# test-siliconflow-dsf4.1 vs tencent/hy4-preview - AI Model Comparison

- Page: https://opencode.ai/data/compare/deepseek/test-siliconflow-dsf4-1/tencent/tencent-hy4-preview
- Updated: 2026-10-19T12:42:40.000Z

|  | test-siliconflow-dsf4.1 | tencent/hy4-preview |
| --- | --- | --- |
| Lab | DeepSeek | Tencent |
| Context window | - | - |
| Max output | - | - |
| Input modalities | - | - |
| Reasoning | - | - |
| Tool calling | - | - |
| Open weights | - | - |
| Release date | - | - |
| Input price per 1M tokens | - | - |
| Output price per 1M tokens | - | - |
| Cached input price per 1M tokens | - | - |
| OpenCode tokens: past 2 months | 1.8M | 93K |
| Share of all tokens | 0% | 0% |
| Rank by tokens last week | #53 | #54 |
| Unique users | 0 | 1 |
| Weekly retention | - | - |

Model pages: [test-siliconflow-dsf4.1](https://opencode.ai/data/deepseek/test-siliconflow-dsf4-1.md), [tencent/hy4-preview](https://opencode.ai/data/tencent/tencent-hy4-preview.md)

## Methodology

- Updates: Aggregated every hour. Days and weeks use UTC.
- Tokens: Input, output, reasoning, and cached tokens for each request.
- Users and sessions: Approximate counts of distinct users and OpenCode sessions.
- Cost: Session cost is the average cost per OpenCode session. Token prices are list prices from the OpenCode model catalog.
- Retention: The share of a model's users in one week who use it again the next week.
- Citation: Cite OpenCode Data (opencode.ai/data) with the update time shown at the top of the page.