# Grok Build 0.1

Grok Build 0.1 is SpaceXAI's coding model purpose-built for agentic software engineering. It pairs always-on reasoning with tool calling and structured outputs across a context window of 256K tokens.

- **Model ID:** `spacexai/grok-build-0.1`
- **Type:** chat
- **Providers:** xai
- **Context window:** 256,000
- **Maximum output tokens:** 256,000
- **Pricing:** $1/1M input tokens, $2/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/grok-build-0.1

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

```ts
import { streamText } from 'ai'

const result = streamText({
  model: 'spacexai/grok-build-0.1',
  prompt: 'Why is the sky blue?'
})
```

## About

Grok Build 0.1 was released May 20, 2026 as SpaceXAI's coding model purpose-built for agentic software engineering. Where general-purpose Grok models handle coding alongside other tasks, Grok Build 0.1 is trained to act as an autonomous engineering agent: refactoring code, invoking tools, producing structured outputs, and iterating through multi-step tasks until completion.

Reasoning is always active on Grok Build 0.1. There is no non-reasoning mode and reasoning effort is not configurable, so every response includes structured analysis before the final output. The model accepts text and image input, which means it can read diagrams, UI mockups, and error screenshots alongside source code. It supports tool calling and structured outputs, which fits agent loops that orchestrate file edits, test runs, and external APIs.

Grok Build 0.1 operates within a context window of 256K tokens and is available through Vercel AI Gateway at $1 per million input tokens, $2 per million output tokens, and $0.2 per million cached input tokens. The cached input rate makes it economical to reuse long codebase prefixes across many agent steps.

## What to consider

Reasoning runs on every request. Grok Build 0.1 always produces chain-of-thought traces, which increases output token consumption compared to direct-response models. Budget output tokens generously and factor reasoning overhead into cost estimates.

The context window of 256K tokens fits substantial codebases in a single session, which suits agent loops that read many files before acting. Cached input pricing reduces the cost of reusing a long repository prefix across steps.

## When to use

### Best For

- **Autonomous coding agents** that read files, call tools, and edit code without step-by-step prompting
- **Codebase refactoring** with multi-file changes that require reasoning over project structure within the context of 256K tokens
- **Test generation and repair** workflows that produce test cases, run them through tool calls, and patch failures
- **Tool-heavy development pipelines** that combine model decisions with shell commands, file edits, and external APIs
- **Multimodal engineering tasks** that read UI mockups, architecture diagrams, or error screenshots alongside source code

### Consider Alternatives When

- **Latency-sensitive completions** where always-on reasoning adds unwanted tokens and time. Grok 3 Fast or Grok 4 Fast Non-Reasoning return direct answers more quickly
- **General-purpose text tasks** such as summarization, content generation, and conversation. Grok 3 Fast or Grok 4 Fast handle these better
- **Image or video generation** where the Grok Imagine models produce media output
- **Maximum reasoning depth on non-coding problems** where Grok 4 and Grok 4.3 target math, science, and analytical reasoning beyond software engineering

## Best for

- **Autonomous Coding Agents:** Loops that read files, call tools, and edit code without step-by-step prompting
- **Codebase Refactoring:** Multi-file changes that require reasoning over project structure within the context of 256K tokens
- **Test Generation And Repair:** Producing test cases, running them through tool calls, and patching failures
- **Tool-Heavy Development Workflows:** Pipelines that combine model decisions with shell commands, file edits, and external APIs
- **Multimodal Engineering Tasks:** Reading UI mockups, architecture diagrams, or error screenshots alongside source code

## Consider alternatives

- **Latency-Sensitive Completions:** Always-on reasoning adds tokens and time per call. Grok 3 Fast or Grok 4 Fast Non-Reasoning return direct answers more quickly
- **General-Purpose Text Tasks:** Summarization, content generation, and conversation work better on Grok 3 Fast or Grok 4 Fast
- **Image Or Video Generation:** Use the Grok Imagine models for media output
- **Maximum Reasoning Depth On Non-Coding Problems:** Grok 4 and Grok 4.3 are tuned for math, science, and analytical reasoning beyond software engineering

## Frequently asked questions

### What is Grok Build 0.1 optimized for?

Grok Build 0.1 is purpose-built for agentic coding workflows. It's trained to act as an autonomous engineering agent that refactors code, invokes tools, produces structured outputs, and iterates through multi-step development tasks.

### Does Grok Build 0.1 support a non-reasoning mode?

No. Reasoning is always active on Grok Build 0.1 and reasoning effort is not configurable. Every response includes structured analysis before the final output.

### What inputs does Grok Build 0.1 accept?

Grok Build 0.1 accepts text and image input. You can include source code, diagrams, UI mockups, or error screenshots in the same request. Output is text.

### What is the context window for Grok Build 0.1?

The context window is 256K tokens, which fits substantial codebases or long agent histories in a single session.

### How does Grok Build 0.1 compare to Grok Code Fast 1?

Grok Build 0.1 is the next-generation coding model from SpaceXAI, with always-on reasoning, tool calling, and structured outputs designed for autonomous agents. Grok Code Fast 1 targets fast code generation and completion in interactive workflows.

### What does Grok Build 0.1 cost through Vercel AI Gateway?

Current pricing is shown on this page. AI Gateway routes across providers, and rates may vary by provider.

### How do I authenticate with Grok Build 0.1 through Vercel AI Gateway?

Use your Vercel AI Gateway API key with `spacexai/grok-build-0.1` as the model identifier. AI Gateway handles provider routing automatically through the AI SDK plus Chat Completions, Responses, and Messages APIs.

### Does Vercel AI Gateway support Zero Data Retention for Grok Build 0.1?

Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.

## Links

- [Model page](https://vercel.com/ai-gateway/models/grok-build-0.1)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://docs.x.ai/developers/models)