# GPT-5.1 Codex mini vs Hy4 flash - AI Model Comparison

- Page: https://opencode.ai/data/compare/openai/gpt-5-1-codex-mini/tencent/hy4-flash
- Updated: 2026-11-18T13:09:59.000Z

|  | GPT-5.1 Codex mini | Hy4 flash |
| --- | --- | --- |
| Lab | OpenAI | Tencent |
| Context window | 400K | 1M |
| Max output | 128K | 66K |
| Input modalities | text, image | text, image |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| Open weights | No | No |
| Release date | 2025-11-13 | 2026-11-16 |
| Input price per 1M tokens | $0.25 | $0.04 |
| Output price per 1M tokens | $2.00 | $0.14 |
| Cached input price per 1M tokens | $0.03 | $0.0015 |
| OpenCode tokens: past 2 months | 0 | 9.1T |
| Share of all tokens | 0% | 0.6% |
| Rank by tokens last week | - | #2 |
| Unique users | 0 | 70K |
| Weekly retention | - | - |

Model pages: [GPT-5.1 Codex mini](https://opencode.ai/data/openai/gpt-5-1-codex-mini.md), [Hy4 flash](https://opencode.ai/data/tencent/hy4-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.
