Back to Models
x-ai logo
x-ai/grok-3-mini-beta
Not Available

Grok 3 Mini Beta

Grok 3 Mini is a lightweight, smaller thinking model. Unlike traditional models that generate answers immediately, Grok 3 Mini thinks before responding. It’s ideal for reasoning-heavy tasks that don’t demand extensive domain knowledge, and shines in math-specific and quantitative use cases, such as solving challenging puzzles or math problems. Transparent "thinking" traces accessible. Defaults to low reasoning, can boost with setting `reasoning: { effort: "high" }` Note: That there are two xAI endpoints for this model. By default when using this model we will always route you to the base endpoint. If you want the fast endpoint you can add `provider: { sort: throughput}`, to sort by throughput instead.

4/9/2025
131,072 tokens
#127 Text (Japanese)

Specifications

Modalities

Input
text
Output
text

Supported Parameters

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

Frequently asked questions

Is Grok 3 Mini Beta 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 3 Mini Beta?
131,072 tokens, shared between the prompt and the response.
How does Grok 3 Mini Beta rank?
#127 on the public arena's Japanese board (ELO 1,336). Ranks move as the leaderboard is updated.

Leaderboard

Text
OverallELO: 1,358
#193
JapaneseELO: 1,336
#127
ChineseELO: 1,375
#194
KoreanELO: 1,287
#170
EnglishELO: 1,372
#202
frenchELO: 1,358
#183
germanELO: 1,334
#171
spanishELO: 1,368
#169
russianELO: 1,349
#192
CodingELO: 1,386
#212
MathELO: 1,371
#179
Creative WritingELO: 1,337
#180
Instruction FollowingELO: 1,353
#187
Hard PromptsELO: 1,370
#198
Multi-TurnELO: 1,345
#200