GPT-4.5 Preview

gpt-4.5-preview

Run GPT-4.5 Preview in a hosted Python Task with structured output, file inputs and MCP connectors.

⚠️ Retired model no longer available via API. This model was retired on July 14, 2025. OpenAI recommends using GPT-4.1 or o-series models instead.

Deprecated model

This model is deprecated and not recommended for new projects. It retires on July 14, 2025.

What GPT-4.5 Preview supports in qbash

Structured outputReplies as JSON that matches a schema you pass.
MCP connectorsCalls tools on MCP connectors during a request.
Image inputReads WEBP, PNG, JPEG and GIF images.
Document inputReads TEXT, PDF, DOC, DOCX, XLSX and 1 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-4.5 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: 128Ktokens
Max output: 16,384tokens
Temperature: 0 to 2default 1

Structured output with GPT-4.5 Preview in a Python Task

qbash.ai.raw calls GPT-4.5 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="gpt-4.5-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

Connect GPT-4.5 Preview to MCP servers

In qbash chat and a Task's inline prompts, you can attach MCP connectors to GPT-4.5 Preview. It calls their tools during the request, for example to read a Postgres table or post to a Slack channel.

This is MCP on the model side. Adding MCP servers to Codex or ChatGPT is a separate setup, and qbash can publish your Tasks as an MCP server for those clients as well.

Browse connectors Connect a client

Supported file formats

Images

WEBP up to 20 MB
PNG up to 20 MB
JPEG up to 20 MB
GIF up to 20 MB

Documents

TEXT
PDF
DOC
DOCX
XLSX
PPTX