Does Hy Image 3.5 Preview support zero data retention?

No. The routes serving Hy Image 3.5 Preview retain content; see the per-route data-handling section for each route's logging stance and retention window.

Where is Hy Image 3.5 Preview hosted?

See the per-route table for Hy Image 3.5 Preview hosting locations and residency details.

Is Hy Image 3.5 Preview trained on prompts and outputs?

No. Every hosting route for Hy Image 3.5 Preview is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Hy Image 3.5 Preview?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Hy Image 3.5 Preview. Contact hello@opper.ai to receive it.

Hy Image 3.5 Preview

by Tencent

Hy Image 3.5 Preview is the latest image model in Tencent's Hunyuan family, released in September 2026. It generates images from a text prompt and edits or recomposes them from one or more reference images, planning the scene in a reasoning step before it renders. Tencent positions it as a clear step up from Hy Image 3.0, reporting a higher win rate in human evaluation and better consistency when editing from references. Output sizes are flexible: any width and height from 256 to 8192 pixels up to a 4096x4096 area, which covers 1K, 2K and 4K output. It is a preview release, so its behaviour may change before a stable version ships.

Call Hy Image 3.5 Preview on Opper with the OpenAI SDK. Sign up without a credit card. Get started

Get your API key Try in chat Compare

Key info

Input

Output

Features

Context window

—

Max output

—

Input price

$1.60 /1M

Output price

$1.60 /1M

No training by default
GDPR DPA available

Available routes

Hy Image 3.5 Preview runs on 1 route through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output	Cache read
Tencent Cloud	Multi		No	$1.60	$1.60	Input price

Live routes and prices as JSON: api.opper.ai/v3/models?q=tencent%3Asg%2Fhy-image-3.5-preview

Data handling per route

Each route hosting Hy Image 3.5 Preview has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Tencent Cloud — Multi-region

Content is retained: provider logging. No training on customer data. GLOBAL; SCCs; DPA available.

Zero data retention: Retained: provider logging.
Training: No training on customer data.
Logging: Other
Abuse monitoring: On by default, keeps nothing
Caching: Not cached
GDPR DPA: DPA available
Transfer mechanism: SCCs

Get started

Call Hy Image 3.5 Preview through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Hy Image 3.5 Preview is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "tencent:sg/hy-image-3.5-preview",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);