
AI APIs for developers
Uncensored AI API
Compare uncensored AI image and video APIs on PoYo. Review model-specific safety controls, supported generation tasks, input requirements and pricing before integrating your application.
Matching models
11 models

$0.024 /image
qwen-image-3
Alibaba's third-generation image model for long prompts, information-dense layouts, fine text rendering, multilingual visuals, and knowledge-rich image generation.

$0.11 /second
happy-horse-1.1
Alibaba Happy Horse 1.1 video generation with text-to-video, image-to-video, and reference-to-video workflows.

$0.06 /second
wan2.7-text-to-video
Wan 2.7 Video models on PoYo for text-to-video, image-to-video, reference-to-video, and edit-video workflows.

$0.075 /image
seedream-5.0-pro
ByteDance's flagship image model for precise prompt following, dense layouts, multilingual text rendering, and region-precise editing.

$0.05 /billed second
wan3.0-text-to-video
Generate videos up to 30 seconds with Wan 3.0 using text, first and last frames, or multimodal references including images, video, audio, documents, and links.

$0.068 /billed second
wan3.0-prime-text-to-video
Wan 3.0 Video Prime is Alibaba's Wan 3.0 tier optimized for faster turnaround, with multimodal image, video, audio, document, and public webpage references, videos up to 30 seconds, and optional generated audio.

$0.03 /image
grok-imagine-image
xAI's Aurora-powered visual AI for image generation and video creation with Fun, Normal, and Spicy creative modes.

$0.01 /generation
z-image
Alibaba's efficient 6B-parameter image model with sub-second generation and exceptional Chinese-English bilingual text rendering capabilities.

$0.025 /generation
seedream-4.5
ByteDance's unified 4K image generation and editing model with professional-grade text rendering and commercial photography quality.

$0.025 /generation
seedream-5.0-lite
ByteDance's efficient multimodal image model with native 2K/3K resolution, deep thinking, bilingual text rendering, and smart editing.

$0.08 /second
happy-horse
Alibaba Happy Horse 1.0 video generation and editing with text-to-video, image-to-video, reference-to-video, and video-edit workflows.
Uncensored Model APIs - Pricing and Model Fit
Compare providers, supported inputs, output formats and prices before choosing a model.
Exact task match
Models appear here only when their catalog metadata includes Uncensored.
Provider comparison
Review model families across providers without leaving the task directory.
API-ready paths
Each model card links to PoYo pricing, examples, playground controls and API details.
| Model | Provider | Task types | Price |
|---|---|---|---|
| Qwen Image 3.0 qwen-image-3 | Alibaba | Text to Image, Image to Image, Uncensored | $0.024/image |
| Happy Horse 1.1 happy-horse-1.1 | Alibaba | Text to Video, Image to Video, Uncensored | $0.11/second |
| Wan 2.7 Video wan2.7-text-to-video | Alibaba | Text to Video, Image to Video, Uncensored | $0.06/second |
| Seedream 5.0 Pro seedream-5.0-pro | Seedream | Text to Image, Image to Image, Uncensored | $0.075/image |
| Wan 3.0 wan3.0-text-to-video | Alibaba | Text to Video, Image to Video, Uncensored | $0.05/billed second |
| Wan 3.0 Video Prime wan3.0-prime-text-to-video | Alibaba | Text to Video, Image to Video, Uncensored | $0.068/billed second |
| Grok Imagine grok-imagine-image | xAI | Text to Image, Image to Video, Uncensored | $0.03/image |
| Z-Image z-image | Alibaba | Text to Image, Uncensored | $0.01/generation |
| Seedream 4.5 seedream-4.5 | Seedream | Text to Image, Image to Image, Uncensored | $0.025/generation |
| Seedream 5.0 Lite seedream-5.0-lite | Seedream | Text to Image, Image to Image, Uncensored | $0.025/generation |
| Happy Horse happy-horse | Alibaba | Text to Video, Image to Video, Uncensored | $0.08/second |
Frequently asked questions
What is an uncensored AI API?
+
The term usually describes model access with more flexible safety controls. This collection covers image and video models with a documented configurable Safety Checker or Spicy mode through PoYo. It does not mean that the service or upstream provider has no restrictions.
Which image and video tasks are available?
+
The included models cover their documented text-to-image, image-editing, text-to-video or image-to-video endpoints. Check the task labels and model details before choosing. A control available for one model or operation is not automatically available for another.
How do I choose an uncensored AI image generation API?
+
Compare image quality, prompt following, reference support, output sizes and cost using the same representative inputs. Review the specific flexible control and its documented behavior. Use Text to Image or Image to Image guidance to evaluate the creative workflow as well as the control option.
How do I choose an uncensored AI video API?
+
Start with text-led or image-led generation, then compare duration, resolution, motion, audio and price. Confirm that the chosen endpoint exposes the control shown for that model. Test actual footage and task outcomes rather than assuming a flexible setting guarantees a successful clip.
Are Safety Checker and Spicy mode the same parameter?
+
No. These names describe model-specific controls and should not be interchanged across endpoints. Read the selected model documentation for exact field names, supported values and limitations. Do not add a generic safety parameter to an endpoint that does not document it.
How do I call these models through the PoYo API?
+
Choose a documented model ID and submit its supported inputs through the generation endpoint. Save task_id and retrieve the completed result by status polling or a supported callback_url. Keep the available control within the model input structure shown in that endpoint documentation.
Can I animate a source image with these APIs?
+
Yes, when the selected model supports an image-to-video endpoint. Verify image requirements, reference limits, duration, resolution and control availability. Use an appropriate source image and review the generated clip for identity, movement and unwanted changes.
Why can an API request still be rejected?
+
Provider-side checks, unsupported inputs, service restrictions and model changes can still affect a request. Read the returned error and task status before retrying. A flexible control is not a guarantee of acceptance, and changing input parameters does not remove applicable restrictions.
How is uncensored AI API usage priced?
+
Read the selected model price and billing unit. Image and video endpoints may charge per image, generation or duration, with separate tiers for quality and other settings. The control label alone does not establish one shared rate across the collection.
How should I handle timeouts and failed generation tasks?
+
Retain the original task ID and query its status before resubmitting. A client timeout may occur while the task is still processing. Inspect the documented error and account usage record, then correct invalid inputs or apply an appropriate retry strategy.
Can I use the generated images or videos commercially?
+
Review the selected provider and PoYo terms, and the rights to prompts, source media, people and brands involved in the project. Commercial use is not established merely because an API accepts a request. Confirm the relevant permissions before publishing or monetizing output.
Are submitted prompts, source files and outputs private?
+
Generation requires PoYo and relevant providers to process submitted content. Logs or generation history may be retained under the applicable service practices. Review the PoYo Privacy Policy and provider terms for your use case, especially before submitting sensitive or third-party media.
What content remains prohibited?
+
Requests involving minors or ambiguous age, non-consensual intimate imagery, sexual deepfakes of real people, coercion, exploitation and illegal content remain prohibited. A configurable safety control does not override PoYo policies or upstream provider restrictions.
What should developers consider for an age-restricted application?
+
Review the applicable service requirements and design appropriate age checks, consent and real-person protections, reporting and takedown paths, and application-level moderation. Test model and provider behavior regularly, since a control or response pattern can change over time.