> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Grok

> Grok is xAI's API platform for text, image, video, embedding, file, search, and voice capabilities.

![Grok logo](https://mintcdn.com/composio-preview/o1IUBrrsmtgkhmyf/images/toolkits/grok.svg?fit=max\&auto=format\&n=o1IUBrrsmtgkhmyf\&q=85\&s=e2680bd71b20427e96a68f2caa0717e0)

* **Category:** artificial intelligence
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 8
* **Triggers:** 0
* **Slug:** `GROK`
* **Version:** 00000000\_00

## Tools

> [accordion] Create Embeddings
>
> **Slug:** `GROK_CREATE_EMBEDDINGS`
>
> Create vector embeddings for one or more text inputs with an xAI embedding model.
>
> #### Input Parameters
>
> **user** `string`
>
> Stable end-user identifier that helps xAI monitor and detect abuse.
>
> **input** `string` *required*
>
> One non-empty text value or a batch of up to 128 non-empty text values to embed.
>
> **model** `string` *required*
>
> xAI embedding model ID to use.
>
> **dimensions** `integer`
>
> Requested number of output dimensions when supported by the model.
>
> **encoding\_format** `string ("float" | "base64")`
>
> Embedding encoding to return: 'float' for numeric vectors or 'base64'.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Response
>
> **Slug:** `GROK_CREATE_RESPONSE`
>
> Generate a bounded, non-streaming Grok response from text or structured multimodal input, with optional reasoning, search, and function or web-search tools. Responses are ephemeral by default; set store=true to retain one for 30 days.
>
> #### Input Parameters
>
> **input** `string` *required*
>
> Plain text, or structured message, function-call, and function-result items containing text, images, or files. To continue a tool call without store=true, replay the model's function\_call item followed by its function\_call\_output.
>
> **model** `string` *required*
>
> xAI model ID to use; obtain available IDs from GROK\_LIST\_MODELS.
>
> **store** `boolean`
>
> Whether xAI should retain the input and response for retrieval or continuation. Defaults to false; stored responses are retained for 30 days.
>
> **tools** `array`
>
> Up to 128 function or web-search tool definitions available to the model.
>
> **temperature** `number`
>
> Sampling temperature from 0 to 2.
>
> **tool\_choice** `string`
>
> Whether tools are disabled, automatic, required, or a named tool is forced.
>
> **instructions** `string`
>
> System-level guidance; do not combine with previous\_response\_id.
>
> **reasoning\_effort** `string ("none" | "low" | "medium" | "high")`
>
> Reasoning effort supported by the selected model.
>
> **max\_output\_tokens** `integer`
>
> Upper bound on generated output and reasoning tokens (1-128000).
>
> **search\_parameters** `object`
>
> Realtime web, X, news, or RSS search configuration.
>
> **previous\_response\_id** `string`
>
> Prior response ID whose conversation context should be continued.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Generate Image
>
> **Slug:** `GROK_GENERATE_IMAGE`
>
> Generate one or more images from a text prompt with an xAI image-generation model.
>
> #### Input Parameters
>
> **user** `string`
>
> Stable end-user identifier that helps xAI monitor and detect abuse.
>
> **model** `string`
>
> xAI image-generation model ID; omit only when relying on the provider default.
>
> **prompt** `string` *required*
>
> Description of the image to generate.
>
> **resolution** `string ("1k" | "2k")`
>
> Output resolution supported by grok-imagine models; omit to use the provider default.
>
> **image\_count** `integer`
>
> Number of images to generate (1-10).
>
> **aspect\_ratio** `string ("1:1" | "3:4" | "4:3" | "9:16" | "16:9" | "2:3" | "3:2" | "9:19.5" | "19.5:9" | "9:20" | "20:9" | "1:2" | "2:1" | "auto")`
>
> Output aspect ratio supported by grok-imagine models; omit to use the provider default.
>
> **response\_format** `string ("url" | "b64_json")`
>
> Image result format: 'url' for a generated-file URL or 'b64\_json' for base64-encoded image bytes.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Generate Video
>
> **Slug:** `GROK_GENERATE_VIDEO`
>
> Start asynchronous xAI video generation from a text prompt, optionally conditioned on an image, and return a request ID for status checks.
>
> #### Input Parameters
>
> **user** `string`
>
> Stable end-user identifier that helps xAI monitor and detect abuse.
>
> **model** `string`
>
> Video-generation model ID; omit only to use xAI's provider default.
>
> **prompt** `string` *required*
>
> Description of the video to generate.
>
> **duration** `integer`
>
> Requested video duration in seconds (1-15); xAI defaults to 8.
>
> **image\_url** `string`
>
> Optional public URL or base64 data URL for a JPEG, PNG, or WebP image to use as the video's first frame.
>
> **resolution** `string ("480p" | "720p" | "1080p")`
>
> Output video resolution supported by xAI.
>
> **aspect\_ratio** `string ("1:1" | "16:9" | "9:16" | "4:3" | "3:4" | "3:2" | "2:3")`
>
> Output aspect ratio supported by xAI.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get API Key Info
>
> **Slug:** `GROK_GET_API_KEY_INFO`
>
> Inspect the connected xAI API key's identity, wildcard or granular ACLs, and key or team blocking state.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Current Account
>
> **Slug:** `GROK_GET_CURRENT_ACCOUNT`
>
> Verify the connected xAI credential and return the caller, team, zero-data-retention status, and key blocking state.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Video
>
> **Slug:** `GROK_GET_VIDEO`
>
> Check an asynchronous xAI video request. Returns pending while generation is in progress, the video and usage when done, or the structured generation error when failed.
>
> #### Input Parameters
>
> **request\_id** `string` *required*
>
> Deferred request ID returned by GROK\_GENERATE\_VIDEO.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Models
>
> **Slug:** `GROK_LIST_MODELS`
>
> List models available to the connected xAI key, including model IDs and published pricing metadata needed to choose a model for other tools.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
