Hy4 on Together AI

Hunyuan · Tencent AI Lab

Serverless
Open Weights

Last refreshed 2026-11-20. Next refresh: weekly.

Why use Hy4 on Together AI?

Together AI offers Hy4 with pay-as-you-go pricing at $0.83/1M input tokens. Together AI is a platform for running open-source and proprietary LLMs with fast serverless and dedicated endpoints at competitive inference pricing.

Compare Hy4 across 5 providers to find the best fit for your use case
Input / 1M
$0.834
Output / 1M
$2.50
Cache
read $0.042
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install together
Auth
export TOGETHER_API_KEY=...
Call
from together import Together
client = Together()  # reads TOGETHER_API_KEY from env
response = client.chat.completions.create(
    model="tencent/Hy4",
Model ID
tencent/Hy4

Request example

from together import Together

client = Together()  # reads TOGETHER_API_KEY from env
response = client.chat.completions.create(
    model="tencent/Hy4",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Gotchas

  • Use provider model ID "tencent/Hy4", not the LLMReference slug "hy4".
  • Together uses "organization/model-name" format, e.g. "meta-llama/Llama-4-Scout-17B-16E-Instruct" or "Qwen/QwQ-32B". See the Together model catalog for the exact ID.
  • The examples expect TOGETHER_API_KEY; rename it only if your application config maps the new variable.

Compare Hy4 Across Providers

ProviderInput (per 1M)Output (per 1M)
Tencent Cloud TI Platform$0.83$2.50
OpenRouter——
Vercel AI Gateway——
AtlasCloud——
Together AI$0.83$2.50

Pricing

TypePrice (per 1M)
Input tokens$0.83
Output tokens$2.50

Capabilities

VisionMultimodalPrompt Caching

About Hy4

Hy4 is Tencent’s multimodal mixture-of-experts flagship, with a 770B-parameter language backbone and 49B active parameters per token. It supports text, image and video understanding with a 1,048,576-token context. Tencent released its instruct and base weights under the Tencent Hy License, with additional commercial terms for large model-as-a-service businesses.

Get Started

Model Specs

Released2026-11-04
Parameters770B (49B active)
Context1M