HY Image 3.5 Preview API access to Tencent Hunyuan's latest image model: text-to-image, reference-based editing and multi-image composition, with strong multilingual text rendering and 1K, 2K, 4K or exact-pixel output.

Image link valid for 72 hours
Transparent pricing with no hidden fees. Pay only for what you use.
| Variant | Tier | GoldCurrent price | Platinum | Diamond | Official | Your savings |
|---|---|---|---|---|---|---|
hy-image-v3.5-preview | 1K | 0.192Credits(~$0.0192)/pic | 0.1824Credits(~$0.0182)/pic | 0.1728Credits(~$0.0173)/pic | 0.24Credits(~$0.024)/pic | 20% |
| 2K | 0.192Credits(~$0.0192)/pic | 0.1824Credits(~$0.0182)/pic | 0.1728Credits(~$0.0173)/pic | 0.24Credits(~$0.024)/pic | 20% | |
| 4K | 0.256Credits(~$0.0256)/pic | 0.2432Credits(~$0.0243)/pic | 0.2304Credits(~$0.023)/pic | 0.32Credits(~$0.032)/pic | 20% |
* Actual costs are subject to final output.
HY Image 3.5 Preview from Tencent Hunyuan creates images from text, edits photos and blends up to five references in one model. Call the HY Image 3.5 Preview API on APIMart with the model ID hy-image-v3.5-preview to make posters with legible Chinese and English text, product scenes and consistent character edits.
Generation, editing and output controls in the HY Image 3.5 Preview API
What marketing, product and design teams build with the HY Image 3.5 Preview model
Three steps from sign-up to your first HY Image 3.5 Preview API request
Sign up for free. One APIMart account gives you HY Image API access to HY Image 3.5 Preview along with every other model on the platform.
Top up your balance. Credits are shared across all models, and HY Image 3.5 Preview is billed per output image.
Create an API key in the dashboard, then call POST /v1/images/generations with the model hy-image-v3.5-preview.
Common questions about the HY Image 3.5 Preview API: model, inputs, sizes, pricing, API key and results
The HY Image 3.5 Preview API gives you HY Image 3.5 Preview, Tencent Hunyuan's image generation and editing model released as a hosted preview on September 22, 2026. One model covers text-to-image, reference-based generation and editing. On APIMart, send the model ID hy-image-v3.5-preview.
HunyuanImage 3.0 is Tencent's earlier open-weight model. HY Image 3.5 Preview is a hosted model with no published weights, and Tencent presents it as an upgrade in text rendering, realism and edit consistency.
Tencent labels this release a preview, so output quality, limits and the underlying model may change. Test important HY Image API workflows before production use and check this page for updates.
Send hy-image-v3.5-preview up to five publicly accessible JPEG, PNG or WebP URLs in image_urls, ideally under 7 MB each. Describe in the prompt which elements to keep, change or combine. Leave image_urls out for text-to-image.
Set size to auto (default) or 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9 or 21:9, and resolution to 1K (default), 2K or 4K. For an exact hy-image-v3.5-preview size, pass size such as 2000x1104 or a width and height pair: 256–8192 px per side, at most 8,294,400 pixels.
No. Each HY Image 3.5 Preview request returns one image, so n must be 1. Send parallel requests when you need several variations.
Yes. Pass the previous result back to hy-image-v3.5-preview as a reference image together with a new instruction. Each round is a separate request.
HY Image 3.5 Preview bills each output image once, whatever you pass to hy-image-v3.5-preview. With an aspect ratio, the resolution tier sets the rate; with exact pixels, the short edge decides: up to 1024 px is 1K, 1025–2048 px is 2K, larger is 4K. The pricing table shows live rates, and failed tasks are fully refunded.
Sign in to APIMart, add credits and create a key on the API Keys page. Send it as a Bearer token in the Authorization header; the same API key works for every HY Image API request and every other model on APIMart.
Submit to POST /v1/images/generations with model hy-image-v3.5-preview and keep the task_id, then poll GET /v1/tasks/{task_id} every 3–5 seconds for up to about 5 minutes. When the status is completed, read result.images[0].url[0] and download the image before expires_at.
Yes, they all refer to the same Tencent model. Its model ID on the images endpoint is hy-image-v3.5-preview; Tencent's chat documentation writes Hy-Image-3.5-Preview, and benchmark sites list HunyuanImage 3.5 (Preview). Spellings such as HY-Image 3.5, Hy Image3.5, HY Image v3.5 or Hunyuan Image 3.5 API point to the same model. On APIMart, call it through the HY Image API with hy-image-v3.5-preview.
You can reach us via the live chat in the bottom-right corner, email us at [email protected], or join our Discord community. Our team will get back to you as soon as possible.
Explore more models in the same category.

Flux 3 Image Klein
FLUX 3 Image Klein is a compact, open-weight image generation and editing model developed by Black Forest Labs. It combines text-to-image creation, image editing, and composition using up to 10 reference images in a single model. With support for up to 4K resolution and bounding-box layout control, it gives creators flexible tools to bring their ideas to life.

Mai Image 2.6
MAI-Image-2.6 is Microsoft's image model for text-to-image, single-image editing and composition with up to 5 reference images. It is available in high-quality and Flash versions, with 1K and 2K output and sharp text rendering.

Mai Image 2.6 Flash
MAI-Image-2.6 Flash is the Flash version of Microsoft MAI-Image-2.6 for text-to-image and image editing with up to 5 references, 1K/2K PNG output and optional Bing grounding, billed by actual token usage.

Flux 3 Image
FLUX 3 Image by Black Forest Labs handles text-to-image, single-image editing and generation with up to 10 reference images. It supports multiple aspect ratios and resolutions up to 4K, priced by resolution with no extra charge for references.