Grok Build 0.1

Grok Build 0.1 is xAI's coding model, trained for agentic software engineering and used inside its Grok Build coding agent. It entered early access in May 2026 and opened to the public API as a beta later that month, with a 256K-token context window.

By xAIReleased May 2026Data checked October 10, 2026

PreviewClosedEfficient

Specifications

Context window: 250Kabout 192,000 words, or 380 pages
Max output: Not published
Input price: $1per 1M tokens
Output price: $2per 1M tokens
Cached input: $0.20per 1M tokens
Weights: ClosedProprietary
Parameters: Undisclosed
Input types: Text, Images
Output types: Text
Reasoning mode: Yes
Tool calling: Yes
Released: May 2026Preview

Rates for prompts under 200K tokens; at 200K or more, $2 input, $0.40 cached and $4 output. No Batch API. Max output is not stated by xAI.

What it costs in practice

Workload	Monthly cost at list price
Support chatbot30,000 conversations a month, 2,000 input and 400 output tokens each	$84
Document summaries2,000 documents a month, 12,000 input and 800 output tokens each	$27
Coding agent1,000 tasks a month, 60,000 input and 6,000 output tokens each	$72

Standard rates, no caching or batch discounts. Run your own numbers.

Strengths

$1 input and $2 output per million tokens
Trained for agentic coding, debugging and MCP workflows
Also answers to the older grok-code-fast-1 model ID

Trade-offs to weigh

Launched as a public beta
256K-token context window, smaller than other current Grok models

Where it fits

xAI positions Grok Build 0.1 for:

codingagentslow latency

Where you can use it

API
OpenRouter
Vercel AI Gateway

Alternatives to consider

Model	Tier	Context	Input / output per 1M
Gemini 3.5 Flash-LiteGoogle	Efficient	1M	$0.30 / $2.50	Compare
SonarPerplexity	Efficient	—	$0.25 / $2.50	Compare
Qwen3.8-27BAlibaba (Qwen)	Efficient	256K	$0.80 / $4	Compare
Gemini 3.1 Flash-LiteGoogle	Efficient	1M	$0.25 / $1.50	Compare

Frequently asked questions

How much does Grok Build 0.1 cost?

Grok Build 0.1 lists at $1 per million input tokens and $2 per million output tokens, with cached input at $0.20 (checked October 10, 2026). Rates for prompts under 200K tokens; at 200K or more, $2 input, $0.40 cached and $4 output. No Batch API. Max output is not stated by xAI. Confirm current rates on the provider's pricing page before you commit.

What is the context window of Grok Build 0.1?

Grok Build 0.1 accepts up to 256,000 tokens of context (about 192,000 words, or 380 pages). Long prompts cost more and can be slower, so most apps send only what the task needs.

Is Grok Build 0.1 open source?

No. Grok Build 0.1 is a proprietary model from xAI; its weights aren't published. You can use it through the xAI API and through OpenRouter, Vercel AI Gateway.

What is Grok Build 0.1 best for?

xAI positions Grok Build 0.1 for coding, agents, low latency. It accepts text, images as input, has a reasoning (thinking) mode and supports tool calling. Test it on a sample of your own tasks before you choose it for production.

Sources

Facts checked against these pages on October 10, 2026. Spot an error? Tell us.

Still choosing a model?

Send us your use case and constraints. We'll come back with a shortlist and an evaluation plan you can run on your own data.

Free and vendor-neutral: no model provider pays for placement.
Your details go only to partners you agree to.