StepFun Step 3.7 Flash

stepfun/step-3.7-flash

Run StepFun Step 3.7 Flash in a hosted Python Task with structured output, extended thinking and file inputs.

StepFun's Step 3.7 Flash via OpenRouter. A mixture-of-experts reasoning model with about 11B active parameters. Accepts image and video input with a 262K token context window.

What StepFun Step 3.7 Flash supports in qbash

Structured outputReplies as JSON that matches a schema you pass.
Extended thinkingReasons through a problem before it replies.
Reasoning effort3 levels, from low to high.
Image inputReads WEBP, PNG, JPEG and GIF images.
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 StepFun Step 3.7 Flash 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: 262Ktokens
Max output: 131,072tokens
Temperature: 0 to 1default 1

Structured output with StepFun Step 3.7 Flash in a Python Task

qbash.ai.raw calls StepFun Step 3.7 Flash 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="stepfun/step-3.7-flash",
    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 StepFun Step 3.7 Flash

Set Effort to low, medium 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 StepFun Step 3.7 Flash reason through a problem before it replies.