xAI: Grok 3 Mini

Text input Text output
Author's Description

A lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible.

Key Specifications
Cost
$$$$$
Context
131K
Parameters
2.7T (Rumoured)
Released
Jun 10, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Stop Temperature Seed Structured Outputs Response Format Max Tokens Include Reasoning Tool Choice Top P Tools Reasoning Logprobs Top Logprobs
Features

This model supports the following features:

Tools Reasoning Structured Outputs Response Format
Performance Summary

xAI: Grok 3 Mini, created on June 10, 2025, is a lightweight model designed for logic-based tasks. It exhibits moderate speed performance, ranking in the 36th percentile across benchmarks, and offers moderate pricing, placing it in the 34th percentile. A standout feature is its exceptional reliability, achieving a perfect 100th percentile, indicating consistent and stable operation with minimal technical failures. The model demonstrates remarkable accuracy in several key areas. It achieved perfect scores in Ethics, Reasoning, and General Knowledge, often being the most accurate model at its price point and speed. Its "thinks before responding" mechanism appears to contribute significantly to its strong performance in these logic and knowledge-intensive domains. In Coding, Grok 3 Mini scored an impressive 95.0% accuracy, again standing out as highly accurate for its cost and speed. While its Instruction Following accuracy of 76.8% is strong (92nd percentile), it is not perfect. Email Classification showed solid performance at 98.0% accuracy. Overall, Grok 3 Mini's key strengths lie in its high accuracy across critical reasoning, ethical, and knowledge-based tasks, coupled with its outstanding reliability. Its primary area for potential improvement, while still performing moderately, is its speed.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.3
Completion $0.5
Input Cache Read $0.075

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
xAI
xAI | x-ai/grok-3-mini 131K $0.3 / 1M tokens $0.5 / 1M tokens
xAI
xAI | x-ai/grok-3-mini 131K $0.6 / 1M tokens $4 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Free Executions Accuracy Cost Duration
Other Models by x-ai