XAI: Grok 4.20

x-ai/grok-4.20

Context

Input

text, image

Output

text

Tool calling

Supported

About this model

Grok 4.20 Reasoning is a high-performance model by xAI designed for complex logic and math, scientific and technical analysis, multi-step investigations, and high-stakes tasks where accuracy matters most. It incorporates a 'thinking' mechanism before responding and offers strict prompt adherence alongside agentic tool calling.

Compare Text Models

Input modalities

text

Accepted as model input

image

Accepted as model input

Providers

Available routing options for this model through OneInfer.

grok

Available

Input tokens

$1.250 / 1M tokens

Output tokens

$2.500 / 1M tokens

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

Usage	Price
Input tokens	$1.250 / 1M tokens
Output tokens	$2.500 / 1M tokens
Cached input tokens	$0.200 / 1M tokens

Performance

Published evaluation results associated with this model.

Coding

SWE-bench Verified76.7

SWE-bench Pro51.8

LiveCodeBench Pro74.2

Vibe Code Bench v1.14.06

Agentic

ARC-AGI-253.3

Knowledge

GPQA-D88.5

Humanity's Last Exam without tools31.6

HealthBench Hard20.3

MedXpertQA Text50.2

Multimodal

MMMU-Pro75.2

CharXiv60.9

ERQA54.1

SimpleVQA57.4

MedXpertQA Multimodal65.8

API example

Refer Documentation

curl https://api.oneinfer.ai/v1/ula/chat/completions \
  -H "Authorization: Bearer $JWT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "x-ai/grok-4.20",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'