Tencent Hunyuan Hy4 Is Live on APIYI

​

Key Highlights

• Official release is live: hy4 is available on APIYI through the OpenAI-compatible /v1/chat/completions endpoint in the Default and SVIP groups
• 770B MoE, 49B active: each inference activates roughly 6.4% of the parameters, decoupling knowledge capacity from per-call cost
• 960K input / 64K output: the official context claim exceeds one million tokens, while the TokenHub limit is 960K input and 64K output
• First Hunyuan model that sees and acts: vision understanding and Computer Use arrive together, covering graphical interfaces and command-line software operation
• Hallucination rate nearly halved: down from 12.95% to 7.2%, with guess-induced errors falling from 23.1% to 5.6%

​

Background

​

Deep Dive

​

Specs: 770B MoE with a 960K context

​

Two firsts: reading images and taking action

​

Measured results across six scenarios

​

Reliability: hallucination and guessing rates

• Hallucination rate: 12.95% → 7.2%
• Guess-induced error rate: 23.1% → 5.6%

​

Practical Use

​

Code example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["APIYI_API_KEY"],
    base_url="https://api.apiyi.com/v1"
)

response = client.chat.completions.create(
    model="hy4",
    messages=[
        {"role": "system", "content": "You are a senior financial analyst. Lead with the conclusion, then list the evidence."},
        {"role": "user", "content": "Turn this quarterly report into a table of revenue, gross margin, and operating cash flow, then name the one point most worth pressing on."}
    ],
    stream=True
)

for chunk in response:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

​

Where it fits

​

Usage notes

1. Vision is available now; validate Computer Use first: pass images directly in messages to use vision understanding, and image tokens bill as input. Computer Use is a new upstream capability, so verify it with a single request in your own format before depending on it in production.
2. Put stable content first: cache hits cost about 5.3% of the input price, so keep system prompts, long documents, and conversation history at the front.
3. Sandbox long-running tasks: run Computer Use workflows in an isolated environment before granting production access.
4. Budget by usage: long contexts and image input raise real token consumption, so do not estimate cost from the unit price alone.

​

Pricing and Availability

​

Pricing

​

Available groups

​

Stacking recharge promotions

​

Summary and Recommendations

• Long documents and code understanding: 960K input with 64K output — a candidate to replace chunk-based pipelines first
• Finance, research, and due diligence: first among open models on the financial test, and more trustworthy with the lower hallucination rate
• Agents and GUI automation: validate Computer Use stability in a sandbox, then widen permissions gradually
• Cost-sensitive, high-volume short text: Hy4 costs more than Hy3, so Hy3 remains the better choice for that workload