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
Supported Parameters
This model supports the following parameters:
Features
This model supports the following features:
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
|
Released | Params | Context |
|
Speed | Ability | Cost |
---|---|---|---|---|---|---|---|
xAI: Grok 4 | Jul 09, 2025 | — | 256K |
Text input
Image input
Text output
|
★ | ★★★★★ | $$$$$ |
xAI: Grok 3 | Jun 10, 2025 | ~2.7T | 131K |
Text input
Text output
|
★★★ | ★★★★★ | $$$$$ |
xAI: Grok 3 Mini Beta | Apr 09, 2025 | ~2.7T | 131K |
Text input
Text output
|
★★ | ★★★★★ | $$$$$ |
xAI: Grok 3 Beta | Apr 09, 2025 | ~2.7T | 131K |
Text input
Text output
|
★★★★ | ★★★★ | $$$$$ |
xAI: Grok 2 Vision 1212 | Dec 14, 2024 | — | 32K |
Text input
Image input
Text output
|
★★★★ | ★★★★ | $$$$$ |
xAI: Grok 2 1212 | Dec 14, 2024 | — | 131K |
Text input
Text output
|
★★★★ | ★★★★ | $$$$$ |
xAI: Grok Vision Beta | Nov 18, 2024 | — | 8K |
Text input
Image input
Text output
|
★★★★ | ★★★ | $$$$$ |
xAI: Grok Beta Unavailable | Oct 19, 2024 | — | 131K |
Text input
Text output
|
★★★★ | ★★★★★ | $$$$$ |