Grok 4.6

xAI xAI docs

grok-4.6

Run Grok 4.6 in a hosted Python Task with structured output, web search, X search and file inputs.

xAI's previous frontier model for coding and agentic work.

What Grok 4.6 supports in qbash

Structured outputReplies as JSON that matches a schema you pass.
Web searchSearches the web while it answers.
X searchSearches posts on X while it answers.
Reasoning effort4 levels, from low to xhigh.
Image inputReads JPEG and PNG 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 Grok 4.6 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: 500Ktokens
Max output: 131,072tokens

Structured output with Grok 4.6 in a Python Task

qbash.ai.raw calls Grok 4.6 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="grok-4.6",
    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

Use Grok 4.6 with web search

Turn on Web Search in an inline prompt's model bar and Grok 4.6 searches the web while it answers. xAI models can search posts on X the same way.

Provider web tools

Reasoning effort with Grok 4.6

Set Effort to low, medium, high and xhigh in the prompt's Settings. The default is high. Higher effort spends more tokens on reasoning before the reply.

Grok 4.6 pricing

Input	$2.00 per 1M tokens
Output	$6.00 per 1M tokens
Cached input	$0.50 per 1M tokens
Input, above 200K input tokens	$4.00 per 1M tokens
Output, above 200K input tokens	$12.00 per 1M tokens

Standard rates in USD.

Supported file formats

Images

JPEG up to 20 MB
PNG up to 20 MB

Documents

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

Grok models need documents uploaded to the xAI Files API before they can be used in chat. xAI stores those files for up to 30 days and does not train on them under its Enterprise API terms. xAI Privacy Policy