Large Language Modelhy4-preview

Hunyuan 4 Preview

Dual-Speed MoE

Tencent Hunyuan 4 next-generation MoE frontier model with dual-speed reasoning, deep Chinese semantic comprehension, and enterprise agent tool integration.

AvailableMoE TransformerProprietary

Params

MoE 256K

Context

256K

Max Output

32K

API Surface/v1/chat/completions

Capabilities & Performance

  • Dual-speed reasoning architecture with adaptive slow-thinking CoT mode
  • Starting at $0.968/M input, $2.903/M output on BatchIn SLA

Transparent Pricing

LanePublic RateCached
Realtime API$0.97 / $2.90$0.194

Prices per 1M tokens. Cached prompt rate applies on prefix hits.

100% OpenAI-Compatible Code

Drop-in API Examples

Python (OpenAI SDK)
from openai import OpenAI

client = OpenAI(
    base_url="https://api.batchin.tech/v1",
    api_key="BATCHIN_API_KEY"
)

resp = client.chat.completions.create(
    model="hy4-preview",
    messages=[{"role": "user", "content": "Benchmark system architecture performance and cost profile."}]
)

print(resp.choices[0].message.content)
JavaScript / Node.js
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.batchin.tech/v1",
  apiKey: process.env.BATCHIN_API_KEY,
});

const resp = await client.chat.completions.create({
  model: "hy4-preview",
  messages: [{ role: "user", content: "Benchmark system architecture performance and cost profile." }],
});

console.log(resp.choices[0]?.message?.content);
cURL / Shell
curl https://api.batchin.tech/v1/chat/completions \
  -H "Authorization: Bearer $BATCHIN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "hy4-preview",
    "messages": [{"role":"user","content":"Benchmark system architecture performance and cost profile."}]
  }'

Related Next-Gen Models

View all models →
qwen3.8-maxQwen

Qwen 3.8 Max

Alibaba 2.4-trillion-parameter MoE flagship model with native 1M context, state-of-the-art autonomous coding, and comprehensive multimodal reasoning. Supports deterministic 0902 snapshot alias.

deepseek-v4-proDeepSeek

DeepSeek V4 Pro

DeepSeek next-gen MoE reasoning flagship for complex architectural design, autonomous coding loops, and math proofs.

glm-5.3Zhipu AI

GLM-5.3

Zhipu AI flagship model with upgraded reasoning, deep tool invocation capabilities, and Chinese enterprise alignment.