Hy3
Provider：Tencent Hunyuan
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:...
Key specs
- Context：262.1K
- Max output：128K
- Tokenizer：Other
- Released：2026-07-06
Token pricing
- Input price：$0.132 / 1M tokens
- Output price：$0.528 / 1M tokens
- Cache read：$0.033 / 1M tokens
- Blended price：$0.231 / 1M tokens
Modalities
Text
Use Cases
- Deep Reasoning & Analysis：Process long legal docs, academic papers, financial reports; multi-hop reasoning and evidence-chain tracing across huge contexts.（≈ $0.0042/call）
- Chat & Support：FAQ auto-response, multi-turn dialogue, emotion detection — e-commerce, finance, gov.（≈ $0.0026/turn）
When to pick this model
Signals derived from public pricing and spec fields — not a benchmark. Validate with official docs and your own eval.
- Low input + output price: solid fit for high-frequency calls and batch processing.
- Low blended price: budget-friendly for fleet-scale deployment.
- Long max output (>=30K tokens): strong fit for deep report / essay / document-drafting workflows.
FAQ
- What is the token pricing of Hy3? Input price $0.132 / 1M tokens, output price $0.528 / 1M tokens, blended about $0.231 / 1M tokens. Refer to Tencent Hunyuan’s official page for the exact rate.
- What context window does Hy3 support? Context window is 262.1K, max output about 128K, suitable for long documents, multi-turn chat and complex reasoning.
- What scenarios is Hy3 best for? Based on its capability and pricing, Hy3 fits best: Deep Reasoning & Analysis, Chat & Support. See the Use Cases section for details and cost estimates.
- What input/output modalities does Hy3 support? Supports Text modality.
- Is Hy3 a free model? Hy3 is billed per token, not a free model.
- Which provider offers Hy3? Hy3 is offered by Tencent Hunyuan.
More models from Tencent Hunyuan
Full info：Hy3