Hy4 preview
Hy4 preview is a large language model made by Tencent, added to the catalog on 28 Aug 2026. It has a context window of 1,048,576 tokens and costs $0.751 per 1M input tokens and $2.251 per 1M output tokens. It accepts text and produces text. Typical uses: coding agent workflows, complex tool-use workflows and productivity tasks.
Price checked ยท source: OpenRouter
What Hy4 preview is
Tencent: Hy4 preview is a text-in, text-out model from Tencent, described in its catalog as a mixture-of-experts model. Its stated focus is coding agents, complex tool-use workflows, and productivity tasks. It accepts text and produces text; the listed capabilities include reasoning, tools, structured outputs, and response-format controls. This combination makes it relevant to text applications where a task may involve reasoning, interaction with tools, or output in a specified structure. The catalog does not identify particular tools, programming languages, or schemas, so those details are not established by the available model information.
The model has a context window of 1,048,576 tokens and a maximum output length of 64,000 tokens. This provides room to supply extensive text as context and request a long text response within one interaction. Its stated focus suggests use in coding-agent tasks, multi-step tool workflows, and productivity work involving text. Structured output and response-format support may fit applications that need generated text arranged according to a specified format; tool support is relevant where an application connects the model to tools. The catalog lists text as its input and output modality and does not specify other modalities or promise a particular result. Hy4 preview is therefore described through its documented text interface, context capacity, output limit, and supported interaction features.
Key features
- Accepts text and produces text
- Supports a context window of 1,048,576 tokens
- Supports tool use and reasoning
- Supports structured outputs and response formats
- Maximum output length is 64,000 tokens
Typical uses
- Coding agent workflows
- Complex tool-use workflows
- Productivity tasks
- Generating structured text
- Processing long text inputs
Hy4 preview pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.751 |
| Output, per 1M tokens | $2.251 |
| Cached input read, per 1M tokens | $0.0378 |
The price last changed on 22 Nov 2026. 4 price changes have been recorded since Hy4 preview was added.
| Date | Input /1M | Output /1M | Change |
|---|---|---|---|
| $0.751 | $2.251 | Price lowered | |
| $0.834 | $2.501 | Price raised | |
| $0.751 | $2.251 | Price lowered | |
| $0.834 | $2.501 | Price raised | |
| $0.751 | $2.251 | Added at this price |
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0011 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.021 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.027 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.116 |
Hy4 preview specifications
| Model id | tencent/hy4-preview |
|---|---|
| Version | hy4-preview-20260827 |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 64,000 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 28 Aug 2026 |
| Input types | text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Hy4 preview yet.
Compare Hy4 preview
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.