Official

openai / gpt-4.1-nano

Fastest, most cost-effective GPT-4.1 model from OpenAI

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

GPT‑4.1 nano is the fastest and most cost-efficient model in the GPT‑4.1 family. It delivers strong performance for lightweight tasks while supporting up to 1 million tokens of context. Designed for speed-critical and high-scale applications, nano is ideal for tasks like classification, autocomplete, and simple reasoning.

Key Features

  • Ultra-low latency and fast response times
  • Lowest cost in the GPT-4.1 lineup
  • Supports 1 million token context windows
  • Optimized for short prompts and high-volume usage
  • Competitive accuracy on key benchmarks

Benchmark Highlights

  • MMLU: 80.1%
  • GPQA: 50.3%
  • Aider Polyglot Diff (diff format): 45%
  • MultiChallenge: 15%
  • IFEval: 75%

Use Cases

  • Text classification
  • Autocomplete and structured text generation
  • Fast Q&A over small or medium context
  • Low-latency applications at scale
  • Budget-sensitive or high-throughput tasks

Notes

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

GPT‑4.1 nano is built for developers who need speed, scale, and affordability.