Model Release
xAI Launches Grok Build 0.1 Coding Model via API
xAI has released Grok Build 0.1, a coding model capable of handling agentic tasks at 100+ tokens per second, now available in public beta.
Image: xAI
xAI has released Grok Build 0.1, a coding model designed for agentic coding tasks such as web development, debugging, and MCP support, now available via the xAI API in public beta. The model, which powers the Grok Build CLI, operates at a rate of 100+ tokens per second and is priced at $1 per million tokens for input and $2 per million tokens for output. It is also positioned as a cost-effective solution for general-purpose agentic and tool calling applications. According to xAI, the model performs optimally in agentic frameworks like Grok Build, Cursor, Hermes Agent, OpenClaw, Kilo Code, or OpenCode. It is also accessible through OpenRouter and Vercel AI Gateway. The company emphasized that Grok Build 0.1 is the same model used in its CLI tool, ensuring consistency across platforms. Developers are encouraged to test the model using the provided API command. *Source: [xai](https://x.ai/news/grok-build-0-1)*
Key points
- xAI has released Grok Build 0.1, a coding model for agentic coding tasks.
- Grok Build 0.1 is available via the xAI API in public beta.
- The model operates at a rate of 100+ tokens per second.
- It is priced at $1/m tokens in and $2/m tokens out.
- Grok Build 0.1 is the same model that powers the Grok Build CLI.
- The model is suitable for general-purpose agentic and tool calling use cases.
- It is available via OpenRouter and Vercel AI Gateway.