KI-Programmierassistenten: Release Notes

• You can now use Grok 4.1 Fast models with the agent tools, check out the documentation of agent tools to get started.
• The price of agent tools drops by up to 50% to no more than $5 per 1000 successful calls, see the new prices at the pricing page.

Files API is generally available

You can now upload files and use them in chat conversations with the Files API. For more details, check out our guide on Files.

New Tools Available

• Collections Search Tool: You can now search through uploaded knowledge bases (collections) in chat conversations via the API. For more details, check out the docs.
• Remote MCP Tools: You can now use tools from remote MCP servers in chat conversations via the API. For more details, check out the docs.
• Mixing client-side and server-side tools: You can now mix client-side and server-side tools in the same chat conversation. For more details, check out the docs.

October 2025

Tools are now generally available

New agentic server-side tools including web_search, x_search, and code_execution are available. For more details, check out our guide on using Tools.

September 2025

Responses API is generally available …

You can now use grok-voice-think-fast-1.0 with the Speech to Speech API. To get started, check out the Speech to Speech docs. For more details, see our blog post.

Speech to Text is available

The xAI Speech to Text API is now generally available. Transcribe audio to text in 25 languages with batch and streaming modes. For more details, check out the Speech to Text docs.

March

Text-to-Speech is available

The Text-to-Speech API is now generally available. Generate natural-sounding speech from text with Grok. For more details, check out the Text-to-Speech docs.

Batch API supports Image and Video generation

The Batch API now supports image generation, image editing, and video generation in addition to chat completions. Both server-side tools and client-side function tools are also now supported in batch requests. Image and video URLs in batch results expire after 1 hour.

Batch API JSONL file upload …

SpaceXAI's coding model, trained specifically for agentic coding workflows. Currently in early access.

The model slug is grok-build-0.1.

Grok Build

Grok Build is now available in beta. Use the interactive TUI, run headlessly in scripts, or build apps and orchestrators with the Agent Client Protocol.

Install with a single command:

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

For more details, see the Grok Build docs.

Custom Voices

You can now clone a voice from a short audio clip and use it across the Text-to-Speech and Speech to Speech APIs. Create and manage your voice catalog from the xAI console. For more details, check out the Custom Voices docs and our blog post.

April

Cost Tracking

Every API response now includes the exact cost of the request via a cost_in_usd_ticks field in the usage object. Works across chat completions, Responses API, image generation, video generation, and streaming. For more details, see the Cost Tracking docs.

Files API TTL

You can now set an expiration policy on uploaded files using expires_after or an explicit expires_at timestamp. Expired files are automatically deleted. For more details, see the Files API docs.

June

Priority Processing

You can now request higher scheduling priority per request by setting service_tier: "priority" on text inference endpoints (Chat Completions and Responses). 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.

Public URLs and Files API ↔ Imagine integration

• 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.

May

Smart Turn for Streaming STT …

August

Imagine image API updates

• Auto quality. The quality parameter on grok-imagine-image-2.0 now accepts auto, and the default when quality is omitted has moved from medium to auto. Auto currently uses low for image generation and medium for image editing. Images are billed at the quality they are served at. Pass low or medium explicitly to pin a specific quality. See Image Generation.
• Five reference images. Image editing now accepts up to 5 source images per request (was 3). See Multi-Image Editing.
• New aspect ratios. Image generation and editing accept 21:9 (cinematic widescreen) and 5:2 (wide banners). See Image Generation.

Claude Opus 4.6 is now available in Windsurf with limited-time promotional pricing for self-serve users:

• No thinking: 2x credits
• With thinking: 3x credits

Opus 4.6 is available in Arena Mode's Frontier Arena and Hybrid Arena. Try it head-to-head against other frontier models to see how it performs on your real-world tasks.

• Fix build for Mac x64

  <Accordion title="Download 1.9577.43"> <Release darwinArm64="https://windsurf-stable.codeiumdata.com/darwin-arm64/stable/745a6c1ac471cc11f782a05d2c3ceacbc1de308f/Windsurf-darwin-arm64-1.9577.43.zip" darwinArm64Dmg="https://windsurf-stable.codeiumdata.com/darwin-arm64-dmg/stable/745a6c1ac471cc11f782a05d2c3ceacbc1de308f/Windsurf-darwin-arm64-1.9577.43.dmg" darwinX64="https://windsurf-stable.codeiumdata.com/darwin-x64/stable/745a6c1ac471cc11f782a05d2c3ceacbc1de308f/Windsurf-darwin-x64-1.9577.43.zip" darwinX64Dmg="https://windsurf-stable.codeiumdata.com/darwin-x64-dmg/stable/745a6c1ac471cc11f782a05d2c3ceacbc1de308f/Windsurf-darwin-x64-1.9577.43.dmg" linuxX64="https://windsurf-stable.codeiumdata.com/linux-x64/stable/745a6c1ac471cc11f782a05d2c3ceacbc1de308f/Windsurf-linux-x64-1.9577.43.tar.gz" linuxX64Deb="https://windsurf-stable.codeiumdata.com/linux-x64-deb/stable/745a6c1ac471cc11f782a05d2c3ceacbc1de308f/Windsurf-linux-x64-1.9577.43.deb" win32Arm64="https://windsurf-stable.codeiumdata.com/win32-arm64/stable/745a6c1ac471cc11f782a05d2c3ceacbc1de308f/WindsurfSetup-arm64-1.9577.43.exe" win32Arm64Archive="https://windsurf-stable.codeiumdata.com/win32-arm64-archive/stable/745a6c1ac471cc11f782a05d2c3ceacbc1de308f/Windsurf-win32-arm64-1.9577.43.zip" win32Arm64User="https://windsurf-stable.codeiumdata.com/win32-arm64-user/stable/745a6c1ac471cc11f782a05d2c3ceacbc1de308f/WindsurfUserSetup-arm64-1.9577.43.exe" win32X64="https://windsurf-stable.codeiumdata.com/w…

Feature

Gemini Enterprise: Control access to Antigravity features

Administrators can control whether users in their organization have access to the following Google Antigravity features:

• Boost: Uses a tiered multi-agent hierarchy to solve complex algorithmic challenges and deep debugging tasks with the /boost command. This feature is generally available (GA) in Antigravity.
• Teamwork: Deploys a coordinated framework of autonomous subagents to execute large-scale, long-horizon projects using the /teamwork-preview command. This feature is in Preview in Antigravity.

These settings are generally available (GA) for administrators in Gemini Enterprise.

For more information, see Configure feature settings.

Organization and enterprise administrators can now see AI Scan for pull requests enablement status in the security overview coverage view. The code scanning summary shows enabled and not enabled repository counts, while repository rows show each repository’s effective AI Scan enablement.

You can filter the coverage view with code-scanning-ai-scan-pr-scan:enabled and code-scanning-ai-scan-pr-scan:not-enabled. Coverage CSV exports now include a Code Scanning AI Scan for pull requests column with enabled and not-enabled values.

This visibility helps you track adoption and manage AI Scan for pull requests enablement across your organization or enterprise.

Learn more about assessing adoption of security features and join the AI Scan Community discussion.

social

The post Code scanning AI Scan enablement status in security overview appeared first on The GitHub Blog.

GitHub stacked pull requests are now generally available. Break large changes into smaller, focused pull requests that you can review independently and merge together.

Since the feature went into public preview, repositories using stacks have seen a 9% increase in merged code compared to peers. Over two-thirds of the top 1% of repos now use stacked pull requests and have seen a 5% improvement in time-to-merge.

With this general availability release, we’re introducing several improvements to make stacks easier to create, review, and merge. Thank you to everyone who provided feedback and input during the preview period.

More flexible merging and rebasing

• Approvals stay in place for unchanged code. When an otherwise unchanged stack is updated after its base branch, such as main, moves ahead, Rebase stack now preserves approvals, even in repositories that dismiss stale approvals.
• Rebased commits stay signed. GitHub creates signed replacement commits during Rebase stack, preserving original authorship. Automatic rebases after partial merges also sign replacement commits when branch rules require signatures or any original commit was signed.
• Bypass permissions apply to stacks. Users with permission to bypass repository rules can now use those permissions to merge the lowest unmerged pull request in a stack. …