xAI

Grok 4.7

CTX500K

86Quality

Reasoning · Vision · Tools

Input$2/M

Output$6/M

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

PaidProprietary1014/1040

Drag to turn

xAITextUncommon

Grok 4.7

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

grok-4.7

Type: Text
Quality: 86 · Top 14% on the Epoch Capabilities Index
Context window: 500,000 tokens
Max output: 500,000 tokens
Input price: $2.00 / 1M tokens
Output price: $6.00 / 1M tokens
Cache read: $0.50 / 1M tokens
Cache write: —
Released: Sep 21, 2026
Knowledge cutoff: May 2026
Takes in: Text, Image, PDF
Puts out: Text
Reasoning: Yes
Tool calling: Yes
Structured output: Yes
File attachments: Yes
Access: Paid
License: Proprietary
Rarity: Uncommon
Set number: 1014/1040

Open xAI docs Quality 86 Where to run it 27 Evolution 5/5 Meet its creature Battle Qwen3.8 Max

Weights aren’t public. Use is governed by xAI’s terms. Specs from models.dev, last changed Oct 18, 2026. Official source: docs.x.ai.

How good is it?

Public leaderboard scores for Grok 4.7, refreshed daily from Epoch AI and LMArena.

Top 14% of the 277 models on the Epoch Capabilities Index: #39.

Quality is the share of a leaderboard’s models this one beats, from 0 to 100. Chat models are rated on Epoch AI’s Capabilities Index when it lists them, otherwise on LMArena; image and video models on LMArena’s image and video arenas.

Leaderboards

Epoch Capabilities Index#39 of 277
One number fitted from dozens of hard benchmarks, from science questions to agentic coding.154.4 index
LMArena Text#153 of 416
People compare two anonymous answers and vote for the better one.1,401 rating
Listed as grok-4.7-xhigh
LMArena Text · Coding#136 of 411
The text arena’s coding prompts only.1,432 rating
Listed as grok-4.7-xhigh
LMArena Text · Math#136 of 400
The text arena’s math prompts only.1,412 rating
Listed as grok-4.7-xhigh
LMArena Text · Creative writing#122 of 414
The text arena’s creative writing prompts only.1,387 rating
Listed as grok-4.7-xhigh
LMArena WebDev#16 of 144
Each model builds a web app from the same prompt; people pick the better one.1,639 rating
Listed as Grok 4.7 (xHigh)
LMArena Vision#80 of 165
Questions about images, voted by people.1,228 rating
Listed as grok-4.7-xhigh

Benchmarks Epoch AI runs

Scores from Epoch AI and LMArena, licensed CC BY 4.0. Boards list models under their own names, so a close match is shown with the name it was scored under. Credits

Where to run it

27 providers sell Grok 4.7 through an API. Prices are per million tokens, cheapest first.

CheapestPrime Inference$1.60 in · $4.80 out
From the labxAI$2.00 in · $6.00 out

API providers

Provider	Input	Output	Context
Prime InferenceCheapest paid`x-ai/grok-4.7`	$1.60	$4.80	500K
302.AI`grok-4.7`	$2.00	$6.00	500K
Amazon Bedrock`global.xai.grok-4.7`	$2.00	$6.00	500K
Cloudflare AI Gateway`xai/grok-4.7`	$2.00	$6.00	500K
CommandCode`xai/grok-4.7`	$2.00	$6.00	500K
CrossModel`x-ai/grok-4.7`	$2.00	$6.00	500K
DevPass (LLM Gateway)`grok-4-7`	$2.00	$6.00	524K
Eden AI`xai/grok-4.7`	$2.00	$6.00	500K
GitHub Copilot`grok-4.7`	$2.00	$6.00	500K
Kilo Gateway`x-ai/grok-4.7`	$2.00	$6.00	500K

Show 17 more providers

Provider	Input	Output	Context
LLM Gateway`xai/grok-4-7`	$2.00	$6.00	500K
Merge Gateway`xai/grok-4.7`	$2.00	$6.00	500K
NanoGPT`x-ai/grok-4.7`	$2.00	$6.00	500K
NEAR AI Cloud`x-ai/grok-4.7`	$2.00	$6.00	500K
Ofox`x-ai/grok-4.7`	$2.00	$6.00	500K
OpenCode`grok-4.7`	$2.00	$6.00	500K
OpenCode Go`grok-4.7`	$2.00	$6.00	500K
OpenRouter`x-ai/grok-4.7`	$2.00	$6.00	500K
Requesty`grok-4.7`	$2.00	$6.00	500K
Tempr Gateway`xai/grok-4.7`	$2.00	$6.00	500K
Vercel AI Gateway`spacexai/grok-4.7`	$2.00	$6.00	500K
Vertex`xai/grok-4.7`	$2.00	$6.00	524K
xAIOfficial`grok-4.7`	$2.00	$6.00	500K
AIHubMix`grok-4.7`	$2.20	$6.60	500K
Venice AI`grok-4-7`	$2.27	$6.80	500K
Neon`grok-4-7`	$2.50	$7.50	500K
Azure`grok-4.7`	—	—	500K

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

Face off

Current text models from other labs at a similar output price.

Grok 4.7

Grok 4.7

How good is it?

Leaderboards

Benchmarks Epoch AI runs

Where to run it

API providers

Face off

More from xAI

Grok Imagine Video 1.5 Lite

Grok 4.6

Grok 4.5

Grok Imagine Video 1.5

Grok 4.3

Grok Build 0.1

Grok Imagine Image Quality

Grok 4.20 Multi-Agent