Hy4
Tencent released Hy4 in November 2026 as a model designed for complex, agentic tasks. It supports both text and image inputs and features a large context window of over one million tokens, making it suitable for long-horizon projects.
Hy4 specs and pricing
- Provider: Tencent
- Released: November 4, 2026
- Context window: 1M tokens
- Max output: 66K tokens
- Input: text, images
- Output: text
- Price: $0.42 input / $1.25 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Hy4 is good at
- Analyzing large documents or image-heavy files
- Executing multi-step agentic workflows
- Complex reasoning tasks requiring long-term context
To-dos to try with Hy4
- Upload a series of technical diagrams and request a summary of the design changes between versions.
- Provide a 500-page project manual and ask the model to outline a multi-week implementation plan.
- Give the model access to a set of data files and ask it to perform a multi-step analysis to identify trends.
FAQ
- What is the primary focus of the Hy4 model? Hy4 is designed to provide strong performance in agentic capabilities and handle complex, long-horizon productivity tasks.
- Can Hy4 process visual information? Yes, the model supports both text and image inputs.
- How much does Hy4 cost? Hy4 costs $0.42 per million input tokens and $1.25 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 1.34 credits ($1 = 100 credits).
- What is the context window of Hy4? Hy4 can read up to 1M tokens at once and write up to 66K tokens in one reply.
- Can I use Hy4 without coding? Yes. In todo.is you pick Hy4 as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.