---
id: "tencent/hy3-preview"
also: ["tencent/hy3-preview-20260421", "tencent/Hy3-preview"]
cheapest_list_usd_per_m: "0.18 in, 0.6 out, at gmicloud/bf16 on openrouter"
cheapest_effective_usd_per_m: "0.1161 in, 0.5998 out, at gmicloud/bf16 on openrouter"
context: 262144
max_output: 235929
input: ["text"]
output: ["text"]
released: "2026-04-22"
reasoning: ["high", "low", "none"]
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["include_reasoning", "max_tokens", "reasoning", "reasoning_effort", "seed", "temperature", "tool_choice", "tools", "top_p"]
endpoints: 1
gateways: "openrouter (1)"
no_training: 1
trains: 0
retains_prompts: 1
coding: 58.8000
agentic: 24.1000
---
# Tencent: Hy3 preview

Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...