xAI: Grok 4.3

Name: Grok 4.3 API
Brand: Xai

stable

Grok 4.3 is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

grok-4.3grokreleased Apr 17, 2026

Provider Quick start

Context

tokens

Max output

30K

tokens

Input

$1.25

per 1M

Output

$2.50

per 1M

Activity

Daily period usage

Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.

Providers

ProviderContextInput /MOutput /M

xAI

1M$1.25$2.50

Pricing

Item	Price	Unit
Input	$1.25	per 1M tokens
Output	$2.50	per 1M tokens
Cache read	$0.20	per 1M tokens

Performance

Reliability

Compare

Compare usage and performance

Place this model beside up to three other catalog models.

Capabilities

Modalities

Input

Output

Details

Model ID: grok-4.3
Family: grok
Status: stable
Knowledge: -
Released: Apr 17, 2026

Gateway Config

API: 2024-01-01
Auth: XAI_API_KEY
Discovery: static
Provider type: static

Quick Start

index.ts

import Everstack from "@everstack/node";const client = new Everstack({  apiKey: process.env.EVERSTACK_API_KEY!,  baseUrl: "https://{instance}.{region}.everstack.ai",});const completion = await client.chat.completions.create({  model: "@xai/grok-4.3",  messages: [{ role: "user", content: "Explain vector cache routing." }],});console.log(completion.choices[0]?.message?.content);

Endpoint

Base URL

https://api.x.ai/v1

Chat completions

https://api.x.ai/v1/chat/completions

Model

grok-4.3

Auth env

XAI_API_KEY

Grok 4.3 FAQ

How much does the Grok 4.3 API cost?

Through xAI, Grok 4.3 costs $1.25 per 1M input tokens and $2.50 per 1M output tokens.

What is the context window of Grok 4.3?

Grok 4.3 accepts up to 1M tokens of context and returns up to 30K output tokens on xAI.

What can Grok 4.3 do?

Grok 4.3 supports chat, function calling, image input and reasoning. It accepts text, image and PDF input.

How do I call Grok 4.3 through Everstack?

Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @xai/grok-4.3. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.