Grok 4.3
xAI · Released – · grok-4.3
$1.25
Input price / 1M tokens
#27 of 61, cheapest first
$2.50
Output price / 1M tokens
#14 of 61, cheapest first
1M
Context window
#29 of 71
132
Output tokens / second
#21 of 61
Summary
Grok 4.3 is a proprietary model from xAI.
At $1.25 input and $2.50 output per million tokens, it is #27 of 61 on input price, cheapest first.
Its 1M-token context window ranks #29 of 71.
Measured output speed is 132 tokens per second, #21 of 61.
Fast, low-cost xAI model with strong tool calling and instruction following, reasoning effort from none to xhigh (default low). It replaced the retired Grok 3 and Grok 4 Fast models.
Benchmarks · 0 reported
No benchmark score we could source for this model. We show scores only with a source link.
Sources
- price, cached price, long-context tier, 20% batch discount: docs.x.ai/developers/pricing, checked 2 Oct 2026
- API ID, 1M context, modalities, reasoning efforts: docs.x.ai/developers/models/grok-4.3, checked 2 Oct 2026
- retired slugs redirect to grok-4.3: docs.x.ai/developers/migration/may-15-retirement, checked 2 Oct 2026
- output speed: artificialanalysis.ai/models/grok-4-3, checked 2 Oct 2026
Building on Grok 4.3?
Get the architecture right before the bill arrives.
We size caching, routing and fallbacks for your workload on a free call, and tell you where a cheaper model is good enough.