Compositev12
← All models Model directory

AI model

Tencent: Hy4 preview (Reasoning)

tencent/hy4-preview-reasoning

Tencent: Hy4 preview (Reasoning) is a 1,048,576-token model served on Composite at $1.04 per million tokens in and $3.13 per million tokens out.

Try in Playground

Community rating

— No community ratings yet.

Sign in to rate this model. Ratings come from accounts that have run requests through Composite.

Specifications

Specifications and pricing as served by Composite
Model IDtencent/hy4-preview-reasoning
Providercv11
Context window1,048,576 tokens
Acceptstext
Returnstext
Input price$1.04 per million tokens
Output price$3.13 per million tokens
Prompt cachingSupported — cached input is billed at the provider's cache rate, on credits and plans alike
ThinkingOptional - see "Tencent: Hy4 preview (Reasoning) (Reasoning)" in the catalog to turn it on by default
ModeratedNo
Cost on a monthly planAbout 9.2 plan credits per typical call (8k in, 1k out)
Routing endpoints1

Measured on Composite

This model has not carried enough traffic on Composite yet to publish a success rate, a latency figure or a traffic rank. The numbers appear here once it has.

Pricing

$1.04 per million tokens input · $3.13 per million tokens output

Credits pay the provider’s price plus 25%; cache hits cost less.

On a monthly plan, a typical call (8k tokens in, 1k out) uses about 9.2 plan credits, at the provider's own price.

Provider

cv11

Roleplay fit

This model is available on Composite alongside dozens of others from other labs, so it is easy to compare against similar options.

Context behavior

With a 1,048,576-token context window, it can hold a long-running roleplay or a full lorebook in memory without losing earlier plot details, so it suits multi-session campaigns and character cards with heavy backstory.

Cost for regular use

It sits in the mid-range on price, a reasonable pick for regular roleplay use without going for the cheapest option available.

From the provider

Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...

Supplied by cv11, not written by Composite.