# Sao10k AI Model Usage & Rankings | OpenCode Data

- Page: https://opencode.ai/data/sao10k
- JSON: https://opencode.ai/data/sao10k.json

## Sao10k models

| Model | Tokens: past 2 months | Share of lab usage | Context window | Max output | Release date |
| --- | --- | --- | --- | --- | --- |
| [Llama 3.3 Euryale 70B](https://opencode.ai/data/sao10k/l3-3-euryale-70b.md) | - | - | 131K | 16K | 2024-12-18 |
| [Llama 3.1 Euryale 70B v2.2](https://opencode.ai/data/sao10k/l3-1-euryale-70b.md) | - | - | 131K | 16K | 2024-08-28 |
| [Llama 3 8B Lunaris](https://opencode.ai/data/sao10k/l3-lunaris-8b.md) | - | - | 8.2K | 7.4K | 2024-08-13 |

## 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.