Hy4 flash is a large language model made by Tencent, added to the catalog on 16 Nov 2026. It has a context window of 1,048,576 tokens and costs $0.035 per 1M input tokens and $0.141 per 1M output tokens. It accepts text and images and produces text. Typical uses: code assistance, reasoning over long documents and tool-assisted workflows.
Price checked · source: OpenRouter
What Hy4 flash is
Tencent Hy4 flash is a model from Tencent that accepts text and images and produces text. Its listed uses include code assistance, and it supports reasoning and tool use. Requests can also use structured outputs and response formats, which provide options for shaping the model’s text output. These features make it suitable for tasks that combine written instructions with tools or require a defined response structure.
The model has a context length of 1,048,576 tokens and a maximum output of 65,536 tokens. The large context can accommodate extensive input, such as long documents, code, or a collection of text and image material, within one request. The output limit allows room for detailed responses, while the model’s text-only output keeps its responses in written form. Its support for image input allows images to be included alongside text when forming a request.
Hy4 flash may suit code assistance, reasoning over lengthy material, and workflows that use tools or structured responses. The catalog description identifies it as a variant of Hy4 and mentions code assistance and agent-oriented work, though it does not specify particular tools, programming languages, image tasks, or supported output schemas. Those details should be checked against the interface where the model is used. Its stated capabilities describe supported input and output formats and features, rather than guaranteeing a particular result for any task.
Key features
- Accepts text and image inputs and produces text.
- Has a context length of 1,048,576 tokens.
- Supports up to 65,536 output tokens.
- Supports tools, reasoning, structured outputs, and response formats.
Typical uses
- Code assistance
- Reasoning over long documents
- Tool-assisted workflows
- Generating structured text responses
- Working with text and image inputs
Hy4 flash pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.035 |
| Output, per 1M tokens | $0.141 |
| Cached input read, per 1M tokens | $0.0015 |
No price change since it was added on 16 Nov 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0001 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0010 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0013 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.0055 |
Hy4 flash specifications
| Model id | tencent/hy4-flash |
|---|---|
| Version | hy4-flash-20261116 |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 65,536 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 16 Nov 2026 |
| Input types | text, image |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| 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 flash yet.
Compare Hy4 flash
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.