xAI: Grok 3 Mini Beta

x-ai/grok-3-mini-beta

131KContext Window

Supported Protocols:reasoninginclude_reasoningmax_tokenstemperaturetop_pseedlogprobstop_logprobsresponse_formatstoptoolstool_choice

Normal

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.

Capabilities

🧠 Reasoning🔧 Function CallingText GenerationCode GenerationAnalysis & ReasoningReasoning

Technical Specs

Input Modality

Text

Output Modality

Text

Arch

—

Default Temperature

0.7

Default Top_P

Pricing

Pay per use, no monthly fees

Billing Type	Unit	Price
Text Input	—	$0.3000/M tokens
Text Output	—	$0.5000/M tokens
Cache Read	—	$0.0750/M tokens
Web Search	—	$0.0050/次

Quick Start

from openai import OpenAI

client = OpenAI(
    base_url="https://api.uniontoken.ai/v1",
    api_key="YOUR_UNIONTOKEN_API_KEY",
)

response = client.chat.completions.create(
    model="x-ai/grok-3-mini-beta",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

print(response.choices[0].message.content)