xAI

Grok 4.6 — Benchmark Scores, Pricing & Performance Analysis

MIDxAI
Input Cost
$2.0/1M
Output Cost
$6.0/1M
Context Window
500K
Max Output
500K
Knowledge Cutoff
Feb 2026
Accepts
text, image, pdf

Grok 4.6 is an AI model by xAI. View detailed benchmark scores, pricing data, and performance metrics on Serenities AI Models.

Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.

General Benchmarks

AA Intelligence Index
44.47th of 66

Artificial Analysis composite intelligence score across 10 sub-benchmarks

Artificial Analysis (via OpenRouter)

Coding Benchmarks

Design Arena ELO
130313th of 120

Human preference ELO for building things — websites, UI, games, charts, SVG

Design Arena (via OpenRouter)
AA Coding Index
76.85th of 96

Artificial Analysis composite coding score

Artificial Analysis (via OpenRouter)
Website Arena ELO
130511th of 108

Human preference ELO for building a working web page from a brief

Design Arena (via OpenRouter)

Reasoning Benchmarks

AA Agentic Index
53.43rd of 70

Artificial Analysis composite score for multi-step tool-using tasks

Artificial Analysis (via OpenRouter)
GPQA Diamond
93.3%5th of 140

Graduate-level science Q&A by domain experts

Papers
τ²-Bench Airline
76.0%17th of 93

Multi-turn service agent making tool calls under strict policy constraints

OpenRouter (measured)

Cost Benchmarks

Output Cost
$6.0310th of 413

Cost per 1M output tokens

OpenRouter API
Input Cost
$2.0336th of 413

Cost per 1M input tokens

OpenRouter API
Cached Input Cost
$0.50120th of 136

Cost per 1M cached input tokens — the price that actually applies to a long agent conversation

OpenRouter API

Context Benchmarks

Context Length
500K88th of 451

Maximum context window size

OpenRouter API

Available from 28 providers

The same model costs different amounts depending on who serves it. You can bring your own key for 6 of these — connect it here.

ProviderInput / 1MOutput / 1MCached inContextYour key
Kenari$0$0500K
302.AI$2$6500K
Abacus$2$6$0.5500K
AIHubMix$2$6$0.5500K
Cloudflare AI Gateway$2$6$0.5500K
CrossModel$2$6$0.5500K
DevPass (LLM Gateway)$2$6$0.5500K
Eden AI$2$6$0.5500K
GitHub Copilot$2$6$0.5500K
Kilo Gateway$2$6$0.5500K
LLM Gateway$2$6$0.5500K
Merge Gateway$2$6$0.5500K
NanoGPT$2$6$0.5500K
Ofox$2$6$0.5500K
OpenCode Go$2$6$0.5500K
OpenCode Zen$2$6$0.5500K
OpenRouter$2$6$0.5500KSupported
Opper$2$6$0.5500K
OrcaRouter$2$6$0.5500K
Perplexity Agent$2$6$0.5500K
Requesty$2$6$0.5500K
Vercel AI Gateway$2$6$0.5500KSupported
Vertex$2$6$0.5524KSupported
xAI$2$6$0.5500KSupported
Amazon Bedrock$2.2$6.6$0.55500KSupported
Venice AI$2.27$6.8$0.57500K
Azure200KSupported
Neon500K

Grok 4.6 — Benchmark Scores Overview

Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).

Grok 4.6 — Frequently Asked Questions

How much does Grok 4.6 cost?

Grok 4.6 costs $2.0 per 1M input tokens and $6.0 per 1M output tokens. This is mid-range pricing for its capability level.

What is the context window of Grok 4.6?

Grok 4.6 has a context window of 500K tokens. This determines how much text, conversation history, and code the model can process in a single request.

Who created Grok 4.6?

Grok 4.6 was created by xAI. It is classified as a mid model in our catalogue.

Is Grok 4.6 open source?

No, Grok 4.6 is a proprietary model. It is available through xAI's API and compatible providers.