# Qwen3.8 Flash vs GPT-6 Luna - AI Model Comparison

- Page: https://opencode.ai/data/compare/alibaba/qwen3-8-flash/openai/gpt-6-luna
- Updated: 2026-10-02T17:41:52.000Z

|  | Qwen3.8 Flash | GPT-6 Luna |
| --- | --- | --- |
| Lab | Alibaba | OpenAI |
| Context window | 1M | 1.1M |
| Max output | 131K | 128K |
| Input modalities | text, image, video | text, image, pdf |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| Open weights | No | No |
| Release date | 2026-08-26 | 2026-09-22 |
| Input price per 1M tokens | $0.15 | $0.10 |
| Output price per 1M tokens | $0.47 | $0.50 |
| Cached input price per 1M tokens | $0.02 | $0.01 |
| OpenCode tokens: past 2 months | 2T | 846B |
| Share of all tokens | 0.2% | 0.1% |
| Rank by tokens last week | #16 | #12 |
| Unique users | 152K | 126K |
| Weekly retention | 60.0% | - |

Model pages: [Qwen3.8 Flash](https://opencode.ai/data/alibaba/qwen3-8-flash.md), [GPT-6 Luna](https://opencode.ai/data/openai/gpt-6-luna.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.