Back to Models
x-ai logo
x-ai/grok-4-fast
Not Available

Grok 4 Fast

Grok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. It comes in two flavors: non-reasoning and reasoning. Read more about the model on xAI's [news post](http://x.ai/news/grok-4-fast). Reasoning can be enabled/disabled using the `reasoning` `enabled` parameter in the API. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#controlling-reasoning-tokens)

9/19/2025
2,000,000 tokens
#101 Text (Japanese)

Specifications

Modalities

Input
text
image
Output
text

Supported Parameters

include_reasoning
logprobs
max_tokens
reasoning
response_format
seed
structured_outputs
temperature
tool_choice
tools
top_logprobs
top_p

Max Output Tokens

30,000

Frequently asked questions

Is Grok 4 Fast available on FastMetal?
Not at the moment. Grok 4.5, from the same lab, is available on the FastMetal API today.
What is the context window of Grok 4 Fast?
2,000,000 tokens, shared between the prompt and the response.
How does Grok 4 Fast rank?
#101 on the public arena's Japanese board (ELO 1,370). Ranks move as the leaderboard is updated.

Leaderboard

Text
OverallELO: 1,404
#140
JapaneseELO: 1,370
#101
ChineseELO: 1,445
#125
KoreanELO: 1,336
#136
EnglishELO: 1,414
#145
frenchELO: 1,440
#105
germanELO: 1,384
#130
spanishELO: 1,405
#120
russianELO: 1,395
#142
CodingELO: 1,438
#156
MathELO: 1,411
#126
Creative WritingELO: 1,381
#126
Instruction FollowingELO: 1,389
#145
Hard PromptsELO: 1,414
#159
Multi-TurnELO: 1,403
#145
Code
OverallELO: 1,162
#126