# GPT-6 Luna vs MiMo-V2.6-Flash - AI Model Comparison

- Page: https://opencode.ai/data/compare/openai/gpt-6-luna/xiaomi/mimo-v2-6-flash
- Updated: 2026-10-23T12:18:57.000Z

|  | GPT-6 Luna | MiMo-V2.6-Flash |
| --- | --- | --- |
| Lab | OpenAI | Xiaomi |
| Context window | 1.1M | 1M |
| Max output | 128K | 131K |
| Input modalities | text, image, pdf | text, image, audio, video |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| Open weights | No | Yes |
| Release date | 2026-09-22 | 2026-09-22 |
| Input price per 1M tokens | $0.10 | $0.10 |
| Output price per 1M tokens | $0.50 | $0.28 |
| Cached input price per 1M tokens | $0.01 | $0.0030 |
| OpenCode tokens: past 2 months | 3.4T | 47T |
| Share of all tokens | 0.3% | 4.2% |
| Rank by tokens last week | #11 | #4 |
| Unique users | 608K | 925K |
| Weekly retention | 66.7% | 82.6% |

Model pages: [GPT-6 Luna](https://opencode.ai/data/openai/gpt-6-luna.md), [MiMo-V2.6-Flash](https://opencode.ai/data/xiaomi/mimo-v2-6-flash.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.