# Dracarys Llama 3.1 70B Instruct vs Grok 4.5 - AI Model Comparison

- Page: https://opencode.ai/data/compare/abacusai/dracarys-llama-3-1-70b-instruct/xai/grok-4-5
- Updated: 2026-09-20T18:43:53.000Z

|  | Dracarys Llama 3.1 70B Instruct | Grok 4.5 |
| --- | --- | --- |
| Lab | Abacusai | xAI |
| Context window | 131K | 500K |
| Max output | 131K | 500K |
| Input modalities | text | text, image |
| Reasoning | No | Yes |
| Tool calling | No | Yes |
| Open weights | Yes | No |
| Release date | 2024-08-14 | 2026-07-08 |
| Input price per 1M tokens | - | $2.00 |
| Output price per 1M tokens | - | $6.00 |
| Cached input price per 1M tokens | - | $0.30 |
| OpenCode tokens: past 2 months | - | 884M |
| Share of all tokens | - | 0% |
| Rank by tokens last week | - | - |
| Unique users | - | 8.2K |
| Weekly retention | - | 46.4% |

Model pages: [Dracarys Llama 3.1 70B Instruct](https://opencode.ai/data/abacusai/dracarys-llama-3-1-70b-instruct.md), [Grok 4.5](https://opencode.ai/data/xai/grok-4-5.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.