opendunes

Hy4 preview

by TencentReleased 28 August 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.

TakesText
GivesText
Open in chatCreate API keyCompare

What it costs

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

≈ 0,69 DA per message3 000 DA buys about 4 300 messages

One message, the ordinary use

1 000 tokens sent× 277,58 DA per 1M0,28 DA
500 tokens back× 832,42 DA per 1M0,42 DA
Total≈ 0,69 DA

Every rate

Meter↑ you send↓ comes back
Text tokens277,58 DA832,42 DA
Cached tokens read13,98 DA

per 1M tokens

Answer a quick question≈ 0,25 DA
Reply to a customer email≈ 0,50 DA
Review a pull request of about 400 lines≈ 2,66 DA
Summarise a 20-page report≈ 4,47 DA
Build a slide outline from ten documents≈ 12,35 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

Seven companies run this model. OpenDunes sends each request to one of them, picked by price and speed. If it fails, the next one takes it. DA per 1M tokens: ↑ what you send · ↓ what comes back.

GMICloudUnited States…
↑ Sent, per 1M
277,58 DA
↓ Back, per 1M
832,42 DA
Cache read
13,98 DA
Latency
…
Throughput
…
AtlasCloud…
↑ Sent, per 1M
277,58 DA
↓ Back, per 1M
832,42 DA
Cache read
13,98 DA
Latency
…
Throughput
…
Cohere…
↑ Sent, per 1M
277,58 DA
↓ Back, per 1M
832,42 DA
Cache read
13,98 DA
Latency
…
Throughput
…
DeepInfraUnited States…
↑ Sent, per 1M
277,58 DA
↓ Back, per 1M
832,42 DA
Cache read
13,98 DA
Latency
…
Throughput
…
Novita…
↑ Sent, per 1M
277,58 DA
↓ Back, per 1M
832,42 DA
Cache read
13,98 DA
Latency
…
Throughput
…
SiliconFlowUnited States…
↑ Sent, per 1M
277,58 DA
↓ Back, per 1M
832,42 DA
Cache read
13,98 DA
Latency
…
Throughput
…
TencentAsia…
↑ Sent, per 1M
277,58 DA
↓ Back, per 1M
832,42 DA
Cache read
13,98 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackCache readLatencyThroughputUptime
GMICloudUnited States277,58 DA832,42 DA13,98 DA………
AtlasCloud277,58 DA832,42 DA13,98 DA………
Cohere277,58 DA832,42 DA13,98 DA………
DeepInfraUnited States277,58 DA832,42 DA13,98 DA………
Novita277,58 DA832,42 DA13,98 DA………
SiliconFlowUnited States277,58 DA832,42 DA13,98 DA………
TencentAsia277,58 DA832,42 DA13,98 DA………

You pay the price of the provider that served your request. Prices read 15:19 · 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/hy4-preview
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/hy4-preview",
    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_tokenstemperaturetop_ptop_kmin_pstopseedfrequency_penaltypresence_penaltyrepetition_penaltylogit_biaslogprobstop_logprobs

Reasoning

Let it think before answering — and see the thinking.

reasoningreasoning_effortinclude_reasoning

Structured output

Get JSON you can parse instead of prose.

response_formatstructured_outputs

Tools

Let the model call your functions.

toolstool_choiceparallel_tool_calls

Other

Also accepted by this model.

max_completion_tokens

Questions about Hy4 preview

  • How much does Hy4 preview cost in dinars?

    About 0,69 DA per message. ↑ 277,58 DA · ↓ 832,42 DA per 1M tokens.

  • Is Hy4 preview 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 Hy4 preview best for?

    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.

  • How do I pay for Hy4 preview without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, Hy4 preview included, is paid from that balance. No foreign card, no conversion.

  • Does Hy4 preview work in Arabic, French or Darja?

    Tencent names no languages for Hy4 preview. Arabic, French and Darja: not stated.

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

    It reads text. Up to 1M tokens in one request, about 1 000 pages. It writes up to 48 000 words at once.

  • Is Hy4 preview open source?

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

  • Who makes Hy4 preview, and when was it released?

    Tencent. Released 28 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
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
Hy3 previewTencent · Apr 22, 2026

Hy3 preview reads and writes text, and keeps about 260 pages in mind at once. You can switch its thinking off, or set it to low or high, trading speed for depth depending on the job. Tencent builds it for long jobs with many steps and for writing code. As a preview it is for trying this line before settling on the finished Hy3, which has the same reading size.

Thinks firstUses your tools260 pages at once
≈0,16 DAper message
View model