Tencent
Hy3 preview
Tencent Hy reasoning model for coding, instruction following, and agent tasks
Model facts
- Context window
- 262K tokens
- Maximum output
- 236K tokens
- Cheapest paid input
- $0.066 per 1M tokens
- Cheapest paid output
- $0.26 per 1M tokens
- Open weights
- yes
- Providers
- 6
Capabilities and modalities
reasoning, tool calling, structured output, temperature control, open weights, text.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| Reasoning | 34.4 | not measured | not measured | not measured |
| Non-reasoning | 26.6 | not measured | not measured | not measured |
Observed price history
- 2026-08-24: $0.066 input / $0.26 output per 1M tokens
API providers
- Tencent TokenHub — model id hy3-preview; free input / free output per 1M tokens; provider documentation
- SiliconFlow — model id tencent/Hy3-preview; $0.066 input / $0.26 output per 1M tokens; provider documentation
- AIHubMix — model id hy3-preview; $0.17 input / $0.567 output per 1M tokens; provider documentation
- ZenMux — model id tencent/hy3-preview; $0.172 input / $0.572 output per 1M tokens; provider documentation
- Kilo Gateway — model id tencent/hy3-preview; $0.18 input / $0.6 output per 1M tokens; provider documentation
- OpenRouter — model id tencent/hy3-preview; $0.18 input / $0.6 output per 1M tokens; provider documentation