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: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings.
Tencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.
現在、EU 域内ルーティングでは利用できません。 リージョン内ルーティングのドキュメント
| $0.132$0.0825 | $0.528$0.33 | $0.033$0.020625 | 2.95s | 58 tps | ||
| $0.14 | $0.58 | $0.035 | 3.06s | 64 tps | ||
| $0.14 | $0.58 | $0.035 | 2.30s | 45 tps | ||
| $0.20 | $0.80 | $0.05 | 2.04s | 31 tps | ||
| $0.15 | $0.64 | $0.04 | 1.77s | 33 tps |
P50、プロバイダー全体での最良値
P50、最適なプロバイダー
上流のプロバイダーでエラーが発生した場合、リクエストフィルターが許可していれば、別の正常なプロバイダーにルーティングして復旧できます。プロバイダーごとの稼働率データにプログラムでアクセスするには Endpoints APIを利用できます。詳しくは、 負荷分散とプロバイダールーティングのオプションをご覧ください。
