models/openai/gpt-4-1-nano
O
OpenAI·deprecated 2026-10-23

GPT-4.1 Nano

OpenAI's efficiency model. Long-context specialist with 1.0M window.

Overall score
3.62
/5.00 · ranked #119
Input
$0.100
per 1M tokens
Output
$0.400
per 1M tokens
Context
1.0M
tokens
Blended
$0.325
3:1 out:in ratio

Price drops, new benchmarks, model updates. Stay current on GPT-4.1 Nano.

One email per change. Unsubscribe anytime.

modelpicker.aipowered by live benchmark data

Scores by test

Methodology →
Structured Output
5.0
Strategic Analysis
2.0
Constrained Rewriting
4.0
Creative Problem Solving
2.0
Tool Calling
4.0
Faithfulness
5.0
Classification
3.0
Long Context
4.0
Safety Calibration
3.0
Persona Consistency
4.0
Agentic Planning
4.0
Multilingual
4.0
Tabular Data
3.0
MATH Level 5
70.0
AIME 2025
28.9
GPQA Diamond
48.9
SciCode
25.9
Epoch Capabilities Index (ECI)
130.7

What you need to know

GPT-4.1 Nano is built for high-reliability data extraction and formatting rather than cognitive reasoning. Its primary technical advantage is a perfect score in structured output and faithfulness, meaning it adheres strictly to schemas and avoids hallucinations. This reliability extends to tool calling and agentic planning, making it a stable engine for automated workflows.

The model's reasoning capabilities are limited. It scores poorly in strategic analysis and creative problem solving, and its performance on complex logic benchmarks is low, specifically scoring 28.9% on AIME 2025 and 25.9% on SciCode. It is not designed for deep analytical tasks or complex mathematical derivation.

At a blended cost of $0.325 per million tokens, this is a low-cost utility model. It provides a massive 1.0M token context window, which, combined with its high faithfulness score, makes it an efficient tool for processing large volumes of text without losing detail.

Use this model if you need a cheap, reliable worker for structured data extraction, API orchestration, or long-context document processing. Skip this model if your use case requires complex reasoning, strategic planning, or high-level mathematical problem solving.

Strengths — Top 3

Structured Output5.0/5.0
Faithfulness5.0/5.0
Constrained Rewriting4.0/5.0

Relative weaknesses — Bottom 3

Strategic Analysis2.0/5.0
Creative Problem Solving2.0/5.0
Classification3.0/5.0

Similar models

MCodestral 2508$0.7503.46MMistral Small 3.2 24B$0.1693.23QQwen: Qwen3 Coder 30B A3B Instruct$0.2283.23MMinistral 3 3B 2512$0.1003.46