LIVE
Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|
Toolofficial publisher

x_search (xAI)

Tool : A precise action the AI can call · requires xai-api

Real-time search of posts and profiles on X.

Unique for real-time social data; billed per post starting September 21, 2026.

Overall score
6.5 /10
Security: one caveat, see the card
Utility
7.0
Reliability
6.0
Security
One caveat
Ease
1 click · Comfortable

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Tracking in real time what users publish on X (formerly Twitter) is difficult without direct access to the platform's API. X Search solves this by allowing Grok to query X content directly through the xAI API, without going through a graphical interface.

In practice, the tool supports keyword search, semantic search, user profile search, and full thread retrieval. Results can be filtered by date range, restricted to specific accounts or excluding certain ones, and image or video understanding can be enabled for posts.

X Search is aimed at developers integrating Grok into their applications who need fresh social data: brand monitoring, trend analysis, tracking specific accounts, or extracting multimedia content from X.

However, this tool is not suited for non-technical users: there is no consumer-facing interface, everything goes through the xAI API. It is also not relevant for those looking for data from other social networks or the open web.

What it offers

  • ·Keyword and semantic search on X posts in real time. (paid)
  • ·User profile search on X. (paid)
  • ·Full thread retrieval, including parent posts and quoted posts. (paid)
  • ·Result filtering by date range in ISO8601 format. (paid)
  • ·Restricting search to a specific list of X accounts (up to 20 handles). (paid)
  • ·Excluding specific X accounts from results (up to 20 handles). (paid)
  • ·Image analysis within X posts via the enable_image_understanding parameter. (paid)
  • ·Video analysis within X posts via the enable_video_understanding parameter. (paid)

In practice

Price
Paid · from 5 €
Commercial use
Commercial use: yes
Available on
api
Host
xai-api
FR interface
No

Security and data

Rating
Security: one caveat, see the card
Capabilities
readswritesexecutesnetwork
Your data
Data with the vendor
Maintenance
Active

Links and repository checked on 25 October 2026 · added on 1 July 2025

How to install x_search (xAI)

1. Create an API key on the xAI portal and store it in an environment variable (XAI_API_KEY), never committing it to your source code. 2. Install the xAI Python SDK with pip install xai-sdk, or use the compatible OpenAI SDK by pointing base_url to https://api.x.ai/v1. 3. Import the client and the x_search function from xai_sdk.tools. 4. Create a chat session specifying the model (e.g. grok-4.6) and passing x_search() in the tools list. 5. Send your user query and iterate over the response stream to retrieve results and citations. 6. Review your filtering parameters (handles, dates) before running production queries to keep costs under control given per-post billing.
pip install xai-sdk

Official documentation ↗

In the same category

Whole category Feed (memory, context) →