Tencent: Hy Image 3.5 Preview

Hy Image 3.5 Preview creates 1024-pixel square images from text and edits reference images using written instructions. It is useful for drafting visuals and refining a composition.

Compare models

hy-image-v3.5-preview

AvailableTencentImageSync

Price: From $0.024
Modalities: Image

About Hy Image 3.5 Preview

Hy Image 3.5 Preview is Tencent Hunyuan's image model that handles text-to-image generation and instruction-based editing of reference images in one model. It makes 1024-pixel square images, returns them as URLs, and is meant for drafting visuals and refining a composition. As a preview build, its style and behavior may still change.

Where it works well

Edits from written instructions: send a reference image and describe the change instead of masking.
One model covers both new images and edits, so a design workflow needs no switch.
Changing one detail while leaving the rest of the picture alone suits product and layout touch-ups.
Short headlines and banner text can be requested directly in the prompt.
Results come back as image URLs, which suits web pipelines.

When to choose another model

It is a preview, so output style and behavior may change before the final release.
Output is 1024-pixel square images, so wide banners or large prints need cropping or upscaling elsewhere.
For vector output or layered files, a model built for them fits better.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

Image editingText to imageTokenLab endpoint

POST/v1/images/generations

curl -X POST "https://api.tokenlab.sh/v1/images/generations" \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
  "n": 1,
  "operation": "text-to-image",
  "response_format": "url",
  "size": "1024x1024",
  "model": "hy-image-v3.5-preview",
  "prompt": "A minimalist product photo of matte black headphones on a soft blue background."
}'

Parameters

Image editing

Parameter	Values and limits	Default	Notes
`image`	Inputs: ≥ 1, ≤ 20	Not provided	At most 20 source images in total across URL and uploaded image inputs. File references and masks are not declared for this contract.
`image_url`	Inputs: ≥ 1, ≤ 1	Not provided	Not provided
`image_urls`	Inputs: ≥ 1, ≤ 20	Not provided	Not provided
`model`	Not provided	Not provided	Not provided
`n`	1 · ≥ 1, ≤ 1 · ≤ 1	`1`	Not provided
`operation`	Not provided	Not provided	Not provided
`prompt`	Not provided	Not provided	Not provided
`response_format`	url	Not provided	Not provided
`seed`	Not provided	Not provided	Not provided
`size`	1024x1024	`1024x1024`	Output size is fixed to 1024x1024. An omitted size uses 1024x1024.

Text to image

Parameter	Values and limits	Default	Notes
`image`	Not provided	Not provided	Text-to-image does not accept source images. Do not send this field for that operation. Use one of this model's declared image operations for source-image requests.
`image_url`	Not provided	Not provided	Text-to-image does not accept source images. Do not send this field for that operation. Use one of this model's declared image operations for source-image requests.
`image_urls`	Not provided	Not provided	Text-to-image does not accept source images. Do not send this field for that operation. Use one of this model's declared image operations for source-image requests.
`model`	Not provided	Not provided	Not provided
`n`	1 · ≥ 1, ≤ 1 · ≤ 1	`1`	Not provided
`operation`	Not provided	Not provided	Not provided
`prompt`	Not provided	Not provided	Not provided
`response_format`	url	Not provided	Not provided
`seed`	Not provided	Not provided	Not provided
`size`	1024x1024	`1024x1024`	Output size is fixed to 1024x1024. An omitted size uses 1024x1024.

Only 1024x1024 is accepted. Omitted size defaults to 1024x1024. No multi-turn interface is exposed.

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Text to image / Image editing · Image

per image

Official price: $0.024
Verified price: —
Discount: —

	Official priceper image	Verified priceper image	Discount
Text to image / Image editing · Image	$0.024	—	—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Nov 15, 2026, 1:51 AM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Hy Image 3.5 Preview in Console with a prompt ready to edit or send.

Help me create an image with hy-image-v3.5-preview using text-to-image at /v1/images/generations. Show the result, cost, and any limits I should know.

Use cases

Best for

Text to Image

Poster drafts
Generate a poster with headline text, then refine layout and colors through a few written edit instructions.
Product image editing
Upload a product photo and ask for a new background or color variant while keeping the item itself unchanged.
Concept art exploration
Produce several stylistic variations of one idea to pick a direction before a designer takes over.
Social media visuals
Create banners with short readable text for campaigns and adjust wording by re-prompting.

Prompt examples

A minimalist concert poster with the words 'Night Market 2026' in bold sans-serif, deep blue background, lantern silhouettes.

Keep the sneaker exactly as it is and change the background to a sunlit concrete studio with a soft shadow.

Make the cat in this photo wear a small knitted hat, keep the lighting and pose the same.

FAQ

What is Hy Image 3.5 Preview?

It is Tencent Hunyuan's image generation and editing model, offered as a preview. It creates images from text and edits reference images from written instructions, within one model instead of separate tools.

Can it edit my own images?

Yes. Provide a reference image and describe the change in words, for example a new background or a different color for one object. The original image and the change instruction go in together in one request.

What size are the images?

1024-pixel squares, and the aspect ratio is fixed to a square. When a layout needs another shape, crop or extend the result in your own tools.

Is it good at text inside images?

Short headlines on posters and banners are a reasonable use. Spell the exact words out in the prompt, and keep long or small text to a minimum, since no image model is flawless there.

What format do results come back in?

Generated images are returned as URLs. Copy results into your own storage as part of the pipeline instead of relying on the returned link as a long-term home.

How much does Hy Image 3.5 Preview cost?

On TokenLab, Hy Image 3.5 Preview costs $0.024 per image. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should Hy Image 3.5 Preview use?

Use https://api.tokenlab.sh/v1/images/generations for Hy Image 3.5 Preview. The request example below shows the matching code shape.

Which operations does Hy Image 3.5 Preview support?

Hy Image 3.5 Preview supports Image editing, Text to image. Select an operation above to see its endpoint and request example.