Grok (xAI)

Generate text completions using xAI's Grok models.

AI and MLAPI key5 actionsAll integrations

On this page

Connect
Call it from a workflow
Actions (5)
ask_grok
categorize_text
extract_data_from_text
generate_image
custom_api_call
Details

Connect

Auth type: API key (secret_text). Paste the API key (or token) from the provider's settings into the connect dialog. It is encrypted at rest and only decrypted on the server when an action runs.

In the editor: Backend panel, Integrations tab, then Connect. This connects it for the project.
For every project in a workspace: Workspace settings, Integrations.
Owners and admins choose which integrations members may connect in the admin panel (Integrations tab), and can attach their own OAuth app there.

Call it from a workflow

Pass the action name and its input. The call resolves with { success, output, error? }; a missing connection resolves with success false and the reason. See ctx.integrations.invoke and ctx.integrations.call.

Native workflow

// .workflow.js (native ctx)
export async function run(ctx) {
  const res = await ctx.integrations.invoke("grok_xai", "ask_grok", {
    "model": "<model>",
    "messages": []
  });
  if (!res.success) throw new Error(res.error);
  ctx.log.info("Grok (xAI) answered", { output: res.output });
}

defineWorkflow module

// defineWorkflow module (@app/sdk ctx)
import { defineWorkflow } from "@app/sdk";

export default defineWorkflow({
  id: "grok-xai-ask-grok",
  name: "Grok (xAI): Ask Grok",
  description: "Calls Grok (xAI) when a row is created.",
  trigger: { type: "entity_event", entity: "tickets", event: "created" },
  async run(ctx, event) {
    const res = await ctx.integrations.call("grok_xai", {
      "action": "ask_grok",
      "model": "<model>",
      "messages": []
    }) as { success: boolean; error?: string };
    if (!res.success) throw new Error(res.error);
  },
});

From an app (connector proxy)

curl -X POST "$APP_ORIGIN/__appbricx/connector-proxy/grok_xai/ask_grok" \
  -H "Authorization: Bearer $APP_KEY" \
  -H "content-type: application/json" \
  -d '{"props":{"model":"<model>","messages":[]}}'

Actions

ask_grokin catalog

Ask Grok. Send prompts to Grok with real-time search, tools, and structured outputs.

Input	Type	Description
`model`required	id (picked from your account)	Grok model to use for generating the response.
`messages`required	array	Conversation messages for multi-turn conversations.
`quickPrompt`optional	long text	Simple text prompt for single-turn conversations. Ignored if Messages is provided.
`systemMessage`optional	long text	System message to set behavior and context.
`imageUrl`optional	text	Image URL for vision models. Works with quick prompt mode.
`temperature`optional	number	Controls randomness (0-2): 0 = deterministic, 1 = balanced, 2 = creative.
`maxCompletionTokens`optional	number	Maximum tokens for the response.
`responseFormat`optional	one of "text" \| "json_object" \| "json_schema"	Output format for the response.
`jsonSchema`optional	long text	JSON schema for structured output (when response format is json_schema).
`enableRealTimeSearch`optional	boolean	Allow Grok to search the web and X for current information.
`searchMode`optional	one of "auto" \| "on" \| "off"	How to handle real-time data search.
`maxSearchResults`optional	number	Maximum number of search results to use (1-30).
`searchSources`optional	ids (picked from your account)	Sources to search in.
`tools`optional	array	Functions the model can call.
`toolChoice`optional	one of "auto" \| "none" \| "required"	How the model should use tools.
`parallelToolCalls`optional	boolean	Allow model to call multiple tools simultaneously.
`reasoningEffort`optional	one of "" \| "low" \| "high"	How hard reasoning models should think (not for grok-4).
`memoryKey`optional	text	Keep conversation history across runs.

categorize_textin catalog

Categorize Text. Assign categories to input text based on custom or predefined labels.

Input	Type	Description
`model`required	id (picked from your account)	Grok model to use for text categorization.
`text`required	long text	Text content to categorize.
`categories`required	array	Define the categories for classification.
`allowMultiple`optional	boolean	Text can be assigned to multiple categories.
`includeConfidence`optional	boolean	Include confidence scores for each category.
`customInstructions`optional	long text	Additional instructions for categorization.
`enableContextSearch`optional	boolean	Search for additional context to improve categorization.
`temperature`optional	number	Controls randomness (0-2): 0 = deterministic, 1 = balanced, 2 = creative.
`maxCompletionTokens`optional	number	Maximum tokens for the response.
`reasoningEffort`optional	one of "" \| "low" \| "high"	How thoroughly to analyze the text.

extract_data_from_textin catalog

Extract Data From Text. Extract structured data fields from unstructured text (e.g., names, addresses, dates).

Input	Type	Description
`model`required	id (picked from your account)	Grok model to use for data extraction.
`text`required	long text	Text to extract data from.
`extractionPrompt`optional	long text	How to extract the data.
`fields`required	array	Define the structured fields to extract from the text.
`enableContextSearch`optional	boolean	Search for additional context to improve extraction.
`strictExtraction`optional	boolean	Only extract explicitly present information.
`temperature`optional	number	Controls randomness (0-2): 0 = deterministic, 1 = balanced, 2 = creative.
`maxCompletionTokens`optional	number	Maximum tokens for the response.
`reasoningEffort`optional	one of "" \| "low" \| "high"	How thoroughly to analyze the text.
`includeConfidence`optional	boolean	Include confidence scores for extracted fields.

generate_imagein catalog

Generate Image. Create images from text prompts using Grok's image generation.

Input	Type	Description
`prompt`required	long text	Detailed description of the image you want to generate.
`model`required	id (picked from your account)	Image generation model to use.
`numberOfImages`optional	number	Number of images to generate (1-10).
`responseFormat`optional	one of "url" \| "b64_json"	Format of the generated images.

custom_api_call

Custom API Call. Make a custom API call to a specific endpoint

Input	Type	Description
`url`required	object (depends on other props)	url
`method`required	one of "GET" \| "POST" \| "PATCH" \| "PUT" \| "DELETE" \| "HEAD"	Method
`headers`required	object	Authorization headers are injected automatically from your connection.
`queryParams`required	object	Query Parameters
`body_type`optional	one of "none" \| "json" \| "form_data" \| "raw"	Body Type
`body`optional	object (depends on other props)	Body
`response_is_binary`optional	boolean	Enable for files like PDFs, images, etc.
`failsafe`optional	boolean	No Error on Failure
`timeout`optional	number	Timeout (in seconds)
`followRedirects`optional	boolean	Follow redirects

Details

Id: grok_xai
Category: AI and ML
Tags: ai, xai, grok, llm
Package: @activepieces/piece-grok-xai@0.1.4
Tier: Community