Official

openai / gpt-4.1-mini

Fast, affordable version of GPT-4.1 (Updated 4 days ago)

  • Public
  • 766.7K runs
  • License
Iterate in playground
Run with an API
Playground API Examples README

Readme

GPT‑4.1 mini is a compact, high-performance model designed for real-world applications that require fast response times and low cost—without sacrificing intelligence. It delivers performance competitive with GPT‑4o while cutting latency nearly in half and reducing cost by 83%.

Key Features

  • Fast and lightweight, ideal for latency-sensitive use cases
  • High accuracy across coding, reasoning, and instruction following
  • Supports 1 million token context windows
  • Cost-effective for large-scale deployments
  • Reliable for long-context and format-specific tasks

Benchmark Highlights

  • SWE-bench Verified (coding): 24%
  • MultiChallenge (instruction following): 36%
  • IFEval (format compliance): 84%
  • Aider Diff Format Accuracy (diff): 45%
  • MMMU (vision QA): 73%

Use Cases

  • Chatbots and assistants
  • Lightweight code generation and review
  • Document Q&A and summarization
  • Image reasoning
  • High-volume, cost-sensitive tasks

Notes

  • Available via the OpenAI API
  • Not currently available in ChatGPT
  • Supports up to 1 million tokens of context