Hy4 API — Pricing, Access & Documentation

Quick Start: Three Things You Need

Hy4 Preview is served as a hosted API and is OpenAI-compatible. If you have existing OpenAI SDK code, you only need to change the base_url and model fields.

Get Your Free API Key →

Code Examples

cURL

curl https://tokenra.io/v1/chat/completions \
  -H "Authorization: Bearer $TOKENRA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tencent/hy4-preview",
    "messages": [
      {"role": "user", "content": "Explain the difference between MoE and dense models."}
    ]
  }'

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    base_url="https://tokenra.io/v1",
    api_key="YOUR_TOKENRA_API_KEY",
)

response = client.chat.completions.create(
    model="tencent/hy4-preview",
    messages=[
        {"role": "user", "content": "Explain the difference between MoE and dense models."}
    ],
)

print(response.choices[0].message.content)

Node.js (OpenAI SDK)

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://tokenra.io/v1',
  apiKey: 'YOUR_TOKENRA_API_KEY',
});

const completion = await client.chat.completions.create({
  model: 'tencent/hy4-preview',
  messages: [{ role: 'user', content: 'Hello, Hy4!' }],
});

console.log(completion.choices[0].message.content);

Hy4 API Pricing (per 1M tokens)

Hy4 Preview uses a single flat rate, unlike DeepSeek's peak/off-peak model. For a full price breakdown against other flagship models, see our Hy4 vs DeepSeek comparison.

Model Specifications

Full architecture details are available on the Hy4 Preview home page.

Frequently Asked Questions