Grok 4.3

Language modelCard summarized

Fast, reliable model with strong tool calling and instruction following capabilities.

● Re-checked 12 Oct 2026 · 44 facts · 0 corrections · 1 unconfirmedSource: Grok 4.3 model page (xAI API docs; no system card or launch post found)

Use it via API

$636 /month

$12.72 per 1K requests

RAG over docs: 12K in · 600 out · 50K requests/mo · 30% cached · change

Code example Compare

Where to call it

xAI APIgrok-4.3

Supports

Image input
Structured outputs
Reasoning control
Tool calling
Web search
Prompt caching
Batch API

Full feature support

Good for

Tool calling and instruction following
Migration target for grok-4-1-fast, grok-4-fast, grok-4-0709 and grok-3 (low or none effort)
Bulk jobs through the Batch API at 20% off

Overview

xAI · 02Fast

Grok 4.3

Fast, reliable model with strong tool calling and instruction following capabilities.

Cost: $1.25 in
Context: 1M

Input / output: $1.25 / $2.50
Max output: —
Knows up to: —
Released: —

xAI describes Grok 4.3 as a "fast, reliable model with strong tool calling and instruction following capabilities." It takes text and images, returns text, has a 1M-token context and configurable reasoning effort from none to xhigh (default low). Since 15 May 2026 it also serves requests sent to retired Grok 4 Fast, Grok 4.1 Fast, Grok 4 and Grok 3 slugs. API docs; migration guide

grok-4.3

Input / output per 1M: $1.25 / $2.50
Context window: 1M
Max output: —
Knows up to: —
Reasoning: Configurable (none, low, medium, high, xhigh)
Weights: Closed

About this card. A model card is the maker's own account of a model: what it's for, how it was trained and tested, and where it falls short. This page condenses xAI (SpaceXAI)'s Grok 4.3 model page (xAI API docs; no system card or launch post found). Every claim carries its source page.