Question 1

What is Hy4 preview?

Accepted Answer

Hy4 preview is a model from Tencent, released on Aug 28, 2026. 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...

Question 2

How much does Hy4 preview cost?

Accepted Answer

On the Respan gateway, input starts at $0.75 per 1M tokens on Novita, and output starts at $2.25 per 1M tokens on Novita, after gateway discounts. Averaged across 3 providers, it costs $0.81 per 1M input tokens and $2.42 per 1M output tokens.

Question 3

Which providers serve Hy4 preview on Respan?

Accepted Answer

3 providers serve Hy4 preview: Novita, DeepInfra, and OpenRouter.

Question 4

What is Hy4 preview's context window?

Accepted Answer

Hy4 preview accepts up to 1.0M tokens of context on its largest provider route.

Question 5

How do I use Hy4 preview with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "hy4-preview". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Hy4 preview?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 19 tokens per second, and the lowest response latency was 3.4 seconds on OpenRouter. Speed varies with request size and provider.

Question 7

Where does Hy4 preview rank on the Respan Index?

Accepted Answer

Hy4 preview scores 46.6 out of 100 on the Respan Index v1.1, ranking #31 of 138 models. By category: Coding 25.3, Agents 65.3, Reasoning 43.3, Knowledge & language 47.4 (estimated), and Human preference 56.0. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

Question 8

How does Hy4 preview score on benchmarks?

Accepted Answer

Hy4 preview has 18 published benchmark scores, including Terminal-Bench 2.1 85.4%, WideSearch 83.9%, and GPQA Diamond 92.3%. Each score links to where it was published; the data is collected by llmmetric.com.

Provider	Context	Input	Output
NovitaSave 10%`novita/tencent/hy4-preview`	1M	$0.75/M	$2.25/M
DeepInfra`deepinfra/tencent/Hy4-preview`	1.0M	$0.83/M	$2.50/M
OpenRouter`openrouter/tencent/hy4-preview`	1.0M	$0.83/M	$2.50/M

Hy4 preview

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Benchmarks

Respan Indexv1.1

Coding7

Apps

Hy4 preview FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.

Agents5

Reasoning3

Math1

Arena2