SF·SIX / MODEL PROFILE
Tencent Hy3
Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...
Tencent Hy3 costs $0.132 per 1M input tokens and $0.528 per 1M output tokens at the standard tier, the lowest default-region price among the 5 providers SF·SIX tracks, from Tencent (fp8). Cached input reads cost $0.033 per 1M tokens. Updated ; prices checked .
- Developer
- Tencent
- Input modalities
- text
- Output modalities
- text
- Context tokens
- 262,144
- Latest price observation
- 2026-10-17
- Lowest paired standard token quote
- $0.132 input / $0.528 output per 1M tokens
Dated price and provider records
| Provider and channel | Input | Output or native rate | Unit and status | Source and observation |
|---|---|---|---|---|
| TencentOpenRouter | $0.132 | $0.528 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| GMI CloudOpenRouter | $0.14 | $0.58 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Novita AIOpenRouter | $0.14 | $0.58 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| PhalaOpenRouter | $0.15 | $0.64 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| AtlasCloudOpenRouter | $0.20 | $0.80 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
These are dated, non-executable observations. Verify the exact endpoint, price and terms with the source before use. Unknown values are not free.