WordGPT

xAI logo

SpaceXAI: Grok 4.7

x-ai/grok-4.7

Try in WordGPT

Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...

Modalities

TextImageFiles / PDFText

In / out price

$2 / $6 per 1M

Context

500K

Released

Sep 21, 2026

Why use Grok 4.7

  • Understands images
  • Reads PDFs and other files
  • Step-by-step reasoning mode
  • Tool and function calling (agent-ready)
  • Structured (JSON) outputs
  • Very long context: whole books or codebases in one prompt

Pricing

Input$2 / 1M tokens
Output$6 / 1M tokens
Cached input (read)$0.5 / 1M tokens

List prices via OpenRouter, checked daily. Real cost depends on the provider and on reasoning tokens.

How it ranks

Intelligence index46.4

Source: Artificial Analysis (artificialanalysis.ai) via OpenRouter (openrouter.ai/rankings).

Cost calculator

Pick a task, set how often you run it, and compare what it costs on each model.

ModelPer runPer monthPer 1,000 runs
SpaceXAI: Grok 4.7$0.014$13.60$13.60

Estimates from list prices via OpenRouter; real bills vary by provider and reasoning tokens.

Will it fit? Context window simulator

Each square is about one page (500 words). Colored squares are your content; grey squares are free space in the model's context window.

Your content

  • Novel (90,000 words)

Total: about 120,000 tokens (≈ 90,226 words). Token counts are estimates.

Models

SpaceXAI: Grok 4.7

500,000 tokens ≈ 752 pages

Fits: uses 24% of the window (room for 4× this much).

Write with the best model for the job

WordGPT picks and switches models for you: drafting, editing and files in one place. Free plan, no credit card.

Try it free

More from xAI