
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.
Modalities
Price
Free
Context
262K
Released
Jul 6, 2026
Token volume and request traffic to this model over time.
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.
Yes. The pricing shown on this page for Hy3 is zero, so you are not charged for prompt or completion tokens. Free endpoints are rate limited — see the rate limit docs.
Hy3 has a 262,144 token context window.
Hy-MT2-1.8B, Hy-MT2-30B-A3B, Hy3 preview and 1 more are other text models from Tencent.
Hy3 was released on July 6, 2026.