Hy4 flash
by OpenRouter · family Hy · listed Nov 2026RTV
Tencent Hy reasoning model for coding, instruction following, and agent tasks
Current rates USD per 1M tokens
Input$0.035
Output$0.141
Cache read$0.0015
Cache write—
Against the market
On the record
- Model id
tencent/hy4-flash- Context window
- 1.0M tokens
- Max output
- 66K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2026-11-16
- Last updated
- 2026-11-16
- Provider docs
- openrouter.ai/models
Back of the envelope
≈
Also listed at
- Vercel AI Gateway$0.035 in · $0.141 out
- Hugging Face$0.035 in · $0.141 out
- Kilo Gateway$0.07 in · $0.281 out
- DevPass (LLM Gateway)$0.07 in · $0.281 out
- Novita AI$0.07 in · $0.281 out
- LLM Gateway$0.07 in · $0.281 out
- Kenari$0.0714 in · $0.286 out
- CrossModel$0.08 in · $0.32 out