OpenAI logo

GPT-4.1 mini

OpenAI GPT-4.1 mini April 14, 2025
Featured

Cost-efficient sibling of GPT-4.1 with the full 1 M-token context window, image inputs, and lower latency/pricing.

Model Capabilities

Input

Accepted Formats

Text
Vision (General)

Input Length

Context Window: 1M Tokens

Output

Generated Formats

Text

Output Length

Max Output: 16,384 Tokens

Core Features & Strengths

Function Calling / Tools
Prompt Caching

Specifications & Pricing

Specifications

Model Size: Unknown params
Architecture: N/A

Pricing

Input / 1M tk

$0.4000

Output / 1M tk

$1.6000

Cached Input

$0.1000

Cached Output

$0.4000

Est. cost in USD

Usage Guidance

Prompting Guide

General Tips

  • **Be Specific & Clear:** Detail the desired outcome, format, tone, and constraints.
  • **Provide Context:** Explain the background, your role, or the purpose (e.g., "Act as a helpful architect...").
  • **Specify Format:** Request bullet points, JSON, markdown, code blocks, etc.
  • **Use Examples (Few-Shot):** Provide 1-3 examples of input/output for complex tasks.
  • **Iterate:** Refine prompts based on the model's responses. Don't expect perfection first try.

Vision Prompt Example

Analyze the attached site plan. List potential challenges for drainage and suggest mitigation strategies.

Function Calling Example

"Book a meeting room for 3 people tomorrow at 2 PM for 1 hour. Find available rooms first."

// Model should trigger 'find_rooms' then 'book_room'