# Reflection AI Model Usage & Rankings | OpenCode Data

> Reflection models processed 990B tokens across OpenCode over the past two months, 0.1% of all usage. beam was the most-used Reflection model.

- Page: https://opencode.ai/data/reflection
- JSON: https://opencode.ai/data/reflection.json
- Updated: 2026-10-16T15:16:53.000Z
- Tokens processed: past 2 months: 990B
- Share of all usage: 0.1%

## Reflection models

| Model | Tokens: past 2 months | Share of lab usage | Context window | Max output | Release date |
| --- | --- | --- | --- | --- | --- |
| [Beam 1.0 501B A23B](https://opencode.ai/data/reflection/beam-1-0-501b-a23b.md) | - | - | 1M | 131K | 2026-10-05 |

## Daily usage: past 2 months

| Date | Tokens | Unique users |
| --- | --- | --- |
| 2026-10-13 | 135B | 6.7K |
| 2026-10-14 | 340B | 11K |
| 2026-10-15 | 330B | 8.9K |
| 2026-10-16 | 185B | 6.1K |

## 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.