xAI: Grok 4.20

xAI: Grok 4.20

x-ai · Released Mar 31, 2026 Professional
Intelligence #10 / 576
82.0 Our Score
Speed #64 / 271
157.2 tokens / sec
Input #455 / 577
$1.25 per 1M tokens
Output #410 / 577
$2.50 per 1M tokens
Context #2 / 577
2M tokens

Analysis Summary

Grok 4.20 is an earlier xAI model with a 2M token context window, vision, file input, tool use, and function calling. Its intelligence index of 29 and coding index of 22 place it in the moderate tier, and its long-context reasoning score is low despite the large context window. Pricing at $1.25 input and $2.50 output per million tokens is competitive.

For businesses, the 2M context is a genuine advantage for very long document workflows, but the limited reasoning depth means it is better suited to retrieval and summarisation tasks than complex analysis or coding. Its agentic score of 38.3 is below average for tool-use pipelines.

Grok 4.20 is a reasonable option for teams that specifically need a very large context window at a moderate price, but most business workloads will be better served by more capable models in a similar price range.

Assessed June 9, 2026

Editorial notes

Grok 4.20 from xAI has a 2M token context window and broad modality support, but moderate reasoning and coding scores limit its fit for complex business tasks.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence4.7Technical4Value7.3Content3.8
Intelligence 4.7/10
Technical 4/10
Content 3.8/10
Value 7.3/10

How xAI: Grok 4.20 compares

XAI: Grok 4.20 ranks #115 of 378 AI models we track for overall intelligence, #134 of 315 for coding, #112 of 289 for agentic tasks. Its 2M-token context window is larger than 100% of the models we list. At $1.25 per million input tokens it is cheaper than 21% of comparable models.

About xAI: Grok 4.20

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..

Capabilities

Tool Use Function Calling Vision

Performance Indices

Source: Artificial Analysis

29 Intelligence Index
22 Coding Index
38.3 Agentic Index

Benchmark Scores

Intelligence

GPQA Diamond 77.6% Graduate-level scientific reasoning
HLE 24.2% Humanity's Last Exam
SciCode 32.8% Scientific computing

Technical

TerminalBench Hard 16.7% Agentic terminal tasks
τ²-Bench 59.9% Conversational agent benchmark

Content

IFBench 49.3% Instruction following
LCR 17.3% Long-context reasoning

Benchmark data from Artificial Analysis and Hugging Face

How does xAI: Grok 4.20 stack up?

Compare side-by-side with other professional models.

Compare Models

Model Information

OpenRouter ID x-ai/grok-4.20
Providerx-ai
Release Date March 31, 2026
Context Length2,000,000 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $1.25 $0.001250
Output $2.50 $0.002500

Live Performance

Live endpoint metrics, refreshed every 30 minutes.

100%
Avg Uptime
720ms
Best Latency (TTFT)
103 tok/s
Best Throughput
1/1
Active Endpoints
Available via: xAI

Leaderboard Categories

Frequently asked questions about xAI: Grok 4.20

How much does xAI: Grok 4.20 cost?

xAI: Grok 4.20 costs $1.25 per million input tokens and $2.50 per million output tokens.

What is the context window of xAI: Grok 4.20?

xAI: Grok 4.20 has a context window of 2,000,000 tokens (2M).

Is xAI: Grok 4.20 good for coding?

On our coding benchmark index, xAI: Grok 4.20 ranks #134 of 315 models, placing it in the broader range of the field for code generation and debugging.

What can xAI: Grok 4.20 do?

xAI: Grok 4.20 supports image/vision input, tool use, and function calling.

Who created xAI: Grok 4.20?

xAI: Grok 4.20 is developed by xAI and was released on March 31, 2026.