Hy4 Flash is Tencent's language model with a 1.0M context window and up to 66K output tokens, available from 2 providers, starting at $0.035 / 1M input and $0.141 / 1M output. A lightweight, fast variant of Tencent's Hy4 LLM optimized for agentic workflows, tool-use, and vision-enabled reasoning tasks.
Capabilities
Input2/5
Text✓
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities5/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | ||
|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
| $0.035 | $0.141 | $0.0015 | |
| $0.035 | $0.141 | $0.0015 | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host Hy4 Flash, ranked by cheapest on-demand price. The model needs about 529 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| p4de.24xlarge | 8× A100 | 640 GB | $27.45/hr | |||
| Standard_ND96amsr_A100_v4 | 8× NVIDIA A100 (80GB) | 640 GB | $32.77/hr | |||
| g7e.48xlarge | 8× RTX PRO Server 6000 | 768 GB | $33.14/hr | |||
Other Models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| Hy4 | — | 1.0M | $0.417 | $1.25 | |
| Hy4 Preview | — | 1.0M | $0.417 | $1.25 | |
| Hy 3 | — | 262K | $0.140 | $0.580 |