Harga+7% bonus
Hunyuan

Hunyuan API & Models on GPTProto

Explore the Hunyuan models available through GPTProto for software development, multi-step agents, document work, and research. See each live model's supported inputs, current token pricing, and API instructions before you build. Use a GPTProto key and shared balance to test Hunyuan alongside other supported providers.

Which Hunyuan model do you actually need?

Hy4 preview
1M-token context

$0.7923 / $2.376 per 1 juta token · — / $0.0399 cache · Konteks 1.05M

Model

Harga

SkenarioDaftar HunyuanOpenRouterGPTProtoPenghematan Anda / bln
Pribadi10M token / bln (4.8M dalam cache)$7.67$8.09$7.48−$0.19≈ $2.30 / thn
Tim100M token / bln (48M dalam cache)$76.71$80.93$74.79−$1.92≈ $23.03 / thn
Bisnis500M token / bln (240M dalam cache)$383.54$404.63$373.94−$9.60≈ $115.15 / thn
Biaya bulanan berdasarkan sumber
OpenRouter
$0.00
Hunyuan
$0.00
GPTProto
$0.00
Hemat $0.00 / bulan
Penghematan tahunan ≈ $0.00 · bayar sesuai pemakaian

About Hunyuan

Hunyuan, also branded Tencent Hy, is Tencent's model family. Tencent develops separate language, image, video, and 3D systems under related names, so a familiar Hunyuan label does not mean every model accepts the same inputs or uses the same API. This directory shows only the Hunyuan models currently supported on GPTProto, with each model's live capabilities, price, and route details on its card. The language-model route can assist with coding, analysis across documents, and research workflows, while the surrounding application remains responsible for tools and verification. Check the model card before choosing a request format; the catalog changes as supported routes change.

Why Use Hunyuan with GPTProto?

Evaluate Tencent's supported model in the same account and billing flow as the other AI models in your application.

One Key, Shared Balance

Use your GPTProto API key and prepaid balance for supported Hunyuan and other provider models from one account.

Hosted Open-Weight Access

Call the supported Hunyuan route without deploying the large open-weight checkpoint and maintaining its inference stack yourself.

Compare Live Costs

Read the current input, output, and cache rates on the model card before estimating your workload cost.

Test Across Providers

Evaluate Hunyuan beside other supported text models while checking each route's request fields and behavior before switching.

How to Access Hunyuan Models

Get started with a supported Hunyuan API route through GPTProto.

  1. 1

    Create a GPTProto Account

    Sign up and open the dashboard to manage your balance, API keys, and usage.

  2. 2

    Generate an API Key

    Create a key in the dashboard and store it securely in your server or application environment.

  3. 3

    Call a Live Hunyuan Model

    Open its model page, copy the current Model ID, and follow the documented endpoint and parameters for that route.

Frequently Asked Questions

Which Hunyuan models can I use on GPTProto?

The live directory above shows the Hunyuan models currently supported on GPTProto. It does not represent every model released by Tencent; open a model card to check availability, input types, and pricing.

Is Tencent Hunyuan 4 the same as Hy4 preview?

People may use “Hunyuan 4” when searching for this release, but Tencent's published model name is Hy4 preview. “Preview” describes an early version; use the exact Model ID shown on GPTProto when calling its API.

Can I create Hunyuan images, videos, or 3D assets from this page?

Check the live input and output labels in the directory. A text-to-text Hunyuan route does not generate images, videos, or 3D assets; Tencent's separate product families do not automatically become available through GPTProto.

Is the Hunyuan model suitable for coding agents?

Tencent developed Hy4 preview for extended software tasks involving planning, debugging, and verification. Your application must still execute tools, manage permissions, and check the result. Test token use and completion quality on your own workload.

Do I need a separate Tencent API key?

No. For the Hunyuan models listed here, use a GPTProto API key and the route instructions on the selected model page.

How is Hunyuan API usage priced?

Check the live model card for current input, output, and cached-input rates. Billing units and applicable rates can change; estimate a real workload using its expected input, output, and cache usage.

Does every Hunyuan model use the same endpoint or parameters?

No. Follow the documentation for the selected GPTProto route. If the catalog adds other model types, their request fields or generation flow may differ.

Mulai dengan Hunyuan

Satu kunci API GPTProto untuk Hunyuan dan penyedia lainnya.

Dapatkan Kunci API