Hy4 preview
A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.
- Context
- 1.0M
- Released
- 1mo ago
- Parameters
- —
- Input / 1M tokens
- $0.75
- Output / 1M tokens
- $2.25
- Cached input / 1M tokens
- $0.04
Sources:models.devOpenRouter
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
No benchmark results have been matched to this model yet.
Specifications
- Developer
- Tencent
- Model family
- Hunyuan
- Type
- Language model
- Predecessor
- —
- Successor
- —
- Released
- August 28, 2026
- Model ID
tencent/hy4-preview- Openness
- Open weights
- License
- —
- Parameters
- —
- Input modalities
- text
- Output modalities
- text
- Modality
- text->text
- Tokenizer
- Other
- Max output tokens
- 64K
- Hugging Face
- tencent/Hy4-preview
- Source freshness
- Metadata synced Oct 8, 2026, 10:17 PM UTC
Additional source evidence
- Source model
- tencent/hy4-preview
- Source family
- Hy
- Last updated
- 2026-08-28
- Model context
- 1.0M
- Model output limit
- 64K
- Open weights
- Yes
- File attachments
- No
- Reasoning
- Yes
- Tool calling
- Yes
- Temperature control
- Yes
Complete source record (JSON)
{
"id": "tencent/hy4-preview",
"name": "Hy4 preview",
"description": "A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.",
"family": "Hy",
"last_updated": "2026-08-28",
"attachment": false,
"reasoning": true,
"tool_call": true,
"temperature": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1024000,
"output": 64000
},
"release_date": "2026-08-28",
"open_weights": true
}Infrastructure
Provider availability
| Provider | Endpoint | Context | Input /M tokens | Output /M tokens | Cached input /M tokens | Cache write /M tokens | Uptime 1d | Data handling |
|---|---|---|---|---|---|---|---|---|
| makora/fp8 | 131K | $0.83 | $2.50 | $0.04 | — | 100.00% | ZDR: Yes | |
| deepinfra/fp4 | 1.0M | $0.83 | $2.50 | $0.04 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| novita/fp8 | 1M | $0.83 | $2.50 | $0.04 | — | 99.11% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| siliconflow/fp8 | 1.0M | $0.83 | $2.50 | $0.04 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| tencent/fp8 | 1.0M | $0.83 | $2.50 | $0.04 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 |
Provider data:OpenRouter
Deployment graph
Can I run this?
Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.