xAI Release Notes

Use the Grok add-in for Microsoft Word to turn notes into documents, style and format your work, or bring research from the web into Word.

Today we're bringing Grok into Microsoft Word. Install the add-in to turn prompts into paragraphs, bring research from the web into your documents, or rewrite text for clarity and concision.

Introducing Grok for Word

Transform notes to structured documents

Transform notes to structured documents

Prompt Grok with an initial set of notes to rewrite into structured, long-form text. Or, have Grok write initial drafts of proposals, reference materials, or guides. The add-in also excels at fixing grammar, rewriting text for clarity, or aligning writing styles across multiple authors.

Bring research and data into Grok

Bring research and data into Grok

Use the Microsoft Word add-in to search the web and bring research or data into your documents. Grok can also search X, or even generate diagrams for your documents. The add-in is also able to leverage connectors; ask it to draft from recent emails, or files in your SharePoint or Google Drive.

Get started

Get started

Grok for Word is a free Microsoft 365 add-in. Add it from the Microsoft Marketplace, and work directly with Grok in your documents. Also available for PowerPoint and Excel.

Grok models are now available via Amazon Bedrock.

Today, we’re excited to announce that Grok 4.3 is now generally available on Amazon Bedrock. Grok 4.3 achieves the lowest hallucination rate among frontier models, offers 1-million-token context window, and supports configurable reasoning efforts (none, low, medium, high). Now, Amazon Bedrock users can leverage the model through Bedrock’s secure and reliable inference engine.

Leading Performance in Enterprise

Grok 4.3 is one of the strongest models available today for building enterprise-ready AI agents:

• #1 on Artificial Analysis Omniscience benchmark*, achieving the lowest hallucination rate among frontier models.
• #1 on Artificial Analysis Tau2 Telecom benchmark*, which evaluates real-world tool-calling performance in customer support agent scenarios.
• #1 on Vals AI Case Law and Corporate Finance benchmarks, which measure Grok's capabilities in complex document understanding tasks.

• In comparison to major frontier labs

Capabilities & Pricing

Grok 4.3 sits on the Pareto frontier for intelligence versus cost, delivering 2-10x more intelligence per dollar than other frontier models.

• Input: $1.25 per 1 million tokens
• Output: $2.50 per 1 million tokens

It features a 1 million context window that handles extremely long documents and codebases with ease. Developers can also configure reasoning: Use none for maximum speed on simple requests, or low / medium / high to scale reasoning effort to the difficulty of the problem.

Build with Grok 4.3 on Amazon Bedrock

Grok 4.3 is now available to all developers in supported AWS Regions.

To get started, please visit the Grok on Amazon Bedrock documentation. We're excited to see what you build!

Improved quality at even faster speeds.

Grok Imagine Video 1.5 is now generally available on the Imagine API. We've also rolled out Video 1.5 Fast on grok.com/imagine and our iOS and Android apps. These are our best image-to-video models yet: better motion, better physics, better audio, at the fastest speeds. We’re also adding features to enhance your creative workflow in Grok Imagine.

Compared to the previous model, 1.5 improves across every dimension that matters for real creative work:

Audio and speech

Sound effects, ambience, and dialogue are generated in the same pass and land on the action. Speech is clearer and better synced.

Motion and physics

Movement holds together over the length of a clip — fewer warps, more believable weight and momentum.

Speed

Grok Imagine Video 1.5 Fast almost doubles generation speed: it produces 6-second, 720p videos in about 25 seconds, down from 40+ seconds in our previous model.

Behind the Scenes - Odyssey

Take a look behind the scenes at how David Thompson (@heavypulp) made a trailer worthy of the big screen entirely with Grok Imagine 1.5:

Enhanced productivity

Alongside Imagine Video 1.5, we're rolling out new features over the next few days to improve your creative workflow:

Projects

Organize your work into Projects that appear on the left sidebar.

Multiple agents

Kick off multiple agents in parallel on your projects. Instead of waiting for one generation to finish before starting the next, you can run several prompts at once and let them work for you.

Search

Find any image or video you've made by searching your library — no more scrolling to track down that one clip.

Now out of preview in the API

Imagine Video 1.5 is out of preview and generally available in the xAI API as grok-imagine-video-1.5. Give it a starting image, describe the motion, and choose your resolution and duration.

Try it today

We can't wait to see what you make.

Grok now works inside Microsoft PowerPoint — turn outlines into slides, expand the deck, and tighten the narrative without leaving the app.

Today we're bringing Grok into Microsoft PowerPoint. Using the add-in next to your deck, use Grok to research, write, and perfect your slides.

Add to PowerPoint

Try Grok

Introducing Grok for PowerPoint

Go from prompts to PowerPoints

Share an outline with Grok to generate full slide decks, complete with research from web or X searches, diagrams, and even images. Or, work with Grok to add single slides, apply styles and themes, or restructure sections with a single instruction. Grok will come back to you to ask clarifying questions.

Research, writing, and styling

Grok can help you improve styling, tighten slide narratives, and even search for up-to-date information from the web. The add-in is also able to leverage your Grok connectors - ask it to write slides based on recent emails, or files in your SharePoint or Google Drive.

Get started

Grok for PowerPoint is a free Microsoft 365 add-in, and work directly with Grok in your presentations. Also available for Word and Excel.

Manage many coding sessions at once. See what each is doing, reply to the ones that need you, and dispatch new work.

The Agent Dashboard puts every Grok Build session on one screen. See what each is doing, run them in parallel, and step in only when input is needed.
Run grok dashboard from your shell, or /dashboard (Ctrl+) from inside any session.

The dashboard sorts sessions by state, with anything waiting for input pulled to the top, so you handle blockers first and leave the rest running. A quick scan shows what each session is doing and for how long, so you stay oriented without opening anything.
Spread across repos? Group by working directory with Ctrl+S. Subagents roll up under the session that launched them, so the list shows the work you dispatched, not the fan-out beneath it.

Select a row to peek at its latest output without leaving the dashboard, then reply from there. Idle sessions send immediately; active ones queue your message until the current turn ends.
When a session requests approval or asks a question, its options appear inline. Answer with the arrow or number keys to continue. Multi-part questions arrive one at a time.

The input at the bottom starts a new session.
Enter dispatches it and keeps you on the dashboard; Shift+Enter dispatches and opens it right away. Before sending, set the model, start in plan mode, or let the session approve its own edits.

Open any session to take over its full conversation. Cycle to the next or previous session without returning to the list, then drop back to the dashboard when you're done. Closing the dashboard leaves every session running, and they're all there when you reopen it.

The Agent Dashboard ships with Grok Build. Install it with a single command, then run grok dashboard, or /dashboard from any session you already have open.

$cURL -fsSL https://x.ai/cli/install.sh| bash

You can now request higher scheduling priority per request by setting service_tier: "priority" on text, image, and video inference endpoints.

The response's service_tier field reports the tier actually applied, and priority rates are billed only when priority is used.

For more details, see the Priority Processing docs.

Launching the built-in plugin marketplace for Grok Build.

Today we're launching the Grok Build Plugin Marketplace - a set of built-in plugins for Grok Build.

A plugin bundles skills, slash commands, agents, hooks, MCP servers, and LSPs into one installable package. The marketplace is built into Grok Build, so you can browse, install, and update plugins without leaving your terminal.

Available at launch

The marketplace opens with plugins from partners across the stack:

• MongoDB — Explore data, manage collections, and optimize queries.
• Vercel — Manage deployments, check build status, and configure domains.
• Sentry — Analyze stack traces and debug production errors.
• Chrome DevTools — Control a live browser, record performance traces, and inspect network requests.
• Cloudflare — Skills for Workers, Durable Objects, and more.
• Superpowers — Popular agent-driven workflows.

Install in seconds

Inside Grok Build, type /marketplace to browse the catalog and press i to install a plugin. Or use the CLI directly:

grok plugin marketplace list
grok plugin install <name> --trust

Every remote plugin in the catalog is pinned to a specific commit SHA, and Grok Build verifies the pin at install time.

Publish your own

The marketplace is an open catalog. If you've built a plugin you want to share, submit a pull request to xai-org/plugin-marketplace.

Getting started

New to Grok Build? Head to x.ai/cli to install it and get started.

Gopuff and SpaceXAI launched Go, an AI-powered shopping assistant built into the Gopuff app and powered by Grok text, audio, and image models.

The SpaceXAI team has collaborated closely with Gopuff to launch the Go agent - a personal shopping assistant that knows what you want and delivers in minutes - using frontier text, image, and audio models.

Go pairs Grok's frontier reasoning, voice, and image generation with Gopuff's 13 years of demand intelligence based on hundreds of millions of orders. Through SpaceXAI API tools, Go also leverages real-time signals from X and the web. The result is a shopping experience that anticipates what you need and delivers it in minutes from Gopuff's network of micro-fulfillment centers.

Building Go

Gopuff and SpaceXAI worked closely to build multimodal capabilities into the new Go agent. Go can build personalized carts for you before you open the app using past preferences and external signals like the weather. Over time, Go learns what you like and dislike, helping you order critical necessities when you need them.

Go also includes a new, visual shopping feed based on Grok Imagine. Using state-of-the-art image models, Go generates hyper-realistic scenes from Gopuff inventory, helping you visualize shopping carts and orders.

Go learns on every order to help you shop faster and more efficiently in the future. Go is available now in the Gopuff app on iOS and Android, starting in the US with the UK to follow.

• Public URLs for Files — turn any file in your Files API storage into a permanent, unauthenticated URL that anyone can open, embed, or share. Revocable at any time, or set an auto-expiry between 1 hour and 30 days. See the Public URLs docs.
• Reference stored files as Imagine inputs — substitute image_file_id, video_file_id, or reference_image_file_ids for URL inputs across every Imagine endpoint, with no need to re-upload bytes or make the file public. See Imagine → Files API Integration.
• Persist Imagine outputs to Files — set storage_options on any Imagine request to save the generated asset to your Files storage; pair with storage_options.public_url to publish a shareable link in one round trip. See Imagine → Files API Integration.

grok-imagine-video-1.5-preview, our latest image-to-video model, is now available via the xAI API in preview.

Our latest image-to-video model, grok-imagine-video-1.5-preview, is now available via the xAI API in preview.

grok-imagine-video-1.5-preview turns a single still image into fluid, cinematic video. Give it a starting frame and a prompt describing the motion, and it animates the scene, including camera moves, atmosphere, and physics, while staying faithful to your source image. You can generate clips at up to 720p.

Direct the shot with natural-language prompts. Describe the camera move, the pacing, and the sound design, then set your resolution and clip length. The model holds detail and lighting from the input frame, so the result continues the original image rather than reinterpreting it.

The model also works well for sequences. Stage each frame, animate it, and chain the shots together into longer scenes that keep a consistent look across an entire project.

Animate an image in a few lines of code.

import os
import xai_sdk
client = xai_sdk.Client(api_key = os.getenv("XAI_API_KEY"))
response = client.video.generate(
 prompt = "Slow cinematic push-in as embers drift across the battlefield and the helmet's crest stirs in the wind",
 model = "grok-imagine-video-1.5-preview",
 image_url = "https://your-host.com/helmet.jpg",
 duration = 10,
 resolution = "720p",
)
print(response.url)

Composer 2.5 is now available in Grok Build. Try it from the /models menu.

Available to SuperGrok and X Premium+

Composer 2.5 is now available in Grok Build. Composer 2.5 is a fast, state-of-the-art model that excels on long-running tasks and following complex instructions.

Try it by typing /model and then selecting Composer 2.5 in the menu.

The streaming Speech to Text API now supports Smart Turn end-of-turn detection. When enabled via the smart_turn query parameter, an ML model predicts whether the speaker has finished their thought at silence boundaries — reducing false endpointing during dictation, number sequences, and mid-sentence pauses. Use smart_turn_timeout to set a maximum silence fallback. For more details, see the Smart Turn docs.

The Context Compaction API is now available. You can shrink long conversations into a shorter context and reuse it in follow-up requests for lower cost, faster time-to-first-token, and sharper responses on long agent loops. For more details, see the Context Compaction docs.

WebSocket Responses API mode is now available.

Drive the Responses API over a single, long-lived WebSocket connection for lower end-to-end latency on tool-heavy agent workloads.

For more details, see the WebSocket Mode docs.

Grok Build 0.1, our fastest coding model, is now available via the xAI API in public beta.

Our latest coding model, grok-build-0.1, is now available via the xAI API in public beta.

grok-build-0.1 is a coding model specifically trained for agentic coding tasks, including web development, debugging, and MCP support. It's the same model that powers the Grok Build CLI.

The model is served at a blazing-fast 100+ tokens/second and is priced at $1/m tokens in and $2/m tokens out. Outside of coding, it’s also a speedy, economical option for general-purpose agentic and tool calling use cases.

Try it now

Create API key

curl https://api.x.ai/v1/responses \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $XAI_API_KEY" \
-d '{
"model": "grok-build-0.1",
"input": [
{
"role": "user",
"content": "Generate a clean, tasteful, and minimalist personal website design with elegant typography"
}
]
}'

grok-build-0.1 performs best in agentic harness like Grok Build, Cursor, Hermes Agent, OpenClaw, Kilo Code, or OpenCode. It’s also available via OpenRouter and Vercel AI Gateway.