Grok Build 0.1
Grok Build 0.1 is SpaceXAI's coding model purpose-built for agentic software engineering workflows. It supports tool calling, structured outputs, text and image input, and a context window of 256K tokens, with always-on reasoning for multi-step development tasks. Your use is subject to SpaceXAI's Terms & Privacy Policies.
View API reference- Input and output price
- Input $1, Output $2, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'spacexai/grok-build-0.1', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out Grok Build 0.1 by SpaceXAI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Grok Build 0.1
Grok Build 0.1
Copy link to headingProviders
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call Grok Build 0.1 through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.
Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'spacexai/grok-build-0.1', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same Grok Build 0.1 request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'spacexai/grok-build-0.1', system: 'You are a concise technical assistant.', prompt: 'Summarize the tradeoffs between static generation and SSR.', maxOutputTokens: 1024, });
console.log(result.text);}
main().catch(console.error);Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID in the form creator/model, e.g. spacexai/grok-build-0.1. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. Grok Build 0.1 supports up to 256,000 output tokens. Reasoning tokens count toward this limit. |
reasoning | 'provider-default' | 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | No | Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under providerOptions take precedence when both are set. See the Reasoning section below. |
providerOptions | Record<string, JSONValue> | No | AI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Text | — | — | — | — | Prompt and response share the 256K-token context window |
| Image | — | URL, base64, Uint8Array | — | — | Sent as image parts in messages; counts as input tokens |
Provider options
Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.
Learn more in the AI SDK xai provider docs.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'spacexai/grok-build-0.1', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['xai'], }, }, });
console.log(result.text);}
main().catch(console.error);These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.
| Parameter | Type | Required | Description |
|---|---|---|---|
providerOptions.gateway.only | string[] | No | Restrict routing to these provider slugs. Requests fail over only within the listed providers. |
providerOptions.gateway.order | string[] | No | Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks. |
providerOptions.gateway.sort | 'cost' | 'ttft' | 'tps' | No | Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order. |
providerOptions.gateway.zeroDataRetention | boolean | No | Route only to providers with a zero-data-retention policy for this model. |
Routing across providers
AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.
Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.
Reasoning
AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.
Learn more in the AI Gateway reasoning guide.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'spacexai/grok-build-0.1', prompt: 'Explain the Monty Hall problem step by step.', reasoning: 'high', });
console.log(result.text);}
main().catch(console.error);Image input
Send images alongside text as message parts. Images count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'spacexai/grok-build-0.1', messages: [ { role: 'user', content: [ { type: 'text', text: 'Describe this image.' }, { type: 'image', image: 'https://example.com/photo.jpg' }, ], }, ], });
console.log(result.text);}
main().catch(console.error);Tool calling
Expose tools the model can call. Define each tool’s inputs with a Zod schema.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'spacexai/grok-build-0.1', prompt: 'What is the weather in San Francisco?', tools: { getWeather: tool({ description: 'Get the current weather for a location', inputSchema: z.object({ location: z.string() }), execute: async ({ location }) => ({ location, temperatureC: 18 }), }), }, });
console.log(result.text);}
main().catch(console.error);Copy link to headingMore models by SpaceXAI
| Model |
|---|
| 500K | 2.4 s | 60 tps | $2/M+1 more | $6/M+1 more | Read$0.50/M | $5/K | +2 | | 09/21/2026 | |||||
| 500K | 2.2 s | 75 tps | $2/M+1 more | $6/M+1 more | Read$0.50/M | $5/K | +2 | | 08/12/2026 | |||||
| 500K | 1.6 s | 55 tps | $2/M+1 more | $6/M+1 more | Read$0.30/M | $5/K | +4 | | 07/08/2026 | |||||
| 1M | 1.1 s | 124 tps | $1.25/M+1 more | $2.50/M+1 more | Read$0.20/M | $5/K | +4 |  | 04/30/2026 | |||||
| 2M | 0.4 s | 103 tps | $1.25/M+1 more | $2.50/M+1 more | Read$0.20/M | $5/K | +3 | | 03/10/2026 | |||||
| 1M | 1.0 s | 154 tps | $0.20/M | $0.50/M | Read$0.05/M | — | +3 | | 11/19/2025 |
Copy link to headingAbout Grok Build 0.1
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.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: 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.
- Configuration: 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.
- Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use Grok Build 0.1
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 when
- 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
Copy link to headingConclusion
Grok Build 0.1 is SpaceXAI's purpose-built model for agentic coding. Always-on reasoning, tool calling, structured outputs, and a context window of 256K tokens make it suitable for autonomous engineering loops rather than single-shot completions. Teams building coding agents should evaluate Grok Build 0.1 against Grok Code Fast 1 and the Grok 4 Fast variants for the right balance of agentic depth, latency, and cost.
Copy link to headingFrequently 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-0.1as 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.