Agentic coding
The model was trained for iterative coding work inside an agent harness rather than one-shot code completion.
Historical tool archive
Grok Code Fast 1 was xAI's low-cost agentic coding model for fast tool use in IDEs and terminal workflows. It was retired on May 15, 2026 and replaced by Grok Build 0.1.
No longer active

Archive
xAI launched Grok Code Fast 1 in August 2025 as a responsive coding model trained for repeated reasoning, terminal, search, and file-editing steps. It was available through the xAI API and launch partners including GitHub Copilot, Cursor, Cline, Roo Code, Kilo Code, OpenCode, and Windsurf.
Grok Code Fast 1 is no longer active as a separate model. xAI now routes its old API aliases to Grok Build 0.1 and recommends that developers migrate explicitly to the successor. This page is retained as a historical reference for teams reviewing old configurations, invoices, or model comparisons.
Past capabilities
The model was trained for iterative coding work inside an agent harness rather than one-shot code completion.
It was designed to work with terminals, file editing, repository search, and other common development tools.
xAI emphasized low latency and high prompt-cache hit rates for repeated coding loops.
The launch highlighted TypeScript, Python, Java, Rust, C++, and Go.
Availability
At launch, Grok Code Fast 1 cost $0.20 per million input tokens, $0.02 per million cached input tokens, and $1.50 per million output tokens. Those historical rates no longer apply: old aliases now route to Grok Build 0.1 under the successor's current pricing.
Status checked . Review the historical source ↗
Current options
Coding
Use Grok Build for xAI's current coding-agent workflow and the Grok Build 0.1 successor model.
Explore Grok Build →Consumer
Consider Grok 4.5 when stronger reasoning and broader agentic work matter more than the successor's speed-first positioning.
Explore Grok 4.5 →Coding
Consider Claude Code for a mature terminal-based agent with Anthropic's current coding models.
Explore Claude Code →Coding
Consider OpenAI Codex for repository-aware coding agents, parallel task workflows, and code review.
Explore Codex →Questions
No. xAI retired it on May 15, 2026. Its old API aliases now route to Grok Build 0.1.
xAI recommends Grok Build 0.1 for agentic coding and web-development workloads.
The former slugs continue to resolve, but xAI serves Grok Build 0.1 instead. Developers should migrate explicitly so the model and pricing are clear.

Get access to all our AI courses, hundreds of real-world AI use cases, live expert-led workshops, an exclusive network of AI early adopters, and more.
Get unlimited access to all of our current & upcoming industry-specific AI courses for the duration of your subscription.
To keep up with the rapid pace of AI, our team publishes AI implementation guides daily. Our library contains 300+ practical use cases to automate real-world work.
Join weekly, live, interactive sessions with industry leaders who are at the forefront of AI for hands-on implementation guidance and exclusive insights.
Network with an exclusive community of AI-first professionals who are working smarter with AI. Learn how early adopters are using AI in their work and businesses.