OpenAI

GPT-4.1 mini API Pricing

OpenAI recommends starting with GPT-5-mini class models for more complex tasks instead.

Verified against OpenAI’s pricing page on 2026-07-02.

View source ↗

Facts

Legacy

Specs

  • FamilyGPT-4.1
  • API IDgpt-4.1-mini
  • ModalityMultimodal
  • Context window1M tokens
  • Max output32.8K tokens
  • Release dateNot published

Pricing (per 1M tokens)

  • Input$0.40 / 1M tokens
  • Output$1.60 / 1M tokens
  • Cached input$0.10 / 1M tokens
  • Cache write
  • Batch discount

Capabilities

vision, tool-use, function-calling, structured-outputs

Notes

OpenAI recommends starting with GPT-5-mini class models for more complex tasks instead.

Worked cost examples

Estimated monthly cost on three common usage shapes

WorkloadEst. monthly cost

Chatbot

800 input / 200 output tokens per request, 100,000 requests/month

$64.00

RAG pipeline

6,000 input / 700 output tokens per request, 30,000 requests/month

$105.60

Batch summarization

20,000 input / 1,500 output tokens per request, 5,000 requests/month

$52.00

Price history

Changes we have documented since we began tracking

No price changes recorded since we began tracking.

GPT-4.1 mini pricing FAQ

How much does GPT-4.1 mini cost per 1M tokens?
GPT-4.1 mini costs $0.40 per 1M input tokens and $1.60 per 1M output tokens.
How much does GPT-4.1 mini cost per request?
A typical request of 800 input and 200 output tokens costs about $0.00064 on GPT-4.1 mini.
Is GPT-4.1 mini cheaper than GPT-4.1?
GPT-4.1 mini is cheaper than GPT-4.1 on input tokens, by about 80%.
Does GPT-4.1 mini have cache pricing?
Yes — cached input reads cost $0.10 per 1M tokens.