GPT-4.1 Nano

Provider: OpenAI US

Input price
$0.10
/ 1M tokens
Output price
$0.40
/ 1M tokens
Cache price
$0.03
/ 1M tokens (read)
Batch API
$0.05 / $0.20
input / output per 1M tokens
Context
1.05M tokens
Max output 943K tokens

Overview

OpenAI's GPT-4.1 Nano is a cost-optimized model designed for workloads requiring extensive context processing and advanced multimodal capabilities. It offers a massive context window paired with vision and structured output features, positioning it as a mid-tier offering.

Strengths

  • Processes extremely long inputs with its 1,047,576 token context window.
  • Supports multimodal inputs including vision capabilities for image understanding.
  • Enables reliable structured data generation through JSON mode.
  • Facilitates seamless integration with external tools via function-calling.
  • Offers a competitive input price for handling large volumes of text.

Best use cases

  • Analyzing and summarizing very lengthy documents or codebases.
  • Developing AI agents that can process and respond to visual information.
  • Automating data extraction from complex documents with structured output.
  • Building advanced chatbots that retain extensive conversation history.
  • Integrating with external APIs and tools for complex workflows.

Pricing position

GPT-4.1 Nano is positioned as a cost-effective option within OpenAI's lineup, with an input price of $0.10/1M tokens and an output price of $0.40/1M tokens. While its input price is slightly higher than GPT-5 Nano ($0.05/1M tokens), it offers a much larger context window. Its pricing is directly comparable to Google's Gemini 2.5 Flash Lite peers but has higher output costs than Llama 3.3 70B Instruct ($0.32/1M tokens) and Ministral 3 3B 2512 ($0.10/1M tokens).

Caveats

While offering a large context and vision, GPT-4.1 Nano lacks a free tier, which might deter initial experimentation. For tasks not requiring its expansive context or multimodal features, models like Ministral 3 3B 2512 offer significantly lower output costs at $0.10/1M tokens. Its input cost is also not the absolute lowest within OpenAI's own offerings.

Notes drafted by an LLM from the figures on this page (2026-05-21) and rewritten when the price changes.

Key facts

Price basis
Median third-party host price (no first-party API)
Max output
943K tokens
Knowledge cutoff
2024-06-30
Listed on OpenRouter
2025-04-14
Tracked since
2026-05-08
Last updated
2026-11-10

Features

Image inputFunction callingJSON output

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.03
1M (small app) 1 0.5 $0.30
10M (mid scale) 10 5 $3.00
100M (large) 100 50 $30.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from OpenAI

Similar-priced models

Source: OpenRouter API (openai/gpt-4.1-nano)