/ Models

Language models

xAI: Grok 4.3

Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...

Maker
X-ai
Context window
1M
Max output
Input / 1M
$1.25
Output / 1M
$2.50
1M in + 1M out
$3.75

Everything else

Max output
Input / 1M$1.25
Output / 1M$2.50
Cache read / 1M$0.2
Cache write / 1M
1M in + 1M out$3.75
Takestext, image, file
Returnstext
Toolsyes
Reasoningoptional · high, medium, low, none
Open weightsno
Released2026-04-30
Knowledge cutoff
Retires
Catalog idx-ai/grok-4.3

Benchmarks

sourceepoch
gpqa0.888
gpqaStderr0.0196
aime0.933
aimeStderr0.0304
simpleQA0.38
simpleQAStderr0.0154

Benchmark scores by Epoch AI, CC BY 4.0.

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models