Grok 4.7
xAI's flagship reasoning model with native real-time web and X search.
Grok 4.7 specifications
| Provider | xAI |
|---|---|
| Context window | 500,000 tokens (500K) |
| Input price | $2.00 / 1M tokens |
| Output price | $6.00 / 1M tokens |
| Inputs | Text, Images |
| Reasoning mode | Yes |
| Vision (image input) | Yes |
| Tool / function calling | Yes |
| Native real-time web | Yes |
| Open-weight | No |
| Released | September 2026 |
| Knowledge cutoff | May 2026 |
Pricing & context web-verified November 2026 — confirm on xAI's pricing page. xAI's current flagship. Prompts of 200K+ tokens bill the whole request at a higher tier ($4 / $12 per 1M).
What Grok 4.7 is best for
- Real-time research and current events
- Reasoning-heavy analysis
- Agentic tool use across web, code, and X search
How to prompt Grok 4.7
- Lean on its live web and X search for anything time-sensitive. It pulls current data.
- Reasoning effort runs from low to xhigh and defaults to high. Drop it for quick, simple asks.
- Its window is 500K tokens, half of Grok 4.3's, so trim or summarize very long inputs first.
Work with Grok 4.7
- Build an optimized prompt with the xAI prompt generator.
- Estimate cost with the token counter & cost calculator, or compare every model on the AI model comparison page.
- Related reading: Best Grok Prompts 2026 · How To Use Grok.
- Official: grok.com
- Other xAI models: Grok 4.3.
Frequently asked questions
What is Grok 4.7's context window?
Grok 4.7 has a 500,000-token context window (about 500K tokens) — the maximum amount of text it can consider at once.
How much does Grok 4.7 cost?
Via the xAI API, Grok 4.7 costs $2.00 per 1M input tokens and $6.00 per 1M output tokens (web-verified November 2026). Output tokens cost more, so the length of the model's reply usually drives the bill.
Is Grok 4.7 multimodal?
Yes — Grok 4.7 accepts Text, Images as input, not just text.
Is Grok 4.7 open-weight?
No — Grok 4.7 is available only through the xAI API, not as downloadable weights.