XGrok 4.20API

Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities.

2MContext window · tokens

$1.25Input price · per M tokens

$2.5Output price · per M tokens

xAIProvider

Prices update automatically — checked daily against provider list prices.

$1.56 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
cheaper than 58% of the 192 commercial models tracked here
3 of 6 xAI models tracked here, from cheapest

See open-source alternatives → Compare all model prices

Benchmarks & performance

Independent benchmark scores for Grok 4.20, measured by Artificial Analysis. Higher is better. Measurement mode: Reasoning.

Intelligence index38

GPQA91.1%

Humanity's Last Exam34.5%

Long Context Reasoning62.3%

SciCode45.6%

IFBench81.2%

τ²-Bench93%

Terminal-Bench Hard37.9%

💰 Blended price$1.563 / 1M tokens

📈 Value24.3 intelligence points per $

vs. models measured heretop 31%

Scores higher than 69% of the 273 models measured by Artificial Analysis and tracked here.
Models at this level cost $1.35 per 1M tokens (median of 24) — this one costs $1.56.
Cheaper and better on this index: GLM 5.3 Flash · Gemini 3.7 Flash · Gemini 3.7 Flash (batch) and 26 more

Benchmark data by Artificial Analysis

About this model

Grok 4.20 is a commercial AI model by xAI. The specifications below are tracked automatically: pricing is refreshed daily from public list prices, so the numbers on this page reflect the current cost of using the model through its API.

Frequently asked questions

What is Grok 4.20?

Grok 4.20 is an AI language model from xAI. It is a proprietary model, available through an API. It scores 38 on the Artificial Analysis intelligence index.

Is Grok 4.20 free?

Grok 4.20 is not free: it costs $1.25 per million input tokens and $2.5 per million output tokens. Open-weight alternatives can be self-hosted at no per-token cost.

What is Grok 4.20 good at?

Independent benchmarks from Artificial Analysis give it GPQA 91.1%, Humanity's Last Exam 34.5%, Long Context Reasoning 62.3%, SciCode 45.6%, IFBench 81.2%, τ²-Bench 93%, Terminal-Bench Hard 37.9%.