What is the context window size for Grok 4.6?

Grok 4.6 offers a 500k context window.

How much does Grok 4.6 cost on Vertex AI?

Input costs $2 per 1 million tokens; cached input costs $0.30 per 1 million tokens; output costs $6 per 1 million tokens.

How do I start using Grok 4.6?

Developers can access it through Vertex Model Garden by visiting the Grok 4.6 model card.

Large Language ModelsTop Companies' AI MovesAI Business & IndustryTop Companies AIAug 21, 2026Aug 22, 2026, 06:30 JST

Grok 4.6 launches on Google Cloud Vertex AI

Send on LINE

3 Key Points

What happened
Google Cloud announced Grok 4.6, its latest flagship model, is now available on Vertex AI through Model Garden. The model supports a 500k context window and adjustable reasoning effort levels (low, medium, high, xhigh).
Why it matters
Grok 4.6 is built for long-running agents and complex interactive and visual work, giving Vertex AI users access to a high-capacity reasoning model. Pricing is $2 per 1 million input tokens, $0.30 per 1 million cached input tokens, and $6 per 1 million output tokens.
What to watch
Developers can access Grok 4.6 immediately through Vertex Model Garden by visiting the model card; no rollout timeline or regional restrictions are mentioned.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, in your inbox every morning.

Get news like this every morning, free

Context & Analysis

Google Cloud's announcement positions Grok 4.6 as a purpose-built model for demanding workloads — agents that run over extended periods and applications requiring both visual and interactive capabilities. The 500k context window is a substantial capacity, allowing the model to maintain awareness of long conversations or large documents in a single request. The tiered pricing structure reflects typical LLM (AI that understands and generates text) costs, with cached input tokens at a significant discount, incentivizing developers to reuse input data across multiple requests and reducing repetitive processing costs.

FAQ

What is the context window size for Grok 4.6?: Grok 4.6 offers a 500k context window.
How much does Grok 4.6 cost on Vertex AI?: Input costs $2 per 1 million tokens; cached input costs $0.30 per 1 million tokens; output costs $6 per 1 million tokens.
How do I start using Grok 4.6?: Developers can access it through Vertex Model Garden by visiting the Grok 4.6 model card.

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Get it free

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.