Hy 3
Hy 3 is Tencent's language model with a 262K context window and up to 128K output tokens, available from 5 providers, starting at $0.132 / 1M input and $0.528 / 1M output. A preview-stage Hunyuan-series LLM from Tencent, identified by the compact 'Hy3' designation and targeting general-purpose text generation.
| Benchmarks | |
|---|---|
| Intelligence Index | #117 |
| Coding Index | #47 |
| GPQA | #48 |
| HLE | #80 |
| Time to First Token | #520 |
| SciCode | #75 |
| LCR | #62 |
| Output TPS | #143 |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities6/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema✓
Web Search✓
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | ||
|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
| $0.156 | $0.625 | $0.0391 | |
| $0.14 | $0.58 | $0.035 | |
| $0.14 | $0.58 | $0.035 | |
| $0.132 | $0.528 | $0.033 | |
| $0.14 | $0.58 | $0.035 | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host Hy 3, ranked by cheapest on-demand price. The model needs about 717 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 | |
|---|---|---|---|---|---|---|
| g7e.48xlarge |  AWS | 8× RTX PRO Server 6000 | 768 GB | $33.14/hr | ||
| g4-standard-384 |  GCP | 8× nvidia-rtx-pro-6000 | 768 GB | $36.00/hr | ||
| Standard_ND96isr_MI300X_v5 |  Azure | 8× AMD Instinct MI300X | 1536 GB | $48.00/hr | ||
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Hy4 Preview | 1.0M | $0.834 | $2.50 | Available | |
| Hy 3 | 262K | $0.132 | $0.528 | Current |