When was Hy3 released?

Tencent released Hy3 on 6 Jul 2026. It is available through the Opper gateway.

Does Hy3 support zero data retention?

Yes. Hy3 is available with zero data retention on DeepInfra, Novita through the Opper gateway.

Hy3 runs on US hosting routes through the Opper gateway.

Is Hy3 trained on prompts and outputs?

No. Every hosting route for Hy3 is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Hy3?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Hy3. Contact hello@opper.ai to receive it.

Hy3

by Tencent

All Tencent releases

Hy3 is the third generation of Tencent's Hunyuan line, released in July 2026 under a fully permissive Apache 2.0 license with no geographic carve-outs. That last detail matters, because the April preview of the same family had excluded the EU, UK and South Korea from its terms, and the full release removed those restrictions. Architecturally it is a Mixture-of-Experts with 295 billion total parameters and roughly 21 billion active for any given token, so serving cost tracks a far smaller model than the headline count suggests. It carries a 256K token context window and a hybrid reasoning system that moves between fast and slow modes by task, and the weights are published on Hugging Face, ModelScope and GitHub in both BF16 and FP8 formats, which suits self-hosted agentic coding and reasoning work.

Call Hy3 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

262K

Max output

262K

Input price

$0.14 /1M$0.04 cache read

Output price

$0.58 /1M

Released

6 Jul 2026

US residency available
Zero data retention on pay-as-you-go
No training by default
GDPR DPA available

Available routes

Hy3 runs on 3 different routes 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	Training	Input	Output	Cache read
DeepInfra	US	No	$0.14	$0.58	$0.04
Novita	US	No	$0.14	$0.58	$0.04
Tencent Cloud	Multi	No	$0.13	$0.53	$0.03

Uptime and availability

Hy3 runs on 2 independently monitored routes through the Opper gateway. A direct integration leaves you on one of them, the gateway serves whichever is healthy.

100%effective uptime, last 30 days

Averaged across these routes on their own, a single provider reached 100% over the same window.

Daily status through the gateway, which serves each request from whichever route is healthy.

2 monitored providers serve Hy3.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 1 further route for this model is not on the board yet and is not counted above. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting Hy3 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

DeepInfra — United States🇺🇸

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; unknown; DPA available.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: No classifier
GDPR DPA: DPA available
Transfer mechanism: unknown

Novita — United States🇺🇸

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs; DPA available.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: On by default, keeps nothing
GDPR DPA: DPA available
Transfer mechanism: SCCs

Tencent Cloud — Multi-region

Content is retained: limited debug logs, 30-day retention. No training on customer data. GLOBAL; SCCs; DPA available.

Zero data retention: Retained: limited debug logs, 30-day retention.
Training: No training on customer data.
Logging: Limited debug logs (30-day retention)
Abuse monitoring: On by default, holds flagged content
Caching: Content cached for replay
GDPR DPA: DPA available
Transfer mechanism: SCCs

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#142 of 670 LLMs

TierEfficient

Output speed95 tok/s

First token2.00s

Intelligence Index25.3

Coding Index58.8

Reasoning & knowledge

GPQA Diamond

90%

Humanity's Last Exam

34%

Long-context reasoning

79%

Coding

SciCode

49%

See full leaderboard →Benchmarks via Artificial Analysis · View on AA

Get started

Call Hy3 through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Hy3 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: "hy3",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);