modelgrep
X

xAI: Grok 4.20

x-ai/grok-4.20

82nd smartest of 178ReasoningToolsJSONVision
Use via OpenRouter ↗
Intelligence
29.7
82nd of 178
Design Elo
Speed
42
196th fastest
Latency
3.7s
first token
Input price
$1.25
219th cheapest
Context
2M

How it compares

Smarter than54%
of all ranked models
Faster than34%
of all ranked models
Cheaper than27%
of all ranked models

Overview

Grok 4.20 is a reasoning model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...

Benchmarks

independent · via OpenRouter
Artificial Analysis53th percentile
Intelligence Index
29.7
Coding Index
25.4
Agentic Index
37.8
GPQA Diamond
79%
Humanity's Last Exam
23%
SciCode
32%
Tau²-Bench (agentic)
70%

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
xAI$1.25$2.50100%

Specifications

Context window2M
Max output
Knowledge cutoffSep 2025
Input modalitiestext, image, file
Output modalitiestext
Prompt caching
Cache read price$0.200/M
ModeratedNo

Grok 4.20 FAQ

How much does Grok 4.20 cost?

Grok 4.20 costs $1.25 per million input tokens and $2.50 per million output tokens via OpenRouter, making it 219th cheapest of 298 paid models.

How smart is Grok 4.20?

Grok 4.20 scores 29.7 on the Artificial Analysis Intelligence Index, ranking 82nd of 178 benchmarked models, with a GPQA Diamond score of 79%.

How fast is Grok 4.20?

Grok 4.20 generates around 42 tokens per second with 3.7s time-to-first-token (p50), the 196th fastest tracked model.

What is Grok 4.20's context window?

Grok 4.20 supports a 2M-token context window. It accepts text, image, file input.

Compare head-to-head