Skip to content

Grok 4.3

Released 2026-04 · reasoning · 1.0M tokens · 0 benchmarks

Editorial notes

API GA 30 abril 2026 (beta SuperGrok Heavy 17 abril). Reasoning siempre activo. Native video input (max 5min, 1080p). Native PDF/PPTX/XLSX generation. tau2-Bench Telecom 98%, IFBench 81%, GDPval-AA Elo 1500 (+321 vs 4.20). Pricing $1.25/$2.50 per MTok (cache $0.20).

Spec sheet

Company
xAI
Country
US
Type
reasoning
Release
2026-04
Context
1.0M tokens
Pricing (xai)
$1.25/$2.5/M
Slug
grok-4-3
No scores published for this model. The editorial notes have additional context.
Cite this model
BibTeX · APA

BibTeX

@misc{frontier-grok-4-3,
  title  = {Grok 4.3},
  author = {{xAI}},
  year   = {2026},
  note   = {Frontier Benchmarks AI atlas. Accessed 2026-05-08},
  url    = {https://frontierbenchmarks.com/models/grok-4-3}
}

APA

xAI (2026). Grok 4.3 [Large language model]. Frontier Benchmarks AI. Retrieved 2026-05-08, from https://frontierbenchmarks.com/models/grok-4-3

Citation reflects the atlas page, not the original model paper. For the paper, see the "Resources" section above.