Hy4 flash
Tencent's Hy4 flash is a cost-efficient AI model designed for faster performance and lower latency. It supports both text and image inputs and features advanced capabilities including reasoning and tool calling.
Hy4 flash specs and pricing
- Provider: Tencent
- Released: November 16, 2026
- Context window: 1M tokens
- Max output: 66K tokens
- Input: text, images
- Output: text
- Price: $0.035 input / $0.14 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Hy4 flash is good at
- Writing and debugging software code
- Powering automated AI agents
- Processing large documents or images
To-dos to try with Hy4 flash
- Analyze this 500-page technical manual and summarize the troubleshooting steps for the hardware.
- Review this codebase and identify potential security vulnerabilities in the authentication module.
- Examine these architectural diagrams and list the primary components identified in the images.
FAQ
- Who developed Hy4 flash? Hy4 flash is developed by Tencent.
- Can this model process images? Yes, Hy4 flash accepts both text and image inputs.
- How much does Hy4 flash cost? Hy4 flash costs $0.035 per million input tokens and $0.14 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.12 credits ($1 = 100 credits).
- What is the context window of Hy4 flash? Hy4 flash can read up to 1M tokens at once and write up to 66K tokens in one reply.
- Can I use Hy4 flash without coding? Yes. In todo.is you pick Hy4 flash 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.