LLM Query Action

misc_action.llm_query sends a prompt directly to an LLM and stores the structured response—no browser state, axtree, or screenshot is involved.

Overview

Use when: You need to transform, classify, or reason over data already in memory (e.g., reformat an extracted date, classify extracted text, compute a derived value).
Execution: The action sends prompt_instructions to the configured LLM, parses the response according to output_format, and stores results in output_data. Specified fields are optionally promoted to generated_variables.
No browser access: Unlike extraction_action.llm, this action does not read the current page. Reference earlier extracted values via {variable_name[index]} in your prompt.

Properties

Property	Type	Default	Description
`output_format`	`dict`	Required	Expected output structure as a type-annotated dict
`prompt_instructions`	`str`	Required	The full prompt to send to the LLM
`output_variable_names`	`list[str] \| None`	`None`	Promote response fields to `generated_variables`
`llm_model_name`	`str \| None`	`None`	LiteLLM model string, e.g. `"gemini/gemini-2.5-pro"`. Falls back to the task model, then `LLM_MODEL`
`llm_provider`	`str \| None`	`None`	Deprecated — prefix the provider in `llm_model_name` instead

JSON Example

{
  "type": "action_node",
  "misc_action": {
    "llm_query": {
      "output_format": {
        "category": "str",
        "confidence": "str"
      },
      "prompt_instructions": "Classify the following support ticket as 'billing', 'technical', or 'other'. Ticket: {ticket_text[0]}",
      "output_variable_names": ["category"]
    }
  }
}

Output Format

Define the expected response structure with Python type hints:

{
  "output_format": {
    "summary": "str",
    "status": "str",
    "items": "List[str]"
  }
}

Only str and List[str] are supported types in output_format.

Using Variables in Prompts

Reference extracted values from earlier nodes using {variable_name[index]}:

{
  "misc_action": {
    "llm_query": {
      "output_format": { "normalized_date": "str" },
      "prompt_instructions": "Reformat this date to ISO 8601 (YYYY-MM-DD): {raw_date[0]}",
      "output_variable_names": ["normalized_date"]
    }
  }
}

After this action, {normalized_date[0]} is available in subsequent nodes.

Storing Output as Variables

Set output_variable_names to promote response fields into generated_variables:

{
  "misc_action": {
    "llm_query": {
      "output_format": {
        "next_url": "str",
        "has_more_pages": "str"
      },
      "prompt_instructions": "Given these pagination links: {page_links[0]}, return the next page URL and whether more pages exist ('true'/'false').",
      "output_variable_names": ["next_url", "has_more_pages"]
    }
  }
}

Every key in output_variable_names must appear in output_format. Validation fails at schema load time if a key is missing.

Choosing a Model

Set llm_model_name to any LiteLLM model string:

Model	Notes
`gemini/gemini-3.5-flash-lite`	Default; cost-effective
`gemini/gemini-2.5-flash`	Previous default
`gemini/gemini-2.5-pro`	Harder reasoning over extracted data
`anthropic/claude-sonnet-4-6`	Strong reasoning
`openai/gpt-4.1-mini`	OpenAI models

Omit llm_model_name to use the task model, which itself falls back to the LLM_MODEL environment variable. See Model Configuration.

LLM Query vs LLM Extraction

	`misc_action.llm_query`	`extraction_action.llm`
Browser context	None — prompt only	axtree and/or screenshot of current page
Typical use	Transform / classify in-memory data	Extract data from the page the browser is on
Input source	Variables embedded in the prompt	Live page content
Output destination	`output_data` + optional `generated_variables`	`output_data` + optional `generated_variables`

Use misc_action.llm_query after an extraction step to post-process or validate extracted data without consuming a browser round-trip.

Quickstart

Building Automations

Action Types

Inference

Advanced

FAQs

Overview

Properties

JSON Example

Output Format

Using Variables in Prompts

Storing Output as Variables

Choosing a Model

LLM Query vs LLM Extraction

​Overview

​Properties

​JSON Example

​Output Format

​Using Variables in Prompts

​Storing Output as Variables

​Choosing a Model

​LLM Query vs LLM Extraction

Overview

Properties

JSON Example

Output Format

Using Variables in Prompts

Storing Output as Variables

Choosing a Model

LLM Query vs LLM Extraction