Hy4
Overview
Hy4 is a Tencent Hy language model designed for multi-step agent workflows and long-running productivity tasks. It adds visual understanding to the Hy4 series, combining text and image input with a 1M-token context window. On B.AI, use the model ID hy4.
Hy4
| Billing Item | Promotional Price (USD / 1M Tokens) |
|---|---|
| Input | $0.42 |
| Cache Write | $0.42 |
| Cache Read | $0.02 |
| Output | $1.25 |
The standard pricing table below continues to show original prices. See Promotions and Pricing Updates for the offer. The promotion period, actual settlement prices, and final billing are subject to the platform display.
Key Features
- Visual Understanding: Reads text in images, interprets charts, and analyzes screenshots alongside written instructions.
- Long-Context Analysis: Handles substantial reference material, with a 1M-token context window and up to 960,000 input tokens.
- Agent Workflows: Combines reasoning and function calling to support multi-step tasks with external tools.
- Adjustable Thinking: Enables deep reasoning by default and allows thinking to be disabled for simpler requests.
- Structured Responses: Supports structured output for extraction, data processing, and application workflows.
Best Use Cases
- Software Development: Plan implementations, investigate code, and use screenshots as context for interface development and debugging.
- Document and Chart Analysis: Extract information from scanned pages, interpret charts, and compare visual evidence with written material.
- Research and Synthesis: Work across long reference sets to produce summaries, comparisons, and reasoned answers.
- Office Agents: Coordinate analysis and document preparation through connected tools in workflows that require multiple steps.
Capabilities and Limitations
| Capability | Description |
|---|---|
| Input and Output | Text and image input; text output, including code and structured responses. |
| Reasoning | Deep thinking is enabled by default and can be disabled; supports preserved reasoning across tool interactions. |
| Context Window | 1M tokens. |
| Maximum Input | 960,000 tokens. |
| Maximum Output | 64,000 tokens. |
| Tool Use | Function calling for external tools and multi-step workflows. |
| Structured Output | Supports structured responses for extraction and downstream processing. |
| Image Input | PNG, JPEG, WEBP, and static GIF; up to 10 MB per image and 600 images per request, including conversation history, subject to token limits. |
Known Limitations
- Images are resized internally to fit within approximately 2048 x 2048 pixels; inputs exceeding 5500 x 5500 pixels are rejected. Crop relevant regions when fine detail or small text matters.
- Executing code, editing files, or operating applications requires an environment with the appropriate external tools and permissions.
- Multi-turn tool workflows need to retain the model's reasoning history to preserve continuity between tool calls.
Standard Pricing
The token prices below are shown in USD per 1 million tokens; web search is billed in USD per use.
| Model | Input (USD / 1M Tokens) | Cache Write (USD / 1M Tokens) | Cache Read (USD / 1M Tokens) | Output (USD / 1M Tokens) | Web Search (USD / use) |
|---|---|---|---|---|---|
| Hy4 | $0.834 | $0.834 | $0.042 | $2.501 | - |
Credits settlement: B.AI converts charges at 1 USD = 1,000,000 Credits and deducts Credits from the account balance.
Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through account benefits. Specific prices and account benefits are subject to the platform display and final billing records.