xAI
xAI
Multimodal model · United States ·May 2026

Grok 4.3

Multimodal Proprietary
1M
Context
2
Benchmarks

About Grok 4.3

Grok 4.3 is an AI model developed by xAI, in the multimodal category, released in 2026, made available as a proprietary (API-only) model. xAI's cost-efficient frontier model with built-in reasoning, a 1-million-token context window, and native video input. I.

On this page you'll find Grok 4.3's full specifications, including a context window of 1M tokens, 2 benchmark results. Review provider pricing and benchmark scores below, or compare Grok 4.3 head-to-head with other multimodal models.

→ More models by xAI → All multimodal models → AI benchmarks leaderboard

Community

Would you run Grok 4.3 again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

Grok 4.3 benchmark scores▶
Compare on the benchmark table →
Benchmark Category Score Variant
GPQA Diamond reasoning 90.1%
Humanity's Last Exam reasoning 35%

More models like Grok 4.3

AI
NeuroChess
· 72.3K
 xAI
Grok Imagine Video 1.5
xAI
 xAI
Grok Build 0.1
xAI
 xAI
Grok Voice Think Fast 1.0
xAI
 xAI
Grok 4.20
xAI
 xAI
Grok Collections API
xAI

Frequently asked questions

What is Grok 4.3? ▶

xAI's cost-efficient frontier model with built-in reasoning, a 1-million-token context window, and native video input. I It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Grok 4.3? ▶

Grok 4.3 was developed by xAI and released in 2026.

Is Grok 4.3 open source or proprietary? ▶

Grok 4.3 is a proprietary model. It is accessed through an API rather than by downloading the weights.

What is Grok 4.3's context window? ▶

Grok 4.3 supports a context window of 1M tokens.

How much does Grok 4.3 cost? ▶

Pricing for Grok 4.3 depends on the provider. See the providers table on this page for the latest API rates.

How does Grok 4.3 perform on benchmarks? ▶

Grok 4.3 is benchmarked across 2 evaluations on GenAIList, including GPQA Diamond (90.1%). See the full benchmark table below and compare it with other models.

Introducing Grok 4.3
Grok Build + Grok 4.3 FULL Test – xAI's Claude Code & Codex Competitor!
Ultimate GROK Tutorial (How to use Grok 4.3)

Know a great video about Grok 4.3?