# GPT-6 Luna vs flint-40b - AI Model Comparison

- Page: https://opencode.ai/data/compare/openai/gpt-6-luna/recursive/flint-40b
- Updated: 2026-11-03T05:05:18.000Z

|  | GPT-6 Luna | flint-40b |
| --- | --- | --- |
| Lab | OpenAI | Recursive |
| Context window | 1.1M | - |
| Max output | 128K | - |
| Input modalities | text, image, pdf | - |
| Reasoning | Yes | - |
| Tool calling | Yes | - |
| Open weights | No | - |
| Release date | 2026-09-22 | - |
| Input price per 1M tokens | $0.10 | - |
| Output price per 1M tokens | $0.50 | - |
| Cached input price per 1M tokens | $0.01 | - |
| OpenCode tokens: past 2 months | 5T | 840B |
| Share of all tokens | 0.4% | 0.1% |
| Rank by tokens last week | #9 | #11 |
| Unique users | 1M | 58K |
| Weekly retention | 65.1% | - |

Model pages: [GPT-6 Luna](https://opencode.ai/data/openai/gpt-6-luna.md), [flint-40b](https://opencode.ai/data/recursive/flint-40b.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.