Hy4 Preview
hy4-previewtencent/hy4-preview- 🧠 770B-parameter Mixture-of-Experts flagship, 49B parameters active per token
- 📏 1M-token context window for long-horizon work
- 🆕 Released 28 August 2026 by Tencent's Hy team
- 🔧 Gated sparse attention with IndexCache plus identity Hyper-Connections residuals
- 🎯 Post-trained for software engineering, office, data analysis, research
- 💬 Reasoning, function calling and web search among listed capabilities
- 🔒 Open weights under the Apache 2.0 license
- ⚡ Served here in FP4 quantization
Tencent is a Chinese multinational technology conglomerate headquartered in Shenzhen, and one of the world's highest-grossing multimedia companies by revenue. Best known for its sprawling presence in social platforms, digital services, and as the largest player in the global…
Explore 2 more models by Tencent →Hy4 Preview is the Tencent Hy Team's Mixture-of-Experts flagship, published on 28 August 2026 under the Apache 2.0 license with open weights on Hugging Face. The catalog listing describes 770 billion total parameters with 49 billion activated per token and a context window of roughly 1.05 million tokens, served in FP4 quantization.
Against its same-family predecessor, the jump is primarily one of scale: Tencent states on the model card that it scaled the model on three fronts simultaneously — model size, context length, and training data. Architecturally, the attention module uses Gated DeepSeek Sparse Attention with IndexCache for cross-layer sparse index reuse, while the residual pathway adopts identity Hyper-Connections to widen inter-layer information flow.
Positioning is agentic and work-oriented rather than general chat. The model is post-trained for software engineering, office and data analysis, game development, and scientific research, with emphasis on long-horizon reasoning and tool use; listed capabilities include reasoning, code optimization, function calling and web search. The very large context window is the natural complement to that focus, supporting whole-repository or multi-document sessions.
Tencent frames this as a deliberately early release, writing on the model card that it would "rather ship early and hear what breaks," the same iterative approach it credits for improving the prior Hy generation.
Sources: [1] tencent/Hy4-preview model card, Hugging Face.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
Daily usage · Hy4 Preview · Organic sellers
| Seller | Health | Rep↓ | Sales | Tokens | Routing | Input $/M | Cached $/M | Output $/M | Save |
|---|---|---|---|---|---|---|---|---|---|
| Super Seeder 0xd19f…41f3 | healthy | 89.22 | $0.00 | 3.25k | #1 | $1.3031 | $0.0656 | $3.9079 | — |
| Sapiens 0x1fae…8318 | healthy | 8.21 | $0.00 | 1.80k | gated | $1.1077 | $0.0558 | $3.3217 | — |
| Fire Ant 🔥🐜 0xbe05…bc5d | — | 0.00 | $0.00 | 10.17k | gated | $0.9383 | $0.0458 | $2.8136 | — |
| LLMart 0x948a…a000 | — | 0.00 | $0.00 | 1.80k | gated | $0.8099 | $0.0406 | $2.5051 | — |
"Best price" and the seller table are live Antseed catalog data (advertised $/1M tokens — or $ per generated image for unit-billed image models — not settled amounts). Reputation = buyer trust score (0-100, the Antseed SDK's own formula). "Routing" = the SDK's default buyer routing (what the VPR desktop app ships with): a trust ≥ 60 gate on the effective reputation, then cheapest-first among routable sellers; live failover state (per-peer cooldowns) is buyer-side runtime and not included. Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase. "Usage on Antseed" counts only settlements whose buyers share the per-model split on-chain (metadata v2/v3, opt-in), so every usage figure is a lower bound.