The AI arena is free today

Open Superagent
xAIReleased on Aug 12, 2026

Grok 4.6: Benchmarks, Pricing & Context Window

Grok 4.6 is a language model from xAI, released in August 2026, with multimodal input, a 500K-token context window, and pricing from $2.00/M input, $0.500/M cached input, $6.00/M output.

Grok 4.6 is SpaceXAI's frontier model built for coding, agentic tasks, and knowledge work. It builds on Grok 4.5 with a particular focus on long-running agents and more ambitious interactive and visual work. The model supports text and

Input
TextImage
Output
Text

Grok 4.6 benchmarks

Capability tiers

Standing within each category, adjusted for leaderboard depth.

Real tasks performance

High-confidence performance for Grok 4.6 across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.

Performance by conversation depth

How Grok 4.6 holds up as conversations get longer.

Quality Tracker

Grok 4.6 Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

LLM Stats Logollm-stats.com - Wed Sep 09 2026
Notice missing or incorrect data?

Grok 4.6 pricing

Providers

Grok 4.6 starts at $2.00 per million input tokens and $6.00 per million output tokens via xAI. Reused prompt prefixes cost $0.500 per million cached input tokens.

ProviderInput $/MCached input $/MOutput $/MContext in / outTTFT p95 sOutput p5 c/sModalities in / out
xAI logoxAI
$2.00$0.500$6.00500.0K/
3.38
13
/

Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.

Grok 4.6 context window

Input and output token limits for Grok 4.6, plus how it ranks on long-context understanding.

Input
500Ktokens
752 pages of text
500K
8K128K1M

Try now

huggle
Grok 4.6in Huggle

Make it with
Grok 4.6.

Grok 4.6

Grok 4.6 latency

Grok 4.6 time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.

Provider operational metrics

Time to first token, output throughput, and failed-request rate from live model usage

Loading chart...
Loading chart...
Loading chart...

Grok 4.6 examples

Recent arena outputs from Grok 4.6, picked from the highest-ranked matchups.

Grok 4.6 license

Grok 4.6 is a proprietary model available under its provider's product and API terms, has a knowledge cutoff of February 2026.

License
Proprietary
Hosted access
Knowledge cutoff
February 2026

Proprietary license - usage restrictions apply

Grok 4.6 resources

Official sources for Grok 4.6: provider documentation, official playground, official launch post.

Grok 4.6 vs other models

The most-compared alternatives to Grok 4.6 are Muse Spark 1.3, Claude Opus 4.8, Kimi K3. Open any pair side-by-side for benchmarks, pricing, context, and latency.

Models like Grok 4.6

Models ranked just above and below Grok 4.6 by LLM Stats score.

 

Muse Spark 1.3

Score pending
 

Claude Opus 4.8

Score pending
 

Kimi K3

Score pending
 

GPT-5.5

Score pending
 

GLM-5.3-Flash

Score pending
 

Gemini 3.7 Flash

Score pending

FAQ

Common questions about Grok 4.6.

When was Grok 4.6 released?

Grok 4.6 was released on August 12, 2026 by xAI. This is the official Grok 4.6 release date tracked on LLM Stats.

How much does Grok 4.6 cost?

Grok 4.6 pricing starts at $2.00 per million input tokens, $0.50 per million cached input tokens, $6.00 per million output tokens via xAI, the lowest price among tracked providers.

Who created Grok 4.6?

Grok 4.6 was created by xAI.

What is the license for Grok 4.6?

Grok 4.6 is released under the Proprietary license.

What is the knowledge cutoff date for Grok 4.6?

Grok 4.6 has a knowledge cutoff of February 2026, meaning it was trained on data up to that point and may not know about events after it.

Is Grok 4.6 multimodal?

Yes, Grok 4.6 is multimodal and can accept both text and images as input.

What is Grok 4.6 latency?

Grok 4.6 p95 time to first token is 3.38 seconds via xAI over the trailing 7 days. Lower time to first token means the model begins responding sooner for chat, agents and model workloads.

Where can I use Grok 4.6?

Grok 4.6 is available through 1 provider including xAI.

Where is the Grok 4.6 paper or technical report?

Grok 4.6 has a paper or technical report available at https://x.ai/news/grok-4-6. Use that source for architecture, training, release and evaluation details.

What models should I compare Grok 4.6 against?

Common Grok 4.6 comparisons include Grok 4.6 vs Muse Spark 1.3, Grok 4.6 vs Claude Opus 4.8, Grok 4.6 vs Kimi K3. Compare them side by side for benchmark scores, pricing, context window, latency and provider availability.