Grok 4.20 Reasoning
grok-4.20-0309-reasoningRun Grok 4.20 Reasoning in a hosted Python Task with structured output, web search, X search and file inputs.
xAI's March 2026 reasoning model for complex tasks and tool calling. Supports X search and web search.
What Grok 4.20 Reasoning 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.
- 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 4.20 Reasoning 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.
Specifications
- Context window
- 1Mtokens
- Max output
- 131,072tokens
- Temperature
- 0 to 2default 1
Structured output with Grok 4.20 Reasoning in a Python Task
qbash.ai.raw calls Grok 4.20 Reasoning 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.
ticket = qbash.inputs.get("ticket")
triage = qbash.ai.raw(
f"Summarize this support ticket and rate its urgency:\n\n{ticket}",
model="grok-4.20-0309-reasoning",
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)
Use Grok 4.20 Reasoning with web search
Turn on Web Search in an inline prompt's model bar and Grok 4.20 Reasoning searches the web while it answers. xAI models can search posts on X the same way.
Grok 4.20 Reasoning pricing
| Input | $1.25 per 1M tokens |
|---|---|
| Output | $2.50 per 1M tokens |
| Cached input | $0.20 per 1M tokens |
| Input, above 200K input tokens | $2.50 per 1M tokens |
| Output, above 200K input tokens | $5.00 per 1M tokens |
Standard rates in USD.
Supported file formats
Images
- JPEG up to 20 MB
- PNG up to 20 MB
Documents
- 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