Tencent Hy4 Preview

tencent/hy4-preview

Run Tencent Hy4 Preview in a hosted Python Task with structured output, extended thinking and file inputs.

Tencent's Hy4 preview via OpenRouter. A mixture-of-experts model (770B total, 49B active parameters) for coding agents and multi-step tool use, with a 1M token context window.

What Tencent Hy4 Preview supports in qbash

Structured outputReplies as JSON that matches a schema you pass.
Extended thinkingReasons through a problem before it replies.
Reasoning effort2 levels, from low to high.
Document inputReads PDF, TEXT, DOC, XLS, RTF and 7 more files.
Prompt cachingRepeated input is billed at the cached rate.

What is qbash?

qbash is where you build Tasks: Python programs that run a business process on managed infrastructure. Your code runs the steps and calls a model like Tencent Hy4 Preview only at the ones that need judgment, with integrations, memory and files available in the same script.

A developer writes the Task once, and anyone on the team runs it from a form, on a schedule, from a webhook or from chat. Each Task is versioned and every run is logged.

How Tasks work

Specifications

Context window: 1.05Mtokens
Max output: 131,072tokens
Temperature: 0 to 1default 1

Structured output with Tencent Hy4 Preview in a Python Task

qbash.ai.raw calls Tencent Hy4 Preview from a Task. Pass a JSON Schema as output_schema and the reply comes back as a Python dict that matches it, ready to route to a connector.

main.py
ticket = qbash.inputs.get("ticket")

triage = qbash.ai.raw(
    f"Summarize this support ticket and rate its urgency:\n\n{ticket}",
    model="tencent/hy4-preview",
    output_schema={
        "type": "object",
        "properties": {
            "summary": {"type": "string"},
            "urgency": {"type": "string", "enum": ["low", "medium", "high"]},
        },
        "required": ["summary", "urgency"],
    },
)

# triage is a dict, e.g. {"summary": "...", "urgency": "high"}
if triage["urgency"] == "high":
    qbash.integrations.slack.create_message(
        channel="#support",
        text=triage["summary"],
    )

qbash.output(triage)

Structured output in Tasks

Reasoning effort with Tencent Hy4 Preview

Set Effort to low and high in the prompt's Settings. Higher effort spends more tokens on reasoning before the reply.

Turn on Thinking in the same Settings popover to have Tencent Hy4 Preview reason through a problem before it replies.