Grok 4.3

Grok 4.3

grok-4.3

Our most advanced flagship model, leading the industry in non-hallucination rate, agentic tool calling, and instruction following capabilities.

View as Markdown

Try in playground

At a glance

Modalities

Text, Image

Text

Context window

1,000,000

Pricing

Capabilities

Function calling

Connect the xAI model to external tools and systems.

Structured outputs

Return responses in specific, organized formats.

Configurable reasoning

Supports none (no reasoning at all), low, medium, and high.

Pricing

Input

Tokens

$1.25/ 1M tokens

Cached tokens

$0.20/ 1M tokens

Output

Tokens

$2.50/ 1M tokens

You are charged for each token used when making calls to our API.

Using cached input tokens can significantly reduce your costs.

This model is available on multiple clusters, you can find full regional based pricing below.

How does pricing work

Tool pricing

Request increased rate limits

We charge different rates for requests which exceed the 200K context window

Details

Model name

Aliases

Region

Rate limits

Requests per minute

1,800

Tokens per minute

10,000,000

Quickstart

Create an API Key and make your first request.

Tool use

Let Grok perform actions and look up information.

Structured outputs

Let Grok generate structured outputs.