Enterprise DNAEnterprise DNA
Tencent logo

Models · Long context

Hy4 preview

by Tencent

Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total.

Visit Tencent ↗

Our verdict

Not reviewed yet

We have not reviewed Hy4 preview yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About Hy4 preview

Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total.

Notes

Hy4 preview is listed in the EDNA Models directory from the OpenRouter catalogue.

Key facts

What we have checked

Input price
$0.834 per million tokens
Checked OpenRouter models API
Output price
$2.50 per million tokens
Checked OpenRouter models API
Price on atlas-cloud
$0.042 per million cached input tokens
Checked OpenRouter models API
Price on atlas-cloud
$0.834 per million input tokens
Checked OpenRouter models API
Price on atlas-cloud
$2.50 per million output tokens
Checked OpenRouter models API
Price on cohere
$0.042 per million cached input tokens
Checked OpenRouter models API
Price on cohere
$0.834 per million input tokens
Checked OpenRouter models API
Price on cohere
$2.50 per million output tokens
Checked OpenRouter models API
Price on deepinfra
$0.042 per million cached input tokens
Checked OpenRouter models API
Price on deepinfra
$0.834 per million input tokens
Checked OpenRouter models API
Price on deepinfra
$2.50 per million output tokens
Checked OpenRouter models API
Proofbench
75% (for 28 Aug 2026)
Checked Epoch AI (CC BY 4.0)

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

API access

How to call it

Call via OpenRouter with model id `tencent/hy4-preview`.

  • openrouter · tencent/hy4-preview · Docs

OpenRouter id: tencent/hy4-preview

Price

What Hy4 preview costs, over time

Input price

$0.834 to $0.834

US dollars per million input tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Output price

$2.50 to $2.50

US dollars per million output tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Prices by host

HostPriceOver timeChecked
atlas-cloudCached input$0.042 per million cached input tokensSince 27 Oct 2026No change recordedOpenRouter models API
atlas-cloudInput$0.834 per million input tokensSince 27 Oct 2026No change recordedOpenRouter models API
atlas-cloudOutput$2.50 per million output tokensSince 27 Oct 2026No change recordedOpenRouter models API
cohereCached input$0.042 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
cohereInput$0.834 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
cohereOutput$2.50 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraCached input$0.042 per million cached input tokensSince 2 Nov 20263 changesOpenRouter models API
deepinfraInput$0.834 per million input tokensSince 2 Nov 20263 changesOpenRouter models API
deepinfraOutput$2.50 per million output tokensSince 2 Nov 20263 changesOpenRouter models API
gmicloudCached input$0.042 per million cached input tokensSince 27 Oct 2026No change recordedOpenRouter models API
gmicloudInput$0.834 per million input tokensSince 27 Oct 2026No change recordedOpenRouter models API
gmicloudOutput$2.50 per million output tokensSince 27 Oct 2026No change recordedOpenRouter models API
io-netCached input$0.042 per million cached input tokensSince 27 Oct 2026No change recordedOpenRouter models API
io-netInput$0.834 per million input tokensSince 27 Oct 2026No change recordedOpenRouter models API
io-netOutput$2.50 per million output tokensSince 27 Oct 2026No change recordedOpenRouter models API
novitaCached input$0.042 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
novitaInput$0.834 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
novitaOutput$2.50 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
siliconflowCached input$0.042 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
siliconflowInput$0.834 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
siliconflowOutput$2.50 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
tencentCached input$0.042 per million cached input tokensSince 29 Oct 20263 changesOpenRouter models API
tencentInput$0.834 per million input tokensSince 29 Oct 20263 changesOpenRouter models API
tencentOutput$2.50 per million output tokensSince 29 Oct 20263 changesOpenRouter models API

Usage

How much Hy4 preview is used

Tokens served a day

1.4T to 48.1B

tokens a day on OpenRouter. 19 Sept 2026 to 10 Nov 2026, 53 readings.

Source: OpenRouter model activity (748 of 748 series). Checked .

Scores

How Hy4 preview scores

Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.

ScoreValueSourceChecked
LMArena web development rating (Elo)1,632EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
Proofbench (best-across-versions)75percentAs of 28 Aug 2026Epoch AI (CC BY 4.0)

Sources

Where this comes from

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

  1. Price changed

    cached input per mtok: 0.0399 to 0.042

    Source: OpenRouter models API

  2. Price changed

    output per mtok: 2.37595 to 2.501

    Source: OpenRouter models API

  3. Price changed

    input per mtok: 0.7923 to 0.834

    Source: OpenRouter models API

  4. Price changed

    cached input per mtok: 0.042 to 0.0399

    Source: OpenRouter models API

  5. Price changed

    output per mtok: 2.501 to 2.37595

    Source: OpenRouter models API

  6. Price changed

    input per mtok: 0.834 to 0.7923

    Source: OpenRouter models API

  7. Price changed

    cached input per mtok: 0.0378 to 0.042

    Source: OpenRouter models API

  8. Price changed

    output per mtok: 2.2509 to 2.501

    Source: OpenRouter models API

  9. Price changed

    input per mtok: 0.7506 to 0.834

    Source: OpenRouter models API

  10. Price changed

    cached input per mtok: 0.042 to 0.0378

    Source: OpenRouter models API

  11. Price changed

    output per mtok: 2.501 to 2.2509

    Source: OpenRouter models API

  12. Price changed

    input per mtok: 0.834 to 0.7506

    Source: OpenRouter models API

  13. Price changed

    cached input per mtok: 0.0378 to 0.042

    Source: OpenRouter models API

  14. Price changed

    output per mtok: 2.2509 to 2.501

    Source: OpenRouter models API

  15. Price changed

    input per mtok: 0.7506 to 0.834

    Source: OpenRouter models API

  16. Price changed

    cached input per mtok: 0.0399 to 0.042

    Source: OpenRouter models API

  17. Price changed

    output per mtok: 2.37595 to 2.501

    Source: OpenRouter models API

  18. Price changed

    input per mtok: 0.7923 to 0.834

    Source: OpenRouter models API

  19. Price changed

    output per mtok: 2.2509 to 2.501

    Source: OpenRouter models API

  20. Price changed

    input per mtok: 0.7506 to 0.834

    Source: OpenRouter models API

USAGE / OPENROUTER

How much Hy4 preview is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
433B ▼95.4%
Requests, last 7 days
3.1M
Tool calls, last 7 days
2.7M
Average cost per request
$1.18
Price per million tokens
$0.834 in · $2.5 out
01.3T2.5T19 Sept: 1.4T tokens, 12M requests20 Sept: 2T tokens, 17.4M requests21 Sept: 1.9T tokens, 16.6M requests22 Sept: 2.1T tokens, 18.1M requests23 Sept: 1.6T tokens, 14.2M requests24 Sept: 1.3T tokens, 11.8M requests25 Sept: 827B tokens, 7.1M requests26 Sept: 874B tokens, 7.4M requests27 Sept: 1T tokens, 8.5M requests28 Sept: 1.2T tokens, 10.8M requests29 Sept: 1.2T tokens, 10.4M requests30 Sept: 1T tokens, 9.2M requests1 Oct: 673B tokens, 5.7M requests2 Oct: 665B tokens, 5.8M requests3 Oct: 766B tokens, 6.8M requests4 Oct: 968B tokens, 8.3M requests5 Oct: 1.1T tokens, 9.2M requests6 Oct: 1.2T tokens, 11M requests7 Oct: 1.4T tokens, 12.2M requests8 Oct: 1.3T tokens, 12.1M requests9 Oct: 1.3T tokens, 11.7M requests10 Oct: 1.2T tokens, 11M requests11 Oct: 841B tokens, 7.5M requests12 Oct: 1.1T tokens, 10M requests13 Oct: 1T tokens, 9.5M requests14 Oct: 1.1T tokens, 9.8M requests15 Oct: 1.3T tokens, 12.3M requests16 Oct: 1.2T tokens, 12.1M requests17 Oct: 907B tokens, 8.6M requests18 Oct: 846B tokens, 8M requests19 Oct: 1.4T tokens, 13.3M requests20 Oct: 1.4T tokens, 13.5M requests21 Oct: 1.5T tokens, 13.8M requests22 Oct: 1.5T tokens, 14M requests23 Oct: 1.3T tokens, 13M requests24 Oct: 978B tokens, 9.3M requests25 Oct: 974B tokens, 9.2M requests26 Oct: 1.4T tokens, 13.6M requests27 Oct: 1.4T tokens, 12.9M requests28 Oct: 1.5T tokens, 13.9M requests29 Oct: 1.7T tokens, 16.5M requests30 Oct: 1.5T tokens, 14.8M requests31 Oct: 959B tokens, 9.2M requests1 Nov: 735B tokens, 7.1M requests2 Nov: 1.6T tokens, 14.8M requests3 Nov: 1.6T tokens, 13.8M requests4 Nov: 71.8B tokens, 501K requests5 Nov: 158B tokens, 902K requests6 Nov: 23.2B tokens, 201K requests7 Nov: 50.7B tokens, 508K requests8 Nov: 48.1B tokens, 449K requests9 Nov: 33.3B tokens, 247K requests10 Nov: 48.1B tokens, 323K requests19 Sept3 Oct17 Oct31 Oct10 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with Hy4 preview.

Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-10. Hosting routes and app features can differ.

DeveloperTencent
Exact model identifiertencent/hy4-preview
Inputtext
Outputtext
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Listed support
Availability
available
Price basis
token
Licence verification
Apache 2.0, open weights
Context length
1M tokens
Knowledge cutoff
Not established
Developer release date
Not established
First seen in the catalogue
28 Aug 2026
Listed retirement date
Not established
Inspect the sources and their scope
catalogue source ↗

tencent/hy4-preview: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-11-10
openrouter.ai ↗

Source for reasoning controls, first seen, tool calling, context length, input, output, structured output.

Checked 2026-11-10
Licence source ↗

Licence declared in the tencent/Hy4-preview model repository on Hugging Face, which holds the weights files. Read the licence terms before use.

Checked 2026-11-07
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Run a reliable agentWorkflow & starter prompt ↗

What would it cost?

Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.

Working out the cost...

Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗

Check the source

Price date: 10 Nov 2026, from OpenRouter models API. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Vals Index: 53.209 (2026-11-09) ↗
Compare this model with alternatives →
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →