---
id: "tencent/hy4-preview"
also: ["tencent/hy4-preview-20260827", "tencent/Hy4-preview", "hf/tencent/Hy4-preview", "requesty/tencent/hy4-preview", "vercel/tencent/hy4-preview"]
card_usd_per_m: "0.834 in, 2.501 out, at tencent/fp8"
cheapest_list_usd_per_m: "0.834 in, 2.501 out, at deepinfra on hf"
cheapest_effective_usd_per_m: "0.0593 in, 2.501 out, at tencent on requesty"
context: 1048576
max_output: 64000
input: ["text"]
output: ["text"]
released: "2026-08-28"
reasoning: ["high", "low", "none"]
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_completion_tokens", "max_tokens", "min_p", "presence_penalty", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 10
gateways: "openrouter (6), hf (2), requesty (1), vercel (1)"
no_training: 7
trains: 1
retains_prompts: 3
---
# Tencent: Hy4 preview

Tencent Hy4 preview is Tencent Hy’s open-source large language model, featuring 770B total parameters, 49B active parameters, and a context window exceeding 1 million tokens. Built for real-world productivity, it supports long-horizon coding, cross-document analysis, office content creation, game development, and scientific reasoning, making it well-suited to complex agents and multi-step professional workflows.