GPT-4.1

Provider: OpenAI US Official API price

Input price
$2.00
/ 1M tokens
Output price
$8.00
/ 1M tokens
Cache price
$0.50
/ 1M tokens (read)
Batch API
$1.00 / $4.00
input / output per 1M tokens
Context
1.05M tokens
Max output 33K tokens

Overview

OpenAI's GPT-4.1 is positioned as a flagship model, designed for complex, high-context workloads. It combines advanced reasoning with multimodal input and robust tool integration capabilities. This model targets applications requiring extensive understanding and sophisticated interaction.

Strengths

  • Processes extremely large context windows, up to 1,047,576 tokens, for deep analysis.
  • Supports multimodal inputs with integrated vision capabilities for diverse data processing.
  • Enables complex agentic workflows through robust function-calling functionality.
  • Guarantees structured responses with a dedicated JSON mode for reliable parsing.
  • Offers a cost-efficient cache read price of $0.5/1M tokens for repeated inputs.

Best use cases

  • Performing deep analysis of extensive documents, reports, or large codebases.
  • Automated generation of detailed image descriptions and multimodal content.
  • Building sophisticated AI agents that interact seamlessly with external tools.
  • Extracting structured data from diverse inputs with high precision and reliability.
  • Powering advanced reasoning applications requiring massive context and capabilities.

Pricing position

GPT-4.1 is a premium-priced model, with input tokens at $2/1M and output tokens at $8/1M. This positions it significantly above OpenAI's cost-optimized Nano and Mini series models, such as the GPT-4.1 Nano at $0.1/M input and $0.4/M output. Its pricing is directly comparable to Sonar Reasoning Pro ($2/M in, $8/M out) and Gemini 3.1 Pro Preview ($2/M in, $12/M out), though it has a higher output price than Mistral Large models ($2/M in, $6/M out).

Caveats

While highly capable, the high price point of $2/1M input and $8/1M output tokens means GPT-4.1 is not economical for simpler tasks. For workloads that do not require its vast context window, vision, or function-calling capabilities, OpenAI's much cheaper GPT-4.1 Nano or GPT-4o-mini models would be more cost-effective. Additionally, this model does not offer a free tier.

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

Key facts

Price basis
Official API price
Max output
33K tokens
Knowledge cutoff
2024-06-30
Listed on OpenRouter
2025-04-14
Tracked since
2026-05-07
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 $0.60
1M (small app) 1 0.5 $6.00
10M (mid scale) 10 5 $60.00
100M (large) 100 50 $600.00

※ 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)