Grok 4.3 — API Pricing & Benchmarks

Grok 4.3 is xAI's flagship reasoning model, released in 2026-04. The API costs $1.25 per 1M input tokens and $2.50 per 1M output tokens ($1.56 blended at a 3:1 ratio), with cached input at $0.20. It supports a 1M-token context window. On the independently measured Artificial Analysis Intelligence Index it scores 37.9, ranking #45 of 68 models tracked on this site, with a median output speed of 137 tokens/sec.

Explore provider routes and additional benchmark sources for Grok 4.3

ProviderxAI
Input price / 1M tokens$1.25
Output price / 1M tokens$2.50
Cached input / 1M tokens$0.20
Blended price (3:1)$1.56
Context window1M
Max output tokens
Knowledge cutoff2025-12
Licenseproprietary
Input modalitiesT+I
Output speed (tok/s)137
Released2026-04
Artificial Analysis Intelligence Index37.9
LMArena Elo1398
GPQA Diamond90.1%
Humanity's Last Exam37.2%

Where Grok 4.3 fits

On a blended 3:1 basis Grok 4.3 costs $1.56 per 1M tokens, cheaper than 53% of the 80 priced models in this index. As xAI's flagship it is aimed at the hardest workloads — complex reasoning, agentic coding and multi-step tool use — where output quality dominates cost. Cached input is priced at $0.20 (84% below standard input), which rewards prompt structures with long stable prefixes — see our caching guide.

Price history

PeriodInput $/1MOutput $/1MCached $/1M
2026-07-18 → current$1.25$2.50$0.20

No list-price changes recorded since tracking began. Full dataset: price-history.json (CC BY 4.0).

Alternatives at a similar price

About xAI

xAI's Grok models compete aggressively on price: Grok 4.6 ties the proprietary frontier on the Artificial Analysis index at a mid-tier price point, and the older Grok 4.x models are among the cheapest ways to buy a large context window.

More xAI models

← Full comparison table (60+ models, live filters)