opendunes

Hy-MT2-30B-A3B

by TencentReleased 20 August 2026

Hy-MT2-30B-A3B reads text in one language and writes it back in another, working among 33 languages. You can give it a glossary of your own terms or a style to follow, and it reads about 8 pages at once. It is the largest of Tencent's three Hy-MT2 translators and the one Tencent calls its flagship.

TakesText
GivesText
Open in chatCreate API keyCompare

What it costs

You pay for what each request uses. No subscription, no minimum.

≈ 0,074 DA per message3 000 DA buys about 40 000 messages

One message, the ordinary use

1 000 tokens sent× 24,63 DA per 1M0,025 DA
500 tokens back× 98,19 DA per 1M0,049 DA
Total≈ 0,074 DA

Every rate

Meter↑ you send↓ comes back
Text tokens24,63 DA98,19 DA

per 1M tokens

Translate a product description≈ 0,036 DA
Translate a customer email≈ 0,054 DA
Translate subtitles for a 2-minute clip≈ 0,066 DA
Translate app interface strings with a glossary≈ 0,074 DA
Translate a full page of text≈ 0,096 DA
When you pay
After the answer, from your balance. Nothing is held.
Why it varies
A longer question or a longer answer costs more.
After each one
The exact charge shows on the request.
DepositDeposits from 50 DA, with Edahabia or CIB.

Where your request runs

One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send · ↓ what comes back.

TencentAsia…
↑ Sent, per 1M
24,63 DA
↓ Back, per 1M
98,19 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackLatencyThroughputUptime
TencentAsia24,63 DA98,19 DA………

You pay the price of the provider that served your request. Prices read 15:20 · speed over the last 30 minutes · uptime over 3 days.

See it in action

Real requests, real replies. Try any of them yourself — one click, pre-filled.

Structured output
You send

Turn this customer email into JSON with intent, urgency and order_id.

customer-email.txt
It replied

{ "intent": "refund", "urgency": "high", "order_id": "OD-58421" }

Try in Chat Lab
Writing
You send

Two lines to welcome a shop in Oran.

It replied

Welcome to our new shop in Oran — fresh bread every morning, and coffee the way the city likes it. Come in, the first cup is on us.

Try in Chat Lab

Try your own request — same model, pre-selected.

Open Chat Lab

Call it in code

Swap the base URL and the key. Your OpenAI code runs unchanged.

POST /v1/chat/completions
Base URL
https://opendunes.com/v1
Model ID
tencent/hy-mt2-30b-a3b
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://opendunes.com/v1",
    api_key=os.environ["OPENDUNES_API_KEY"],
)

resp = client.chat.completions.create(
    model="tencent/hy-mt2-30b-a3b",
    messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)

print(resp.choices[0].message.content)
pip install openaiFull reference for this route
Sign in to run it

Runs this request once on your balance.

Parameters you can send

Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.

Shaping the reply

How long, how varied, where to stop.

max_tokenstemperaturestop

Structured output

Get JSON you can parse instead of prose.

response_formatstructured_outputs

Other

Also accepted by this model.

max_completion_tokens

Questions about Hy-MT2-30B-A3B

  • How much does Hy-MT2-30B-A3B cost in dinars?

    About 0,074 DA per message. ↑ 24,63 DA · ↓ 98,19 DA per 1M tokens.

  • Is Hy-MT2-30B-A3B free? Can I try it?

    No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.

  • What is Hy-MT2-30B-A3B best for?

    Hy-MT2-30B-A3B reads text in one language and writes it back in another, working among 33 languages. You can give it a glossary of your own terms or a style to follow, and it reads about 8 pages at once. It is the largest of Tencent's three Hy-MT2 translators and the one Tencent calls its flagship.

  • Hy-MT2-30B-A3B or Hy-MT2-1.8B?

    Hy-MT2-1.8B costs 0,030 DA less for the same message.

  • How do I pay for Hy-MT2-30B-A3B without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, Hy-MT2-30B-A3B included, is paid from that balance. No foreign card, no conversion.

  • Does Hy-MT2-30B-A3B work in Arabic, French or Darja?

    Tencent lists 33 languages, Arabic and French among them. Darja is not named.

  • Can it read PDFs, images or a whole book?

    It reads text. Up to 8K tokens in one request, about 8 pages. It writes up to 3 000 words at once.

  • Is Hy-MT2-30B-A3B open source?

    Yes, its weights are public. Open weights on Hugging Face

  • Who makes Hy-MT2-30B-A3B, and when was it released?

    Tencent. Released 20 August 2026.

Other Tencent models, priced in dinars

See all Tencent models
Hy4Tencent · Nov 4, 2026

This model accepts text and pictures as input and produces text as output. It can process up to 1000 pages of material at one time and generate responses up to 65 pages long. It is designed for complex, real-world productivity tasks that require planning and the use of specific tools. However, it cannot access the internet to find new information.

Thinks firstUses your tools1 000 pages at once
≈0,35 DAper message
View model
Hy Image 3.5 PreviewTencent · Oct 5, 2026

Hy Image 3.5 Preview takes a written description plus up to 20 reference pictures and returns an image up to 4K, or an edited version of a picture you supply. It can keep one subject looking the same across a series of edits, follows your description closely, and draws Chinese and English lettering inside the picture. You can edit over several rounds.

Up to 20 references4K
≈7,99 DAper image
View model
Hy4 previewTencent · Aug 28, 2026

Hy4 preview reads and writes text, and keeps about 1,000 pages in mind at once. Tencent built it for coding assistants, long jobs that use the tools and apps you connect to it, and office-style work that needs planning and a steady thread over many steps. Pick it when the material is very long.

Thinks firstUses your tools1 000 pages at once
≈0,69 DAper message
View model
Hy3Tencent · Jul 6, 2026

Hy3 reads and writes text, and keeps about 260 pages in mind at once. You choose how hard it thinks: not at all by default, or at a low or high level for tricky maths, coding and problems with many steps. Tencent points it at coding, game development, financial analysis, document work and web page design, and says it flags missing evidence rather than inventing an answer. Hy4 preview reads about 1,000 pages at once.

Thinks firstUses your tools260 pages at once
≈0,13 DAper message
View model