xAI
xAI
Multimodal

Grok 3 Fast

Balanced

Speed-tuned Grok 3 with vision. Trades a few quality points for faster response, useful for chat UIs that need streaming feel.

Grok 3 Fast is a multimodal AI model from xAI. It costs $5.000 per million input tokens and $25.000 per million output tokens (blended $11.000/M), with a 131,000-token context window.

INPUT
$5.000/M
per million input tokens
OUTPUT
$25.000/M
per million output tokens
BLENDED 70/30
$11.000/M
unchanged since 3 May
CONTEXT
131,000
tokens
What it is good at
  • Fast Grok 3
  • Vision-capable
  • Real-time X data
Typical use cases
  • Realtime chat UI
  • Vision QA grounded in social media

Benchmarks

vs. best public score
MMLU86%
Multitask academic knowledge across 57 subjects.
Graduate-level science questions, "Google-proof".
MATH89%
High-school competition math problems.
Python function synthesis from docstrings.
LMArena Elo1332 Elo
Crowd-sourced head-to-head preference Elo rating.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

More from xAI

See all 8 →

Frequently asked questions

How much does Grok 3 Fast cost?

Grok 3 Fast costs $5.000 per million input tokens and $25.000 per million output tokens, for a blended reference rate of $11.000 per million tokens.

What is Grok 3 Fast's context window?

Grok 3 Fast supports up to 131,000 tokens of context in a single request.

What is Grok 3 Fast best for?

Grok 3 Fast is well suited to Fast Grok 3, Vision-capable and Real-time X data.

Who makes Grok 3 Fast?

Grok 3 Fast is developed and served by xAI.

Terms used on this page