xAI: Grok Build 0.1

Fast Grok coding model tuned for agentic engineering and iterative edits

grok-build-0.1

AvailablexAIChatNew

Input / Output: $1.00 / $2.00
Context: 256K
Released: May 19, 2026
Max output: 128K
Modalities: VisionChat
Capabilities: Tool usePrompt CacheReasoning

About Grok Build 0.1

Grok Build 0.1 is the early-access xAI coding model that powers Grok Build, xAI's agentic coding tool with a terminal interface and headless scripting. It is tuned for engineering workflows and iterative edits, accepts text and images, supports tool calling and reasoning, and has a shorter context window than xAI's general Grok 4 models.

Where it works well

Tuned for agentic software engineering, where the model plans, edits and re-edits code across several turns.
Fast iteration suits tight edit-and-test loops that call tools repeatedly.
Accepts screenshots with code, so a rendering bug or a design mock-up can sit in the same prompt.
Supports reasoning, function calling and structured outputs for scripted pipelines.
Prompt caching lowers repeat cost when a repository summary is resent each turn.

When to choose another model

It is an early 0.1 release; general questions and long-document work are better served by Grok 4.7 or 4.3.
Its context window is the shortest among the Grok chat models, so very large codebases need selective loading.
Output is text only, and it is built for code rather than creative writing or open-ended chat.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.
02
Send your first request
Copy the example for your language and run it against the endpoint.
Text to textResponses API
POST/v1/responses
API format:
```
curl https://api.tokenlab.sh/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxx" \
  -d '{
    "model": "grok-build-0.1",
    "input": "Hello!"
  }'
```

Pricing

Official price is the model maker's public baseline. TokenLab price is what you pay for this model on TokenLab.

Default spec

per 1M tokens

Official price: Input $1.00 / Output $2.00 / Cache read $0.20
Official: Input $1.00 / Output $2.00 / Cache read $0.20
Discount: —

Prompt cache pricing

Cache read

Official price: $0.20
Official: $0.20
Discount: —

	Official priceper 1M tokens	Officialper 1M tokens	Discount
Default spec	Input $1.00 / Output $2.00 / Cache read $0.20	Input $1.00 / Output $2.00 / Cache read $0.20	—
Prompt cache pricing
Cache read	$0.20	$0.20	—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Oct 3, 2026, 07:24 PM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Grok Build 0.1 in Console with a prompt ready to edit or send.

Help me try grok-build-0.1 with a short message at /v1/responses. Show the reply, latency, and cost.

Use cases

Best for

Code
Reasoning
Vision

Terminal coding agent
Drive a repo from the command line: describe a change, let the model read files, edit them and run commands, then review the diff.
Scripted code maintenance
Run it headless in a script to apply a repeated migration, such as renaming an API across many files, and report what it touched.
UI fixes from screenshots
Show it a screenshot of a broken layout with the component source and ask for the CSS change that fixes the problem.

Prompt examples

Rename the config option timeoutMs to timeout_ms across the repo, update the docs and tests, and list each file you changed.

This screenshot shows the sidebar overlapping the table at narrow widths. The component source is attached. Fix it without changing desktop layout.

Add pagination to the /orders endpoint, write tests for the first and last page, and run them until they pass.

This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.

FAQ

What is Grok Build 0.1?

It is xAI's early-access coding model, described as an intelligent model for agentic software and engineering tasks. It is the model behind Grok Build, xAI's coding tool with an interactive terminal and headless script mode.

Does Grok Build 0.1 accept images?

Yes. It takes text and images as input and returns text, so a screenshot of a bug can go into the prompt next to the code.

Does Grok Build 0.1 support tool calling?

Yes. Function calling, structured outputs and reasoning are all supported, which is what a coding agent needs to read files, run commands and report results.

Should I use Grok Build 0.1 or Grok 4.7 for coding?

Grok Build is tuned for fast iterative edits in agent tools; Grok 4.7 is xAI's broader frontier model for coding and knowledge work. Try both on your own repository, and prefer 4.7 when tasks need deeper reasoning or more context.

Is Grok Build 0.1 stable?

The 0.1 version number marks an early release, so behaviour may change as xAI updates it. Pin the ID in production and re-run your own tests when you adopt a new version.

How much does Grok Build 0.1 cost?

On TokenLab, Grok Build 0.1 costs Input $1.00 / Output $2.00 per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

What are the context window and output limit of Grok Build 0.1?

Grok Build 0.1 accepts up to 256,000 tokens of context and returns up to 131,072 tokens in one response.

Which endpoint should Grok Build 0.1 use?

Use https://api.tokenlab.sh/v1/responses for Grok Build 0.1. The request example below shows the matching code shape.

Which operations does Grok Build 0.1 support?

Grok Build 0.1 supports Text to text. Select an operation above to see its endpoint and request example.