# Hunyuan 4 Preview

Hunyuan 4 Preview is Tencent's 770B-parameter mixture-of-experts model with 49B active parameters, served natively on Tencent Cloud TokenHub with a one-million-token window of up to 960K input and 64K output. It reasons at high effort by default and exposes a two-rung reasoning control, none or high, for callers who want to turn thinking off. Its published context window is 1,048,576 tokens. The advertised input rate is $0.834 per million input tokens. The advertised output rate is $2.501 per million output tokens.

- Model identifier: ` tencent/hy4-preview `
- Creator: Tencent
- Providers: Tencent
- Model type: Text generation
- Canonical model page: [Hunyuan 4 Preview](<https://impossibl.com/tencent/hy4-preview>)
- API availability: Listed as serving through Impossibl.

## Providers

Tencent hosts Hunyuan 4 Preview. Impossibl routes your request intelligently and handles failover automatically when a provider is down.

| Provider | Endpoint location | Routes | Verified context window | Tool calling |
| --- | --- | --- | --- | --- |
| Tencent | Not specified | 1 | Not verified | Not verified |

The model price applies whichever provider serves the request. Endpoint locations do not guarantee inference residency.

## Specs and Capabilities

- Context window: 1,048,576 tokens
- Maximum output tokens: Not published in the public catalog; this is separate from the context window.
- Inputs: text
- Outputs: text
- Tool calling: Not published

## API access

Use ` tencent/hy4-preview ` as the model identifier through the Impossibl API.

Published API endpoints:

- ` /v1/chat/completions `

[API quickstart](<https://impossibl.com/docs/agent-quickstart>) · [Models and billing documentation](<https://impossibl.com/docs/models>)

## Published API prices

All rates are in USD. An unpublished rate is unknown, not zero. Workspace-specific pricing, taxes, balance-purchase fees, billing adjustments, and tool charges can affect the amount paid.

| Usage | Published base rate | Billing unit |
| --- | --- | --- |
| Input | $0.834 | per million input tokens |
| Output | $2.501 | per million output tokens |
| Cache read | $0.042 | per million cached input tokens |
| Cache write (default retention) | Not published | per million tokens |
| Cache write (one-hour retention) | Not published | per million tokens |
| Audio input | Not published | per million audio input tokens |

## Availability and retirement

The model is listed as serving. No retirement is announced in the current public catalog.

## Frequently asked questions

### What is Hunyuan 4 Preview?

Hunyuan 4 Preview is Tencent's 770B-parameter mixture-of-experts model with 49B active parameters, served natively on Tencent Cloud TokenHub with a one-million-token window of up to 960K input and 64K output. It reasons at high effort by default and exposes a two-rung reasoning control, none or high, for callers who want to turn thinking off.

Sources: [Tencent Cloud TokenHub pricing](<https://www.tencentcloud.com/document/product/1300/78937>); [Tencent Cloud deep reasoning guide](<https://www.tencentcloud.com/document/product/1300/80637>)

### How much does Hunyuan 4 Preview cost?

Hunyuan 4 Preview costs $0.834 per million input tokens and $2.501 per million output tokens through the Impossibl API. Cache reads cost $0.042 per million tokens. All rates are in USD.

### What is the context length of Hunyuan 4 Preview?

Hunyuan 4 Preview has a 1,048,576-token context window through the Impossibl API.

### What inputs and outputs does Hunyuan 4 Preview support?

Hunyuan 4 Preview accepts text as input. Hunyuan 4 Preview returns text.

### How do I use Hunyuan 4 Preview through an API?

Hunyuan 4 Preview is available through the Impossibl API. Use tencent/hy4-preview as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.

## Sources and related links

Prices, limits, capabilities, endpoints, and availability come from the public Impossibl catalog. Creator documentation supplies descriptions and release dates where available; it does not override the published API offering.

- [Public Impossibl model catalog](<https://api.impossibl.com/v1/models>)
- [Full model directory as JSON](<https://impossibl.com/models.json>)
- [Hunyuan 4 Preview: model details and pricing](<https://impossibl.com/tencent/hy4-preview>)
- [Model directory](<https://impossibl.com/models>)
- [Tencent Cloud TokenHub pricing](<https://www.tencentcloud.com/document/product/1300/78937>)
- [Tencent Cloud deep reasoning guide](<https://www.tencentcloud.com/document/product/1300/80637>)