# Dracarys Llama 3.1 70B Instruct vs GPT-5.6 Sol - AI Model Comparison

- Page: https://opencode.ai/data/compare/abacusai/dracarys-llama-3-1-70b-instruct/openai/gpt-5-6-sol
- Updated: 2026-09-28T12:09:38.000Z

|  | Dracarys Llama 3.1 70B Instruct | GPT-5.6 Sol |
| --- | --- | --- |
| Lab | Abacusai | OpenAI |
| Context window | 131K | 1.1M |
| Max output | 131K | 128K |
| Input modalities | text | text, image, pdf |
| Reasoning | No | Yes |
| Tool calling | No | Yes |
| Open weights | Yes | No |
| Release date | 2024-08-14 | 2026-07-09 |
| Input price per 1M tokens | - | $4.00 |
| Output price per 1M tokens | - | $20.00 |
| Cached input price per 1M tokens | - | $0.40 |
| OpenCode tokens: past 2 months | - | 0 |
| Share of all tokens | - | 0% |
| Rank by tokens last week | - | - |
| Unique users | - | 0 |
| Weekly retention | - | - |

Model pages: [Dracarys Llama 3.1 70B Instruct](https://opencode.ai/data/abacusai/dracarys-llama-3-1-70b-instruct.md), [GPT-5.6 Sol](https://opencode.ai/data/openai/gpt-5-6-sol.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.