The AI arena is free today

Open Superagent
xAIReleased on Feb 17, 2025

Grok-3: Benchmarks, Pricing & Context Window

Grok-3 is a language model from xAI, released in February 2025, with multimodal input, a 128K-token context window, and pricing from $3.00/M input and $15.00/M output.

Grok 3, launched by xAI on February 17, 2025, is an advanced AI model with significantly enhanced capabilities compared to Grok 2, boasting an order of magnitude increase in performance. Trained on a vast dataset that includes legal

Input
TextImage
Output
Text

Grok-3 benchmarks

Capability tiers

Standing within each category, adjusted for leaderboard depth.

Real tasks performance

High-confidence performance for Grok-3 across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.

Performance by conversation depth

How Grok-3 holds up as conversations get longer.

Quality Tracker

Grok-3 Performance Across Datasets

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

LLM Stats Logollm-stats.com - Fri Oct 09 2026
Notice missing or incorrect data?

Grok-3 pricing

Providers

Grok-3 starts at $3.00 per million input tokens and $15.00 per million output tokens via xAI.

ProviderInput $/MCached input $/MOutput $/MContext in / outTTFT p95 sOutput p5 c/sModalities in / out
xAI logoxAI
$3.00—$15.00128.0K/8.0K
0.70
—
/

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-3 context window

Input and output token limits for Grok-3, plus how it ranks on long-context understanding.

InputOutput
128Ktokens
8Ktokens
≈ 192 pages of text
128K
8K128K1M

Try now

huggle
Grok-3in Huggle

Make it with
Grok-3.

Grok-3

Grok-3 latency

Grok-3 time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.

Grok-3 examples

Recent arena outputs from Grok-3, picked from the highest-ranked matchups.

Grok-3 license

Grok-3 is a proprietary model available under its provider's product and API terms, has a knowledge cutoff of November 2024.

License
Proprietary
Hosted access
Knowledge cutoff
November 2024

Proprietary license - usage restrictions apply

Grok-3 resources

Official sources for Grok-3: provider documentation.

Grok-3 vs other models

The most-compared alternatives to Grok-3 are LongCat-Flash-Thinking, Grok-4 Heavy, Step3-VL-10B. Open any pair side-by-side for benchmarks, pricing, context, and latency.

Models like Grok-3

Models ranked just above and below Grok-3 by LLM Stats score.

 

LongCat-Flash-Thinking

Score pending
 

Grok-4 Heavy

Score pending
 

Step3-VL-10B

Score pending
 

EXAONE 4.5 33B

Score pending
 

GPT-5.1 Instant

Score pending
 

Gemma 4 31B

Score pending

FAQ

Common questions about Grok-3.

When was Grok-3 released?

Grok-3 was released on February 17, 2025 by xAI. This is the official Grok-3 release date tracked on LLM Stats.

How much does Grok-3 cost?

Grok-3 pricing starts at $3.00 per million input tokens and $15.00 per million output tokens via xAI, the lowest price among tracked providers.

Who created Grok-3?

Grok-3 was created by xAI.

What is the license for Grok-3?

Grok-3 is released under the Proprietary license.

What is the knowledge cutoff date for Grok-3?

Grok-3 has a knowledge cutoff of November 2024, meaning it was trained on data up to that point and may not know about events after it.

Is Grok-3 multimodal?

Yes, Grok-3 is multimodal and can accept both text and images as input.

What is Grok-3 latency?

Grok-3 p95 time to first token is 0.70 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-3?

Grok-3 is available through 1 provider including xAI.

What models should I compare Grok-3 against?

Common Grok-3 comparisons include Grok-3 vs LongCat-Flash-Thinking, Grok-3 vs Grok-4 Heavy, Grok-3 vs Step3-VL-10B. Compare them side by side for benchmark scores, pricing, context window, latency and provider availability.