Is Hy3 preview available on FastMetal?

Not at the moment. Hy3, from the same lab, is available on the FastMetal API today.

What is the context window of Hy3 preview?

262,144 tokens, shared between the prompt and the response.

Back to Models

Tencent

tencent/hy3-preview

Not Available

Hy3 preview

Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...

4/22/2026

262,144 tokens

Specifications

Modalities

Input

text

Output

text

Supported Parameters

frequency_penalty

include_reasoning

max_tokens

presence_penalty

reasoning

reasoning_effort

seed

stop

temperature

tool_choice

tools

top_k

top_p

Reasoning Configuration

Default: Thinking on (effort: high)
Selectable effort levels: high
low
none
Turning thinking off: Possible (reasoning.enabled: false)

How to control thinking, and what it costs

Data policy

Prompt retention: Unknown — we could not confirm
Training: Unknown — not declared

"Unknown" does not mean "safe". It means we could not confirm it.

Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.

Frequently asked questions

Is Hy3 preview available on FastMetal?: Not at the moment. Hy3, from the same lab, is available on the FastMetal API today.
What is the context window of Hy3 preview?: 262,144 tokens, shared between the prompt and the response.

Models you can use on FastMetal