# beam Usage, Cost & Rank | OpenCode Data

> beam ranked #10 by tokens across OpenCode last week, with 0.1% of tokens over the past two months.

- Page: https://opencode.ai/data/reflection/beam
- JSON: https://opencode.ai/data/reflection/beam.json
- Model ID: beam
- Lab: Reflection
- Updated: 2026-10-16T20:32:02.000Z

## OpenCode usage: past 2 months

| Metric | Value |
| --- | --- |
| Rank by tokens last week | #10 |
| Tokens | 1.1T |
| Share of all tokens | 0.1% |
| Change vs previous 2 months | +100% |
| Unique users | 36K |
| Completed sessions | 749,278 |
| Average tokens per session | 1.5M |
| Average cost per session | $0.0000 |
| Total spend | $0 |
| Input tokens served from cache | 95.5% |
| Weekly retention | - |

## Daily usage: past 2 months

| Date | Tokens | Unique users | Sessions |
| --- | --- | --- | --- |
| 2026-10-13 | 135B | 6.7K | 129,644 |
| 2026-10-14 | 340B | 11K | 232,347 |
| 2026-10-15 | 330B | 8.9K | 200,202 |
| 2026-10-16 | 322B | 9.6K | 187,085 |

## Top countries: past 2 months

| Rank | Country | Tokens | Share |
| --- | --- | --- | --- |
| 1 | United States | 131B | 11.6% |
| 2 | Netherlands | 110B | 9.7% |
| 3 | India | 94B | 8.3% |
| 4 | United Kingdom | 90B | 8% |
| 5 | Brazil | 61B | 5.4% |
| 6 | Germany | 54B | 4.8% |
| 7 | Indonesia | 41B | 3.6% |
| 8 | Türkiye | 30B | 2.6% |
| 9 | Japan | 29B | 2.5% |
| 10 | France | 28B | 2.5% |
| 11 | Spain | 26B | 2.3% |
| 12 | Canada | 21B | 1.8% |
| 13 | Singapore | 18B | 1.6% |
| 14 | Philippines | 18B | 1.6% |
| 15 | Vietnam | 17B | 1.5% |

## Nearby models by tokens last week

| Rank | Model | Lab | Tokens |
| --- | --- | --- | --- |
| 6 | [nemotron-3-ultra](https://opencode.ai/data/nvidia/nemotron-3-ultra.md) | NVIDIA | 4T |
| 7 | [deepseek-v4-flash](https://opencode.ai/data/deepseek/deepseek-v4-flash.md) | DeepSeek | 3.3T |
| 8 | [glm-5.3-flash](https://opencode.ai/data/zhipuai/glm-5-3-flash.md) | Zhipu | 2.8T |
| 9 | [longcat-2.5-preview](https://opencode.ai/data/meituan/longcat-2-5-preview.md) | Meituan | 2.1T |
| 10 | [beam](https://opencode.ai/data/reflection/beam.md) | Reflection | 1.1T |
| 11 | [nemotron-3.5-lightning](https://opencode.ai/data/nvidia/nemotron-3-5-lightning.md) | NVIDIA | 864B |
| 12 | [gpt-6-luna](https://opencode.ai/data/openai/gpt-6-luna.md) | OpenAI | 729B |
| 13 | [deepseek-v4-pro](https://opencode.ai/data/deepseek/deepseek-v4-pro.md) | DeepSeek | 500B |
| 14 | [deepseek-v4-flash-vision-exp](https://opencode.ai/data/deepseek/deepseek-v4-flash-vision-exp.md) | DeepSeek | 472B |
| 15 | [mimo-v2.6-pro](https://opencode.ai/data/xiaomi/mimo-v2-6-pro.md) | Xiaomi | 460B |

## 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.