Back to Models

Grok 4.20 0309 v2

![xAI](https://artificialanalysis.ai/img/logos/xai.svg)xAI
29/ 57

Intelligence Score

Intelligence

29

#82 of 203 (top 40%)

Speed

90 tok/s

#74 of 131

Price

$3.00

per M tokens

#112 cheapest of 136

Context Window

2M

tokens

Latency: 1ms (#13)

Score Breakdown

Quality Score48%
Speed Score13%
Cost Score73%

Similar Models

DeepSeek V3.2 Speciale

![DeepSeek](https://artificialanalysis.ai/img/logos/deepseek_small.svg)DeepSeek

29intelligence

ERNIE 5.0 Thinking Preview

![Baidu](https://artificialanalysis.ai/img/logos/baidu_small.svg)Baidu

29intelligence

Grok Code Fast 1

![xAI](https://artificialanalysis.ai/img/logos/xai.svg)xAI

29intelligence

MiMo-V2-Flash

![Xiaomi](https://artificialanalysis.ai/img/logos/xiaomi_small.svg)Xiaomi

30intelligence

Nova 2.0 Lite (medium)

![Amazon](https://artificialanalysis.ai/img/logos/aws_small.svg)Amazon

30intelligence

Use This Model

Claude Code

claude --model grok-4-20-non-reasoning

API (cURL)

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -d '{
    "model": "grok-4-20-non-reasoning",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Vercel AI SDK

import { generateText } from "ai";
import { openrouter } from "@openrouter/ai-sdk-provider";

const { text } = await generateText({
  model: openrouter("grok-4-20-non-reasoning"),
  prompt: "Hello",
});
Back to Models