# Dracarys Llama 3.1 70B Instruct vs Hy4 preview - AI Model Comparison

- Page: https://opencode.ai/data/compare/abacusai/dracarys-llama-3-1-70b-instruct/tencent/hy4-preview
- Updated: 2026-10-22T20:28:48.000Z

|  | Dracarys Llama 3.1 70B Instruct | Hy4 preview |
| --- | --- | --- |
| Lab | Abacusai | Tencent |
| Context window | 131K | 1M |
| Max output | 131K | 64K |
| Input modalities | text | text |
| Reasoning | No | Yes |
| Tool calling | No | Yes |
| Open weights | Yes | Yes |
| Release date | 2024-08-14 | 2026-08-28 |
| Input price per 1M tokens | - | $0.83 |
| Output price per 1M tokens | - | $2.50 |
| Cached input price per 1M tokens | - | $0.04 |
| OpenCode tokens: past 2 months | - | 366B |
| Share of all tokens | - | 0.0% |
| Rank by tokens last week | - | #35 |
| Unique users | - | 55K |
| Weekly retention | - | 54.3% |

Model pages: [Dracarys Llama 3.1 70B Instruct](https://opencode.ai/data/abacusai/dracarys-llama-3-1-70b-instruct.md), [Hy4 preview](https://opencode.ai/data/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.