; the finished generation lists each file’s URL, type and size, and the charge with its units.
curl https://api.uncensoredllm.ai/v1/generations \ -H "Authorization: Bearer sk-ullm-live-…" \ -H "Content-Type: application/json" \ -d '{"model":"hunyuan-image-3-instruct-uncensored","input":{"prompt":"a lighthouse at dusk"}}'curl https://api.uncensoredllm.ai/v1/generations/gen_<id> \ -H "Authorization: Bearer sk-ullm-live-…"A generation that fails is given back in full: its charge reads refunded and the balance gets the amount back. Files stay under the API’s /v1/files path for 30 days. Base URL and key setup for every client are on the docs page.
What HunyuanImage 3.0 Instruct Uncensored will not run
Any prompt involving a minor is refused before it is priced or sent (HTTP 400, content_not_allowed). The rest is in the acceptable-use terms.
More uncensored image models
HunyuanImage 3.0 Instruct Uncensored questions
$0.1125 per image, paid from a prepaid balance that starts at $10. See every price.
Yes. enable_safety_checker defaults to false, so every request runs without it unless the request sends true.
It takes aspect ratio 1:1, 3:2, 16:9, 21:9, 9:16, 2:3, 3:4, 4:5.
It is given back in full. The generation reads failed, its charge shows refunded, and the balance gets the amount back.
Thirty days. Each result is a link under the API’s /v1/files path; download what you want to keep.
Any prompt involving a minor is refused before it is priced or sent, with HTTP 400 content_not_allowed. See the acceptable-use terms.