ZMIME
OpenAI · Released Apr 14, 2025

GPT-4.1 nano

Tiny GPT-4.1 option for classification, routing, and very high-volume tasks.

  • Proprietary
  • Tool calling
  • Vision
  • Deprecated
Capability
129.6ECI · #127 of 148
Input
$0.10per 1M tokens
Output
$0.40per 1M tokens
Context
1.05M33K max output
Pricing

What it costs

Input
$0.10per million tokens
Output
$0.40per million tokens
Cached input
$0.025per million tokens
Blended (3:1)
$0.175cheaper than 79% of priced models

Typical monthly bills

Monthly usageEstimated cost
Side project2M input + 0.5M output tokens$0.40
Team assistant25M input + 5M output tokens$4.50
Production app250M input + 50M output tokens$45.00

Official OpenAI API price, as listed on models.dev.

Capability

Independent benchmarks

129.6Epoch Capabilities Index
#127 of 148 scored models
88Median 146167

The shaded band is Epoch AI’s confidence range (123.2–132.0); the tick marks the median scored model.

  • GPQA DiamondGraduate-level science questions48.9%
  • OTIS Mock AIME 2024–2025Competition mathematics28.9%
  • SimpleQA VerifiedShort factual questions6.0%

Scores from Epoch AI, run independently of OpenAI.

Specifications

The details

Lab
OpenAI
Released
Apr 14, 2025
Knowledge cutoff
Apr 2024
Context window
1,047,576 tokens
Max output
32,768 tokens
Inputs
Text, Images
Output
Text
Reasoning
No
Tool calling
Yes
Structured output
Yes
Weights
Proprietary
API model ID
gpt-4.1-nanoon OpenAI
Availability
20 API providerslisted on models.dev
Status
Deprecated by the provider

OpenAI model documentation

Lab-reported

What OpenAI claims

Published by the lab at launch. Settings vary, so compare these only with care.

BenchmarkScoreSettingSource
Aider Polyglot8.9 percent correct—Source
Same lab

More from OpenAI

Questions

About GPT-4.1 nano

How much does GPT-4.1 nano cost?

GPT-4.1 nano costs $0.10 input / $0.40 output per million tokens (official OpenAI API price). Cached input is $0.025 per million tokens. At a 3:1 input-to-output mix that is $0.175 per million tokens, cheaper than 79% of the 360 priced models we track.

What is the context window of GPT-4.1 nano?

GPT-4.1 nano accepts up to 1,047,576 tokens per request and can write up to 32,768 tokens in one response.

How good is GPT-4.1 nano?

Epoch AI gives GPT-4.1 nano a Capabilities Index score of 129.6 (likely range 123.2–132.0), ranking it #127 of 148 models Epoch has scored. Epoch AI benchmark results: GPQA Diamond 48.9%, OTIS Mock AIME 2024–2025 28.9%, SimpleQA Verified 6.0%.

Is GPT-4.1 nano open source?

No. GPT-4.1 nano is proprietary; you use it through OpenAI’s API or partner platforms.

What inputs does GPT-4.1 nano support?

GPT-4.1 nano accepts text and images and replies in text. It is not a dedicated reasoning model, supports tool calling and can return structured JSON output.

When was GPT-4.1 nano released?

OpenAI released GPT-4.1 nano on Apr 14, 2025. Its training data runs to Apr 2024.

What are the best alternatives to GPT-4.1 nano?

The closest current models from other labs on capability, price and release date are Gemma 3 27B IT (Google, ECI 130.0, $0.08 / $0.20), Llama 4 Scout 17B Instruct (Meta, ECI 129.7, $0.225 / $0.69), Mistral Small 3.2 (Mistral AI, ECI 131.7, $0.10 / $0.30) and Qwen3 30B A3B (Alibaba (Qwen), ECI 136.2, $0.114 / $0.50).