Roar AI
DiscordGet started
All models
Tencent · Open weights

Hunyuan Hy3

Hunyuan Hy3 costs $0.1365 per million input tokens and $0.5655 per million output tokens on Roar AI. Tencent’s open flagship, switching between quick answers and deep reasoning.

Input$0.1365per 1M tokens
Output$0.5655per 1M tokens
Context window256Ktokens

Hunyuan Hy3 API pricing

Input$0.1365 per 1M tokens
Output$0.5655 per 1M tokens
Cached input$0.0429 per 1M tokens

Example: 1,000 requests with 3,000 input and 1,000 output tokens each cost $0.97. Every rate is published and stays the same from one request to the next. See every model.

Rates as of 20 November 2026.

Specs

Made byTencent
ReleasedJuly 2026
TypeChat
Context window256K tokens
ReadsText
Thinks before answeringYes, adjustable
WeightsOpen (Apache 2.0)
Size295B total, 21B active
Processed inGlobal
Model idhy3

About Hunyuan Hy3

Hy3 is the model behind Tencent’s own products, including its coding assistant, the Yuanbao chatbot and features inside WeChat. It is a mixture-of-experts model with 295 billion parameters, 21 billion active per token, and Tencent says it reasons as well as flagships two to five times its size. Its model card reports 90.4% on GPQA Diamond and 78% on SWE-bench Verified.

It has two speeds: a no-think mode for direct answers and a high-effort mode for hard problems. Tencent says it cut its rate of made-up answers to 5.4%. The weights are open under Apache 2.0.

What is Hunyuan Hy3 good for?

  • Coding agents on a budget.
  • Office and productivity assistants.
  • Mixed work that switches between quick answers and deep reasoning.

Hunyuan Hy3 limitations

  • Text only.
  • Tencent’s own figures still show a 12.7% error rate on commonsense questions, and its benchmarks are self-reported.

How to use the Hunyuan Hy3 API

Use the OpenAI SDK you already have: point it at Roar AI and set the model name. Read the docs.

from openai import OpenAI

client = OpenAI(base_url="https://api.roar-ai.com/v1", api_key="roar_live_…")

reply = client.chat.completions.create(
    model="hy3",
    messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)

Hunyuan Hy3 FAQ

How much does Hunyuan Hy3 cost?

Input is $0.1365 per 1M tokens; output is $0.5655 per 1M tokens. For example, 1,000 requests with 3,000 input and 1,000 output tokens each cost $0.97.

Can I use Hunyuan Hy3 alongside other models?

Yes. Every model on Roar AI is on the same API key and the same monthly invoice, so switching from Hunyuan Hy3 to another model only means changing the model name in your code.

Is Hunyuan Hy3 open source?

Its weights are open under the Apache 2.0 licence, so you could run it yourself. Through Roar AI you call it like any other model, with no servers to manage.

What is the context window of Hunyuan Hy3?

Hunyuan Hy3 can read up to 256K tokens in one request.

Can Hunyuan Hy3 read images and PDFs?

It reads text only. You can still send it a PDF: Roar AI turns each page into text first, at no extra charge. Scanned pages need a model that can see images.

Start using Hunyuan Hy3

Create a free account, get an API key and call Hunyuan Hy3 with the OpenAI SDK.