Integration · Developer tools

Connect Claude & ChatGPT to Grok by xAI

Give your AI assistant access to Grok models through your own xAI account. Claude or ChatGPT can send a question to Grok and get its reply, generate or edit images, start a video generation, create embeddings and count tokens. It can also list the available models and read files uploaded to your xAI account.

Connect Grok by xAI free

Free plan, no credit card. Takes about a minute.

Try asking

“Ask Grok for its take on this product description.”
The AI sends the text to a Grok model and shows Grok's reply next to its own.
“Generate three images of a red bicycle on a Copenhagen street.”
It asks the image model for three images from the prompt and returns them.
“Make the background of this image white.”
It sends the image and the instruction to image editing and returns the edited image.

What your AI can do

Chat with Grok

Send messages to a Grok model with your choice of model, temperature and max tokens, and count tokens before you send.

Images and video

Generate images from a prompt, edit existing images, and start video generations and check their results.

Models, files and embeddings

List language, image and video models, read uploaded files, and create embeddings for text.

“Start a 10-second video of waves on a beach.”
It starts the video generation, gets a request ID and then checks the status with that ID.
“Which Grok models can I use, and what do they cost?”
It lists the chat models available to your API key, with pricing and context limits.
“How many tokens is this document for Grok?”
It tokenizes the text for the model you pick and returns the count.

41 tools for Grok by xAI

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

chat_completionChanges dataAsk a Grok model a question. Pass `messages` (role + content list) and optionally `model`, `temperature` and `max_tokens`. Returns the model's reply.
count_tokensChanges dataTokenize `text` for a given `model` to see how many tokens it uses.
create_compactChanges dataCreate a new compact. Required: input or model. API summary: Compacts a full Responses API input window into a shorter canonical window.
create_completeChanges dataCreate a new complete. API summary: (Legacy - Not supported by reasoning models) Create a text completion response. This endpoint is compatible with the Anthropic API.
create_completion_handle_sample_requestChanges dataCreate a new completion. API summary: (Legacy - Not supported by reasoning models) Create a text completion response for a given prompt. Replaced by /v1/chat/completions.
create_document_public_urlChanges dataCreate a new public url for a document. API summary: Create a permanent, unauthenticated public URL for an existing file. The underlying file is unaffected and can still be fetched through the….
create_edit_handle_edit_video_requestChanges dataCreate a new edit. Required: prompt or video. API summary: Edit a video based on a prompt. This is an asynchronous operation that returns a requestid for polling.
create_embeddingChanges dataCreate vector embeddings for text `input` with an embedding `model`.
create_extensionChanges dataCreate a new extension. Required: prompt or video. API summary: Extend a video by generating continuation content. This is an asynchronous operation that returns a requestid for polling.
create_messageChanges dataCreate a new message. API summary: Create a messages response. This endpoint is compatible with the Anthropic API.
create_responseChanges dataCreate a new response. Required: input. API summary: Generates a response based on text or image prompts. The response ID can be used to retrieve the response later or to continue the conversat….
create_revokeChanges dataCreate a new revoke. API summary: Revoke the active public URL for a file. The underlying file remains available through the authenticated content endpoint.
delete_documentDeletesPermanently delete a document by document id. Destructive action; may require approval. API summary: Delete a file by ID. After this returns, the file no longer appears in GET /v1/files, content download returns 404, and the ID can no longer….
delete_responseDeletesPermanently delete a response by response id. Destructive action; may require approval. API summary: Delete a previously generated response.
delete_skillDeletesPermanently delete a skill by skill id. Destructive action; may require approval.
edit_imageChanges dataEdit an existing image according to a text `prompt`. Pass the source `image` (or `images`).
generate_imageChanges dataGenerate an image from a text `prompt`. Optionally set `model`, `n` (number of images) and `aspect_ratio`. Returns image URLs or data.
generate_videoChanges dataStart generating a video from a text `prompt` (optionally with a starting `image`, `duration` and `aspect_ratio`). Returns a request ID; check it with get_video.
get_deferred_completionGet one deferred completion by request id. API summary: Tries to fetch a result for a previously-started deferred completion. Returns 200 Success with the response body, if the request has been co….
get_embedding_modelGet one embedding model by model id. API summary: Get full information about an embedding model with its modelid.
get_fileGet metadata for one uploaded file by `file_id`.
get_file_contentDownload the content of an uploaded file by `file_id`.
get_image_generation_modelGet one image generation model by model id. API summary: Get full information about an image generation model with its modelid.
get_language_modelGet details for one language model by `model_id`.
get_modelGet one model by model id. API summary: Get information about a model with its modelid, including pricing.
get_responseGet one response by response id. API summary: Retrieve a previously generated response.
get_skillGet one skill by skill id.
get_videoGet the status and result of a video generation by `request_id`.
get_video_generation_modelGet one video generation model by model id. API summary: Get full information about a video generation model with its modelid.
list_api_keysList api keys. API summary: Get information about an API key, including name, status, permissions and users who created or modified this key.
list_embedding_modelsList embedding models. API summary: List all embedding models available to the authenticating API key with full information.
list_filesList files uploaded to your xAI account.
list_image_modelsList the image generation models available to this API key.
list_language_modelsList the Grok chat models available to this API key, with pricing and context limits.
list_mesList mes. API summary: Get information about the currently authenticated caller. Works with both API keys and OAuth tokens. Returns identity, team, and ZDR status.
list_modelsList models. API summary: List all models available to the authenticating API key, including model names (ID), creation times, and pricing.
list_response_productsList products for a response. Optional filters: order. Results are paginated. API summary: List input items for a previously generated response.
list_skill_contentsList contents for a skill.
list_skillsList skills. Optional filters: order. Results are paginated.
list_video_modelsList the video generation models available to this API key.
search_documentsChanges dataSearch documents. Use this to find existing documents before creating a new document. API summary: Search for content related to the query within the given collections.

Set up in three steps

1
Pick the app
Create a free HeyMyApps account and choose Grok by xAI from the app list.
2
Paste your key
Paste your xAI API key. Sign in to the xAI console (console.x.ai), open the API Keys page, create an API key and paste it here.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
1. Click your name, then Settings › Connectors › Add custom connector.
2. Paste your link as the Remote MCP server URL.
3. Switch it on from the + menu in a chat.

Questions

What can the AI do in Grok by xAI?

The AI can send chat messages to Grok models, generate and edit images, start video generations and check their status, create embeddings and count tokens. It can list language, image and video models and read the metadata and content of files uploaded to your xAI account.

Does the AI see my xAI API key?

No. Your xAI API key is encrypted at rest and never shown to the AI. After you save it, it is not shown again, not even to you. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on, for example chat without image or video generation. Every call to Grok uses your xAI account, so these tools can require your approval before they run. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT go to Settings › Apps & Connectors › Advanced and turn on Developer mode, then add your HeyMyApps link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

HeyMyApps has a free plan with no credit card required. Paid plans bill per completed task. You also need your own xAI account. Grok usage is billed by xAI on your own xAI account, so anything xAI charges is between you and xAI.

Why connect Grok to Claude or ChatGPT?

It lets the assistant you already use call Grok models from the same chat, for example to get a second answer, generate images or create embeddings. Requests use your own xAI API key and the models available to it.