OpenAI · Pricing & cost calculator

GPT-4o mini pricing

The cheapest credible OpenAI model. 80% of GPT-4o quality at 1/17th the input cost.

Input tokens

$0.00015

per 1,000 tokens

Output tokens

$0.00060

per 1,000 tokens

Context window

128,000

tokens max

Prices sourced from OpenAI's public API rate card. Last reviewed April 2026.

Calculate your GPT-4o mini spend

Drag the sliders. The math runs in your browser.

Per request

$0.000525

at 1,500/500 tokens

Monthly spend

$5.25

10,000 requests × $0.000525

When should you use GPT-4o mini?

  • High-volume classification
  • Chat assistants
  • Budget-conscious RAG

GPT-4o mini pricing FAQ

How much does GPT-4o mini cost per 1,000 tokens?

GPT-4o mini costs $0.00015 per 1,000 input tokens and $0.00060 per 1,000 output tokens as of the current OpenAI API pricing.

What is a cheaper alternative to GPT-4o mini?

GPT-4o mini is already one of the cheapest options in its tier. For budget-critical workloads, consider caching common requests to save more.

How can I reduce my GPT-4o mini API costs?

The three highest-leverage ways: (1) route requests to a cheaper model where possible, (2) cache identical requests so you don't pay twice for the same response, (3) set hard monthly budgets that block requests when exceeded. TrackCost automates all three at the gateway layer.

What's the context window for GPT-4o mini?

GPT-4o mini supports up to 128,000 tokens of context. For comparison with other models, use the TrackCost savings calculator.

Compare pricing across other models