gpt-oss-120b

openai/gpt-oss-120b

Run gpt-oss-120b in a hosted Python Task with structured output, extended thinking and file inputs.

OpenAI's open-weight gpt-oss-120b via OpenRouter. A 117B-parameter mixture-of-experts reasoning model with 5.1B active parameters and a 131K token context window.

What gpt-oss-120b 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.
Document inputReads PDF, TEXT, DOC, XLS, RTF and 7 more files.

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 gpt-oss-120b 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: 131Ktokens
Max output: 117,964tokens
Temperature: 0 to 1default 1

Structured output with gpt-oss-120b in a Python Task

qbash.ai.raw calls gpt-oss-120b 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="openai/gpt-oss-120b",
    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 gpt-oss-120b

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 gpt-oss-120b reason through a problem before it replies.

gpt-oss-120b pricing

Input	$0.037 per 1M tokens
Output	$0.17 per 1M tokens

Standard rates in USD.

Supported file formats

Documents

PDF
TEXT
DOC
XLS
RTF
DOCX
XLSX
PPTX
PPT
ODT
ODP
ODS