Grok 4.5

xAI llm

xAI's flagship model trained alongside Cursor for coding, agentic and knowledge work, positioned as the default model in Grok Build.

overall ⌄

—

nothing published

price · $/M tokens

2 / 6

in / out, as of 2026-07-25

to run it yourself ⌄

API only

no weights to run

Benchmarks

What its maker published, and what anyone else measured. Every figure links the document it came from.

benchmark	published	measured
GPQA	—	93.1
HLE	—	40.3

Nothing is both cheaper and ranked as high. This model is on the value frontier — whatever you pay for it, you are paying for something.

No recorded lineage — root or standalone model.