Grok Build 0.1
Grok Build 0.1 is a coding-focused model developed by SpaceXAI, released on May 20, 2026. It is designed for agentic software engineering workflows and supports both text and image inputs with built-in reasoning and tool-calling capabilities.
Grok Build 0.1 specs and pricing
- Provider: SpaceXAI
- Released: May 20, 2026
- Context window: 256K tokens
- Max output: 230K tokens
- Input: text, images, files
- Output: text
- Price: $1.00 input / $2.00 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Grok Build 0.1 is good at
- Automating software engineering workflows
- Analyzing codebases and technical documentation
- Interactive coding and debugging tasks
To-dos to try with Grok Build 0.1
- Analyze a set of UI design images and generate the corresponding front-end code.
- Review a repository of files to identify and suggest fixes for potential security vulnerabilities.
- Execute a multi-step coding task by calling external software tools to verify the output.
FAQ
- What is the primary purpose of Grok Build 0.1? It is a model specifically trained for agentic software engineering workflows and interactive coding.
- Can this model process images? Yes, Grok Build 0.1 supports both text and image inputs.
- How much does Grok Build 0.1 cost? Grok Build 0.1 costs $1.00 per million input tokens and $2.00 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 3.08 credits ($1 = 100 credits).
- What is the context window of Grok Build 0.1? Grok Build 0.1 can read up to 256K tokens at once and write up to 230K tokens in one reply.
- Can I use Grok Build 0.1 without coding? Yes. In todo.is you pick Grok Build 0.1 as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.